NeurIPS 2024 Schedule

Filter Events

MON 9 DEC

noon

Registration (West)

(ends 6:00 PM)

TUE 10 DEC

7:30 a.m.

Registration (East & West)

(ends 6:00 PM)

8 a.m.

Affinity Workshop:

Black in AI

(ends 5:00 PM)

Affinity Workshop:

LatinX in AI

(ends 5:00 PM)

Affinity Workshop:

Women in Machine Learning

(ends 5:00 PM)

8:30 a.m.

Expo Talk Panel:

Transforming Asset Management Research with Generative AI: From Data Curation to Idea Generation and Implementation

(ends 9:30 AM)

Expo Talk Panel:

AI for Autonomous Driving at Scale

(ends 9:30 AM)

Expo Talk Panel:

AI Verification & Validation: Trends, Applications, and Challenges

(ends 9:30 AM)

Expo Talk Panel:

Onboarding Generative AI at the Edge: Challenges and Solutions from Industrial Research

(ends 9:30 AM)

Expo Talk Panel:

Incentivizing Collaborative AI: A Decentralized Approach to Scaling Machine Learning

(ends 9:30 AM)

Expo Talk Panel:

Commerce Foundation Model

(ends 9:30 AM)

Expo Talk Panel:

TikTok Symphony: AIGC Solution for Advertising

(ends 9:30 AM)

Expo Talk Panel:

Core Technical Interpretation and Best Practices of Responsible AI

(ends 9:30 AM)

Expo Talk Panel:

Compute: Past, Present & Future

(ends 9:30 AM)

9 a.m.

Creative AI Session 1 [9:00-12:00]

Chairs: Jean Oh · Marcelo Coelho · Lia Coleman · Yingtao Tian

s 9:00-12:00

[9:00] Charting the Shapes of Stories with Game Theory

[9:00] Designed by a computer, built by a designer. Learnings from the fabrication of a chair generated by a ML model

[9:00] Exploratory Study Of Human-AI Interaction For Hindustani Music

[9:00] Forrest Dance

[9:00] Narratron: A Storytelling AI for Shadow Play

[9:00] OpenOpenAI and Alternate Altman: Democratizing the Future of AI through Speculative Participatory Media

[9:00] Pushing the Boundaries of AI Art: an Immodest Proposal

[9:00] RECITYGEN Interactive and Generative Participatory Urban Design Tool with Latent Diffusion and Segment Anything

[9:00] Secure & Personalized Music-to-Video Generation via CHARCHA

[9:00] The Tale of Punyakoti: An AI-Enhanced Audio Experience

[9:00] Tuning Music Education: AI-Powered Personalization in learning music

[9:00] Typologies

(ends 12:00 PM)

Break:

Coffee Break

(ends 10:00 AM)

9:30 a.m.

Tutorial:

Causality for Large Language Models

(ends 12:00 PM)

Tutorial:

Watermarking for Large Language Models

(ends 12:00 PM)

Tutorial:

Evaluating Large Language Models - Principles, Approaches, and Applications

(ends 12:00 PM)

Tutorial:

Opening the Language Model Pipeline: A Tutorial on Data Preparation, Model Training, and Adaptation

(ends 12:00 PM)

Tutorial:

Dynamic Sparsity in Machine Learning: Routing Information through Neural Pathways

(ends 12:00 PM)

Tutorial:

Experimental Design and Analysis for AI Researchers

(ends 12:00 PM)

Tutorial:

Flow Matching for Generative Modeling

(ends 12:00 PM)

10 a.m.

Affinity Workshop:

Global South in AI

(ends 3:00 PM)

noon

Expo Workshop:

Active Training: Building Agentic Apps with Llama 3.2 and Llama Stack

(ends 1:30 PM)

Expo Workshop:

Hands-On AI for Everyone using Jumping Jacks, Drones, and Your Favorite Soccer Players

(ends 1:30 PM)

Expo Workshop:

Accelerating Edge AI: Optimizing and Deploying AI Models with Qualcomm AI Hub

(ends 1:30 PM)

Expo Workshop:

Knowledge-enhanced LLMs for Industry Verticals

(ends 1:30 PM)

Expo Workshop:

Sony’s Efficient Content Creation and Editing through Deep Generative Models

(ends 1:30 PM)

Expo Workshop:

AutoGen 0.4: Redefining Agentic AI Systems

(ends 1:30 PM)

Expo Workshop:

Accelerating AI Research and Development with AMD Instinct Systems

(ends 1:30 PM)

Expo Workshop:

AutoGluon 1.2: Advancing AutoML with Foundational Models and LLM Agents

(ends 1:30 PM)

Expo Talk Panel:

Demystify Financial Textual Data with LLMs

(ends 1:00 PM)

Break:

Lunch Break

(ends 1:30 PM)

1 p.m.

Creative AI Session 2 [1:00-4:00]

Chairs: Jean Oh · Marcelo Coelho · Lia Coleman · Yingtao Tian

s 1:00-4:00

[1:00] Charting the Shapes of Stories with Game Theory

[1:00] Designed by a computer, built by a designer. Learnings from the fabrication of a chair generated by a ML model

[1:00] Exploratory Study Of Human-AI Interaction For Hindustani Music

[1:00] Forrest Dance

[1:00] Narratron: A Storytelling AI for Shadow Play

[1:00] OpenOpenAI and Alternate Altman: Democratizing the Future of AI through Speculative Participatory Media

[1:00] Pushing the Boundaries of AI Art: an Immodest Proposal

[1:00] RECITYGEN Interactive and Generative Participatory Urban Design Tool with Latent Diffusion and Segment Anything

[1:00] Secure & Personalized Music-to-Video Generation via CHARCHA

[1:00] The Tale of Punyakoti: An AI-Enhanced Audio Experience

[1:00] Tuning Music Education: AI-Powered Personalization in learning music

[1:00] Typologies

(ends 4:00 PM)

Affinity Workshop:

Muslims in ML

(ends 5:00 PM)

Affinity Workshop:

New in ML

(ends 6:00 PM)

1:30 p.m.

Tutorial:

Beyond Decoding: Meta-Generation Algorithms for Large Language Models

(ends 4:00 PM)

Tutorial:

Out-of-Distribution Generalization: Shortcuts, Spuriousness, and Stability

(ends 4:00 PM)

Tutorial:

Generating Programmatic Solutions: Algorithms and Applications of Programmatic Reinforcement Learning and Code Generation

(ends 4:00 PM)

Tutorial:

Cross-disciplinary insights into alignment in humans and machines

(ends 4:00 PM)

Tutorial:

Advancing Data Selection for Foundation Models: From Heuristics to Principled Methods

(ends 4:00 PM)

Tutorial:

Sandbox for the Blackbox: How LLMs Learn Structured Data?

(ends 4:00 PM)

Tutorial:

PrivacyML: Meaningful Privacy-Preserving Machine Learning and How To Evaluate AI Privacy

(ends 4:00 PM)

3 p.m.

Expo Demonstration:

Deploying Personal AI Assistants with Voice, LLMs, RAG via OpenVINO™ on the AI PC

(ends 5:00 PM)

Expo Demonstration:

MemoMagnet: A fridge-magnet memo agent based on LLM

(ends 5:00 PM)

Expo Demonstration:

HPC-AI.COM: Unleashing the Power of High-Performance Cloud Computing for Large-Scale AI Model Training

(ends 5:00 PM)

Expo Demonstration:

Augmenting Driving Scenes by High Fidelity Generative Models

(ends 5:00 PM)

Expo Demonstration:

Diffusion Video Editing on Mobile

(ends 5:00 PM)

Expo Demonstration:

Deploying Cached Conditional Mixture-of-Experts LLMs on Mobile Devices with Memory Constraints

(ends 5:00 PM)

Expo Demonstration:

Low-Rank Adaptation (LoRA) for Large Vision Model on a Mobile Device

(ends 5:00 PM)

Expo Demonstration:

Large Multimodal Model running on a mobile device

(ends 5:00 PM)

Expo Demonstration:

Video Ocean: Filmmaking for everyone

(ends 5:00 PM)

Expo Demonstration:

Automatically Deploying a Sequence-to-Sequence Transformer for Accelerated Discovery on the IBM HERMES Project Chip

(ends 5:00 PM)

Expo Demonstration:

EvalAssist - An LLM-as-a-Judge Framework

(ends 5:00 PM)

Expo Demonstration:

Site Reliability Engineering Agent-101 for Incident Management

(ends 5:00 PM)

Expo Demonstration:

ProLLM: Program analysis driven, LLM assisted application modernization

(ends 5:00 PM)

Expo Demonstration:

Software Engineering Agent-102

(ends 5:00 PM)

Expo Demonstration:

Moving beyond chat: Enabling LLMs with intrinsic functions that give fine-grained control in application development

(ends 5:00 PM)

Expo Demonstration:

IBM Granite Vision Model for Enterprise AI

(ends 5:00 PM)

Expo Demonstration:

Trace: An LLM-powered End-to-end Optimization Framework of AI Workflow

(ends 5:00 PM)

Expo Demonstration:

Practices of Alibaba Cloud PAI (Platform for AI): An AI Native Large Models and AIGC Engineering Platform

(ends 5:00 PM)

4 p.m.

Expo Talk Panel:

Building industry-grade NLP applications for the financial domain

(ends 5:00 PM)

Expo Talk Panel:

Sequence Modeling in Financial Services

(ends 5:00 PM)

Expo Talk Panel:

Improving Foundation Models Using Human Data

(ends 5:00 PM)

Expo Talk Panel:

Colossal-AI: Breakthroughs in Efficient AI Training and Implementation

(ends 5:00 PM)

Expo Talk Panel:

AgentInstruct: Agentic flows are effective synthetic-data generators

(ends 5:00 PM)

Expo Talk Panel:

Granite Time Series Foundation Models

(ends 5:00 PM)

Expo Talk Panel:

Graph Reasoning in Large Language Models

(ends 5:00 PM)

Expo Talk Panel:

Training the Unprecedented Decart Diffusion World Simulator at scale on the Crusoe Cluster

(ends 5:00 PM)

Expo Talk Panel:

Symbolic AI and Foundation Models Integration towards Reliable and Trustworthy Industry-grade AI Systems

(ends 5:00 PM)

Break:

Coffee Break

(ends 4:30 PM)

5:30 p.m.

Invited Talk:

The Golem vs. Stone Soup: Understanding How Children Learn Can Help Us Understand And Improve AI

Alison Gopnik

(ends 6:15 PM)

6:30 p.m.

Welcome Reception:

Welcome Reception

(ends 8:00 PM)

Affinity Poster Session:

Affinity Joint Poster Session

(ends 8:00 PM)

WED 11 DEC

7:30 a.m.

Registration (East & West)

(ends 6:00 PM)

Break:

Coffee Break

(ends 8:30 AM)

8:30 a.m.

Invited Talk:

Toward Industrial Artificial Intelligence

Sepp Hochreiter

(ends 9:30 AM)

9:30 a.m.

Break:

Coffee Break

(ends 10:00 AM)

10 a.m.

Oral Session 1A: Neuroscience and Intepretability [10:00-11:00]

Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks

Trading Place for Space: Increasing Location Resolution Reduces Contextual Capacity in Hippocampal Codes

NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction

(ends 11:00 AM)

Oral Session 1B: Human-AI Interaction [10:00-11:00]

Human Expertise in Algorithmic Prediction

RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation

The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models

(ends 11:00 AM)

Oral Session 1C: Optimization and Learning Theory [10:00-11:00]

The Road Less Scheduled

Learning Diffusion at Lightspeed

Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity

(ends 11:00 AM)

Oral Session 1D: Learning Theory [10:00-11:00]

Generalization Error Bounds for Two-stage Recommender Systems with Tree Structure

Optimal Parallelization of Boosting

Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures

(ends 11:00 AM)

Affinity Workshop:

Queer in AI

(ends 5:00 PM)

Overflow for Oral Session 1D: Learning Theory [10:00-11:00]

(ends 11:00 AM)

Overflow for Oral Session 1C: Optimization and Learning Theory [10:00-11:00]

(ends 11:00 AM)

11 a.m.

Creative AI Session 3 [11:00-2:00]

Chairs: Jean Oh · Marcelo Coelho · Yingtao Tian · Lia Coleman

s 11:00-2:00

[11:00] AI Nüshu

[11:00] AI TrackMate: Finally, Someone Who Will Give Your Music More Than Just “Sounds Great!”

[11:00] Ambiguity in AI: The Paradox of Gender Neutrality

[11:00] break me, genAI

[11:00] Creative Loss: Ambiguity, Uncertainty and Indeterminacy

[11:00] Diff4Steer: Steerable Diffusion Prior for Generative Music Retrieval with Semantic Guidance

[11:00] Learning to Move, Learning to Play, Learning to Animate

[11:00] Ørigin

[11:00] Perfect Syntax

[11:00] Redefining Artistic Boundaries: A Real-Time Interactive Painting Robot for Musicians

[11:00] Rhythm Bots: A Sensitive Improvisational Environment

[11:00] SketcherX: AI-Driven Interactive Robotic drawing with Diffusion model and Vectorization Techniques

[11:00] Sketchy Collections: Exploring Digital Museum Collections by Drawing via CLIP

[11:00] Tesseract.art, a real-time generative AI interactive painting robot for multidisciplinary art

[11:00] The Visual-Riddles Gallery: A Challenge of AI, Creativity and Ambiguity

[11:00] Towards a ‘Non-Universal‘ Architecture: Designing with Others through Gestures (1:1 Scale)

[11:00] Towards Kinetic Manipulation of the Latent Space

(ends 2:00 PM)

Poster Session 1 West [11:00-2:00]

Posters 11:00-2:00

Fast Proxy Experiment Design for Causal Effect Identification

Likelihood-based differentiable structure learning

Sample Complexity of Interventional Causal Representation Learning

Mutli-Armed Bandits with Network Interference

Drift-Resilient TabPFN: In-Context Learning Distribution Shifts on Tabular Data

Linear Causal Representation Learning from Unknown Multi-node Interventions

Hybrid Global Causal Discovery with Local Search

Marginal Causal Flows for Validation and Inference

Benchmarking Counterfactual Image Generation

DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs

A Cross-Domain Benchmark for Active Learning

Comprehensive Framework for Curating Speech Datasets and Evaluating ASR Systems: A Case Study for the Polish Language

WildPPG: A Real-World PPG Dataset of Long Continuous Recordings

SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models

Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation

Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics

The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models

UltraEdit: Instruction-based Fine-Grained Image Editing at Scale

A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era

Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation

Muharaf: Manuscripts of Handwritten Arabic Dataset for Cursive Text Recognition

SHDocs: A dataset, benchmark, and method to efficiently generate high-quality, real-world specular highlight data with near-perfect alignment

GC-Bench: An Open and Unified Benchmark for Graph Condensation

Arctique: An artificial histopathological dataset unifying realism and controllability for uncertainty quantification

SolarCube: An Integrative Benchmark Dataset Harnessing Satellite and In-situ Observations for Large-scale Solar Energy Forecasting

MmCows: A Multimodal Dataset for Dairy Cattle Monitoring

Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads

Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?

DetectEval: Benchmarking LLM-Generated Text Detection in Real-World Scenarios

VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding

DivSafe: Evaluating the Generalization of LLM Safety Training Across Diverse Tasks and Prompt Types

CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset

Semi-Truths: A Large-Scale Dataset for Testing Robustness of AI-Generated Image Detectors

DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model

Game-Traversal-Benchmark: Evaluating Planning Abilities Of Large Language Models Via Traversing 2D Game Maps

DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA

Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming

AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery

Multi-Chain Graphs of Graphs: A New Paradigm in Blockchain Dataset

USCILab3D: A Large-scale, Long-term, Semantically Annotated Outdoor Dataset

FinBen: An Holistic Financial Benchmark for Large Language Models

RedPajama: an Open Dataset for Training Large Language Models

CryoBench: Datasets and Benchmarks for Heterogeneous Cryo-EM Reconstruction

A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes

Advancing Video Anomaly Detection: A Concise Review and a New Dataset

Einsum Benchmark: Enabling the Development of Next-Generation Tensor Execution Engines

BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack

HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models

A Benchmark Suite for Evaluating Neural Mutual Information Estimators on Unstructured Datasets

MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations

GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks

Code Agents are State of the Art Software Testers

Animal-Bench: Benchmarking Multimodal Video Models for Animal-centric Video Understanding

Reproducibility study of FairAC

ABCFair: an Adaptable Benchmark approach for Comparing Fairness Methods

FairJob: A Real-World Dataset for Fairness in Online Systems

Harnessing Multiple Correlated Networks for Exact Community Recovery

Replicability in Learning: Geometric Partitions and KKM-Sperner Lemma

AnonFair: A Flexible Toolkit for Algorithmic Fairness

Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context

Fair Secretaries with Unfair Predictions

Monoculture in Matching Markets

Mitigating Spurious Correlations via Disagreement Probability

Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learning

Perceptual Fairness in Image Restoration

Mitigating Biases in Blackbox Feature Extractors for Image Classification Tasks

Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks

Optimal Private and Communication Constraint Distributed Goodness-of-Fit Testing for Discrete Distributions in the Large Sample Regime

Differentiable Quantum Computing for Large-scale Linear Control

Learning from Snapshots of Discrete and Continuous Data Streams

Active Classification with Few Queries under Misspecification

On the Comparison between Multi-modal and Single-modal Contrastive Learning

Statistical-Computational Trade-offs for Density Estimation

A two-scale Complexity Measure for Deep Learning Models

Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithm

Active Learning of General Halfspaces: Label Queries vs Membership Queries

Group-wise oracle-efficient algorithms for online multi-group learning

Efficient Graph Matching for Correlated Stochastic Block Models

Contextual Multinomial Logit Bandits with General Value Functions

No-Regret Learning for Fair Multi-Agent Social Welfare Optimization

Improved Analysis for Bandit Learning in Matching Markets

The Many Faces of Optimal Weak-to-Strong Learning

Information-theoretic Generalization Analysis for Expected Calibration Error

Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis

Exploring the Precise Dynamics of Single-Layer GAN Models: Leveraging Multi-Feature Discriminators for High-Dimensional Subspace Learning

A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation

Optimal Parallelization of Boosting

Distributed Least Squares in Small Space via Sketching and Bias Reduction

On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory

Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classification

Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting

Optimal Multiclass U-Calibration Error and Beyond

On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice

Multimodal Conformal Prediction in Dynamic Environments

No-Regret M${}^{\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and NP-Hardness of Adversarial Full-Information Setting

Improved learning rates in multi-unit uniform price auctions

PRODuctive bandits: Importance Weighting No More

A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds

Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured training

Online Weighted Paging with Unknown Weights

Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization

Nonparametric Instrumental Variable Regression through Stochastic Approximate Gradients

BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning

Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation

Memory-Efficient LLM Training with Online Subspace Descent

Stochastic Extragradient with Flip-Flop Shuffling & Anchoring: Provable Improvements

SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization

Towards Exact Gradient-based Training on Analog In-memory Computing

The Road Less Scheduled

Stochastic contextual bandits with graph feedback: from independence number to MAS number

F-OAL: Foward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning

An Equivalence Between Static and Dynamic Regret Minimization

Learning Diffusion at Lightspeed

Derivatives of Stochastic Gradient Descent

Near-Optimal Methods for Convex Simple Bilevel Problems

Interpretable Lightweight Transformer via Unrolling of Learned Graph Smoothness Priors

Adaptive Proximal Gradient Method for Convex Optimization

A Simple and Optimal Approach for Universal Online Learning with Gradient Variations

Promoting Fairness Among Dynamic Agents in Online-Matching Markets under Known Stationary Arrival Distributions

A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem

Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations

Leveraging partial stragglers within gradient coding

LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing

SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead

Thinking Forward: Memory-Efficient Federated Finetuning of Language Models

The Collusion of Memory and Nonlinearity in Stochastic Approximation With Constant Stepsize

Addressing bias in online selection with limited budget of comparisons

Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization

Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad

Learning high-dimensional targets by two-parameter models and gradient flow

The Star Geometry of Critic-Based Regularizer Learning

Learning to Handle Complex Constraints for Vehicle Routing Problems

Rethinking the Capacity of Graph Neural Networks for Branching Strategy

IPM-LSTM: A Learning-Based Interior Point Method for Solving Nonlinear Programs

pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning

Near-Optimal Distributed Minimax Optimization under the Second-Order Similarity

Semi-Random Matrix Completion via Flow-Based Adaptive Reweighting

Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimization

Multi-Stage Predict+Optimize for (Mixed Integer) Linear Programs

Automatic Outlier Rectification via Optimal Transport

No Free Lunch Theorem and Black-Box Complexity Analysis for Adversarial Optimisation

Inversion-based Latent Bayesian Optimization

No-regret Bandit Exploration based on Soft Tree Ensemble Model

Fishers and Hessians of Continuous Relaxations

Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry

Differentially Private Set Representations

Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification

Dual Critic Reinforcement Learning under Partial Observability

Real-Time Recurrent Learning using Trace Units in Reinforcement Learning

Distributional Preference Alignment of LLMs via Optimal Transport

A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data

Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions

Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning

Doubly Mild Generalization for Offline Reinforcement Learning

Worst-Case Offline Reinforcement Learning with Arbitrary Data Support

BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning

Measuring Dejavu Memorization Efficiently

Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions

The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning

Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization

Time-Constrained Robust MDPs

No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO

Resolving Partial Observability in Decision Processes via the Lambda Discrepancy

Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL

Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning

Autoregressive Policy Optimization for Constrained Allocation Tasks

No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery

Diffusion-Reward Adversarial Imitation Learning

Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity

Learning Heuristics for Numeric Planning

Towards Effective Planning Strategies for Dynamic Opinion Networks

Measuring Mutual Policy Divergence for Multi-Agent Sequential Exploration

Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents

MADiff: Offline Multi-agent Learning with Diffusion Models

Integrating Suboptimal Human Knowledge with Hierarchical Reinforcement Learning for Large-Scale Multiagent Systems

Opponent Modeling based on Subgoal Inference

Melting Pot Contest: Charting the Future of Generalized Cooperative Intelligence

SustainDC: Benchmarking for Sustainable Data Center Control

ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination

BenchMARL: Benchmarking Multi-Agent Reinforcement Learning

SPO: Sequential Monte Carlo Policy Optimisation

Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing

Latent Plan Transformer: Planning as Latent Variable Inference

On Complexity of Teaching a Family of Linear Behavior Cloning Learners

Understanding Preference Learning Through the Lens of Coverage

RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning

Robot Policy Learning with Temporal Optiaml Transport Reward

LLM-based Skill Diffusion for Zero-shot Policy Adaptation

Stepwise Alignment for Constrained Language Model Policy Optimization

Regularized Conditional Diffusion Model for Multi-Task Preference Alignment

Beyond Optimism: Exploration With Partially Observable Rewards

Verified Safe Reinforcement Learning for Neural Network Dynamic Models

Is Score Matching Suitable for Estimating Point Processes?

Ad Auctions for LLMs via Retrieval Augmented Generation

Quantum algorithm for large-scale market equilibrium computation

Cross-Device Collaborative Test-Time Adaptation

Continuous Temporal Domain Generalization

Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning

Preference Learning of Latent Decision Utilities with a Human-like Model of Preferential Choice

Evidential Mixture Machines: Deciphering Multi-Label Correlations for Active Learning Sensitivity

Clustering with Non-adaptive Subset Queries

POCA: Partially Observable Cost-Aware Active-Learning

On the Convergence of Loss and Uncertainty-based Active Learning Algorithms

Learnability Matters: Active Learning for Video Captionin

Online Bayesian Persuasion Without a Clue

Multi-Winner Reconfiguration

Conformalized Credal Set Predictors

Multi-Agent Coordination via Multi-Level Communication

Policy Optimization for Robust Average Reward MDPs

Offline Multitask Representation Learning for Reinforcement Learning

Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning

Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently

Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces

The Value of Reward Lookahead in Reinforcement Learning

Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces

CoFie: Learning Compact Neural Surface Representations with Coordinate Fields

Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning

A Careful Examination of Large Language Model Performance on Grade School Arithmetic

Text to Blind Motion

GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring

Euclidean distance compression via deep random features

Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures

Breaking the curse of dimensionality in structured density estimation

Coherence-free Entrywise Estimation of Eigenvectors in Low-rank Signal-plus-noise Matrix Models

Deterministic Policies for Constrained Reinforcement Learning in Polynomial-Time

Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm

Towards Robust \emph{De Novo} Peptide Sequencing in Proteomics against Data Biases

Instance-adaptive Zero-shot Chain-of-Thought Prompting

Motion Graph Unleashed: A Novel Approach to Video Prediction

ROIDICE: Offline Return on Investment Maximization for Efficient Decision Making

Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels

Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms

Boosting Alignment for Post-Unlearning Text-to-Image Generative Models

Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification

Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning

TAPTRv2: Tracking Any Point with Transformers as Detection

Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning

RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks

Steganalysis on Digital Watermarking: Is Your Robustness a Maginot Line?

Derivative-enhanced Deep Operator Network

Variational Flow Matching for Graph Generation

SpeechAlign: Speech Language Models Can Self-Improve via Preference Optimization

Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling

Sharpness-Aware Minimization Activated Interactive Teaching Understanding and Optimization

Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learning

Rethinking Decoders for Transformer-based Semantic Segmentation: Compression is All You Need

LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling

SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network

Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset

SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion

PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher

Scaling Retrieval-Based Language Models with a Trillion-Token Datastore

ShowMaker: Creating High-Fidelity 2D Human Video via Fine-Grained Diffusion Modeling

Generalization Error Bounds for Two-stage Recommender Systems with Tree Structure

Implicit Curriculum in Procgen Made Explicit

Wings: Learning Multimodal LLMs without Text-only Forgetting

One-Step Diffusion Distillation through Score Implicit Matching

Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion

Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning

Proving Theorems Recursively

Simplified and Generalized Masked Diffusion for Discrete Data

Iterative Methods via Locally Evolving Set Process

AdaFlow

(ends 2:00 PM)

Poster Session 1 East [11:00-2:00]

Posters 11:00-2:00

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering

GFlowNet Assisted Biological Sequence Editing

Neural Krylov Iteration for Accelerating Linear System Solving

Test-time Aggregation for Collaborative Filtering

MotionTTT: 2D Test-Time-Training Motion Estimation for 3D Motion Corrected MRI

Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model

Information Re-Organization Improves Reasoning in Large Language Models

Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification

Learning Plaintext-Ciphertext Cryptographic Problems via ANF-based SAT Instance Representation

Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf

M3LEO: A Multi-Modal, Multi-Label Earth Observation Dataset Integrating Interferometric SAR and RGB Data

Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models

NeuralSteiner: Learning Steiner Tree for Overflow-avoiding Global Routing in Chip Design

PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition

LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation

GV-Rep: A Large-Scale Dataset for Genetic Variant Representation Learning

HEST-1k: A Dataset For Spatial Transcriptomics and Histology Image Analysis

Molecule Generation with Fragment Retrieval Augmentation

Disentangling Interpretable Factors of Variations with Supervised Independent Subspace Principal Component Analysis

Approximating mutual information of high-dimensional variables using learned representations

A probability contrastive learning framework for 3D molecular representation learning

Full-Atom Peptide Design with Geometric Latent Diffusion

How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval

MMSite: A Multi-modal Framework for the Identification of Active Sites in Proteins

Adaptive Visual Scene Understanding: Incremental Scene Graph Generation

DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation

Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis

MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting

LION: Linear Group RNN for 3D Object Detection in Point Clouds

LaSe-E2V: Towards Language-guided Semantic-Aware Event-to-Video Reconstruction

3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration

MutaPLM: Protein Language Modeling for Mutation Explanation and Engineering

Generative Modeling of Molecular Dynamics Trajectories

DRACO: A Denoising-Reconstruction Autoencoder for Cryo-EM

Kermut: Composite kernel regression for protein variant effects

Reprogramming Pretrained Target-Specific Diffusion Models for Dual-Target Drug Design

Memorize What Matters: Emergent Scene Decomposition from Multitraverse

Consensus Learning with Deep Sets for Essential Matrix Estimation

UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes

UMB: Understanding Model Behavior for Open-World Object Detection

2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution

Self-Supervised Adversarial Training via Diverse Augmented Queries and Self-Supervised Double Perturbation

Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting

NVRC: Neural Video Representation Compression

Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network

3D Gaussian Can Be Sparser Than You Thought: Efficient Rendering via Learned Fragment Pruning

DMesh: A Differentiable Mesh Representation

Unveiling the Power of Diffusion Features For Personalized Segmentation and Retrieval

Exploiting Descriptive Completeness Prior for Cross Modal Hashing with Incomplete Labels

Learning Optimal Lattice Vector Quantizers for End-to-end DNN Image Compression

Transformer Doctor: Diagnosing and Treating Vision Transformers

Soft Superpixel Neighborhood Attention

VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization

SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection

AverNet: All-in-one Video Restoration for Time-varying Unknown Degradations

3D Gaussian Splatting as Markov Chain Monte Carlo

VeXKD: The Versatile Integration of Cross-Modal Fusion and Knowledge Distillation for 3D Perception

Efficient Zero-Shot HOI Detection: Enhancing VLM Adaptation with Innovative Prompt Learning

Equivariant spatio-hemispherical networks for diffusion MRI deconvolution

Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data

Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection

Dynamic Multi-Object 3D Grounding with Language Informed Spatial Attention

Towards Croppable Implicit Neural Representations

FreeSplat: Generalizable 3D Gaussian Splatting Towards Free View Synthesis of Indoor Scenes

Self-Distilled Depth Refinement with Noisy Poisson Fusion

FineCLIP: Self-distilled Region-based CLIP for Better Fine-Grained Understanding

GSDF: 3DGS Meets SDF for Improved Neural Rendering and Reconstruction

Beware of Road Markings: A New Adversarial Patch Attack to Monocular Depth Estimation

LiT: Unifying LiDAR "Languages" with LiDAR Translator

Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis

ReGS: Reference-based Controllable Scene Stylization with Gaussian Splatting

Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation

Zero-shot Image Editing with Reference Imitation

DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation

SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models

UDPM: Upsampling Diffusion Probabilistic Models

Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation

Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance

Learning Action and Reasoning-Centric Image Editing from Videos and Simulation

START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation

AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation

Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition

Reproducibility study of “LICO: Explainable Models with Language-Image Consistency"

SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution

Make Fashion Real: Texture-preserving Rendered-to-Real Translation with Diffusion Models

pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization

IF-Font: Ideographic Description Sequence-Following Font Generation

FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification

ReFIR: Grounding Large Restoration Models with Retrieval Augmentation

HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach

Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation

OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding

One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos

Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNs

LESS: Label-Efficient and Single-Stage Referring 3D Instance Segmentation

Towards Flexible Visual Relationship Segmentation

ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

ActAnywhere: Subject-Aware Video Background Generation

NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing

Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control

4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models

COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing

X-Ray: A Sequential 3D Representation For Generation

MotionBooth: Motion-Aware Customized Text-to-Video Generation

LRM-Zero: Training Large Reconstruction Models with Synthesized Data

XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation

A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation

AdaPKC: PeakConv with Adaptive Peak Receptive Field for Radar Semantic Segmentation

E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding

A Trajectory-aware Spatio-temporal Graph for Video Salient Object Ranking

Towards Multi-Domain Learning for Generalizable Video Anomaly Detection

No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance

REDUCR: Robust Data Downsampling using Class Priority Reweighting

DAVED: Data Acquisition via Experimental Design for Data Markets

Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

TabEBM: A Tabular Data Augmentation Method with Class-Specific Energy-Based Models

Algorithmic progress in language models

Optimal and Approximate Adaptive Stochastic Quantization

Improving robustness to corruptions with multiplicative weight perturbations

Credal Deep Ensembles for Uncertainty Quantification

Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks

Towards Understanding the Mechanisms of Associative Memory in Transformers

Single Image Reflection Separation via Interactive Dual-Stream Transformers

Infinite-Dimensional Feature Interaction

DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation

3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability

A Layer-Wise Natural Gradient Optimizer for Training Deep Neural Networks

Neglected Hessian component explains mysteries in sharpness regularization

Learning 3D Equivariant Implicit Function with Patch-Level Pose-Invariant Representation

Scaling Laws and Compute-Optimal Training without Fixed Training Duration

Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers

Spectral Adapter: Fine-Tuning in Spectral Space

Linear Transformers are Versatile In-Context Learners

KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization

FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision

Mobility-LLM: Learning Visiting Intentions and Travel Preference from Human Mobility Data with Large Language Models

Learning symmetries via weight-sharing with doubly stochastic tensors

Bootstrapping Top-down Information for Self-modulating Slot Attention

Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning

Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularization

Algebraic Positional Encodings

TripletCLIP: Improving Compositional Reasoning of CLIP via Vision-Language Negatives

VMamba: Visual State Space Model

Decoupled Kullback-Leibler Divergence Loss

SAM-Guided Masked Token Prediction for 3D Scene Understanding

Transferable Adversarial Attacks on SAM and Its Downstream Models via Universal Meta Initialization and Gradient Robust Attacks

Constructing Semantics-Aware Adversarial Examples with Probabilistic Perspective

Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models

Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing

Adaptive Randomized Smoothing: Certifying Multi-Step Defences against Adversarial Examples

Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes

Benchmarking the Reasoning Robustness against Noisy Rationales in Chain-of-thought Prompting

Coded Computing: A Learning-Theoretic Framework

A teacher-teacher framework for clinical language representation learning

Learning diverse causally emergent representations from time series data

Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning

Understanding Transformer Reasoning Capabilities via Graph Algorithms

Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings

How does Gradient Descent Learn Features --- A Local Analysis for Regularized Two-Layer Neural Networks

Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization

Provable Benefits of Complex Parameterizations for Structured State Space Models

Transformers are Minimax Optimal Nonparametric In-Context Learners

On the Saturation Effects of Spectral Algorithms in Large Dimensions

Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks

The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains

Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame

What makes unlearning hard and what to do about it

Toward a Well-Calibrated Discrimination via Survival Outcome-Aware Contrastive Learning

ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

Categorical Flow Matching on Statistical Manifolds

Invariant Tokenization for Language Model Enabled Crystal Materials Generation

Stress-Testing Capability Elicitation With Password-Locked Models

Hierarchical Selective Classification

Learning Infinitesimal Generators of Continuous Symmetries from Data

AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks

The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof

Accelerating Inference with Fast and Expressive Sketch Structured Transform

CODA: A Correlation-Oriented Disentanglement and Augmentation Modeling Scheme for Better Resisting Subpopulation Shifts

Spiking Token Mixer: A event-driven friendly Former structure for spiking neural networks

Physics-Guided Neural Impulse Response Field via Implicit Wave Propagation Modeling

DreamScene: Layout-Guided 3D Scene Generation

Towards a Scalable Reference-Free Evaluation of Generative Models

Motion Generation based on Spatial-Temporal Joint Modeling

B'MOJO: Realizations of Hybrid State Space Models with Eidetic and Fading Memory

Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models

A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health

Stability and Generalizability in SDE Diffusion Models with Measure-Preserving Dynamics

Absorb & Escape: Overcoming Single Model Limitations in Generating Heterogeneous Genomic Sequences

Synergistic Dual Spatial-aware Generation of Image-to-text and Text-to-image

Equivariant Flow-Matching for Molecular Conformer Generation

Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences

Classification Diffusion Models: Revitalizing Density Ratio Estimation

Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generation

Evaluating the design space of diffusion-based generative models

Learning Diffusion Priors from Observations by Expectation Maximization

DiffGS: Functional Gaussian Splatting Diffusion

RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance

SyncTweedies: A General Generative Framework Based on Synchronized Diffusions

VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models

Local Curvature Smoothing with Stein's Identity for Efficient Score Matching

Energy-Based Modelling for Discrete and Mixed Data via Heat Equations on Structured Spaces

Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference

DeepDRK: Deep Dependency Regularized Knockoff for Feature Selection

Theoretical guarantees in KL for Diffusion Flow Matching

Generative Fractional Diffusion Models

Model-based Diffusion for Trajectory Optimization

Constrained Diffusion Models via Dual Training

Diffusion of Thought: Chain-of-Thought Reasoning in Diffusion Language Models

Learning Image Priors Through Patch-Based Diffusion Models for Solving Inverse Problems

Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise

DiffuPac: Contextual Mimicry in Adversarial Packets Generation via Diffusion Model

Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models

Neural Residual Diffusion Models for Deep Scalable Vision Generation

Taming Generative Diffusion Prior for Universal Blind Image Restoration

Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models

Your Diffusion Model is Secretly a Noise Classifier and Benefits from Contrastive Training

Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens

Where does In-context Learning \\ Happen in Large Language Models?

Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack

Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising

Coherent 3D Scene Diffusion From a Single RGB Image

PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference

Attack-Resilient Image Watermarking Using Stable Diffusion

Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning

Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure

Time-Varying LoRA: Towards Effective Cross-Domain Fine-Tuning of Diffusion Models

4Diffusion: Multi-view Video Diffusion Model for 4D Generation

ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization

Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents

How In-Context Learning Emerges from Training on Unstructured Data: The Role of Co-Occurrence, Positional Information, and Noise Structures

Accuracy is Not All You Need

Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning

Verified Code Transpilation with LLMs

Piecewise deterministic generative models

On the Identifiability of Hybrid Physics-Neural Models: Meta-Learning as a Solution

Can LLMs Solve Molecule Puzzles? A Multimodal Benchmark for Molecular Structure Elucidation

Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning

Multi-language Diversity Benefits Autoformalization

SemCoder: Training Code Language Models with Comprehensive Semantics

Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees

What do Graph Neural Networks learn? Insights from Tropical Geometry

Graphcode: Learning from multiparameter persistent homology using graph neural networks

Deep Homomorphism Networks

Spectral Graph Pruning Against Over-Squashing and Over-Smoothing

RAGraph: A General Retrieval-Augmented Graph Learning Framework

EGonc : Energy-based Open-Set Node Classification with substitute Unknowns

Graph Neural Networks and Arithmetic Circuits

[Re] GNNInterpreter: A probabilistic generative model-level explanation for Graph Neural Networks

[Re] Reproducibility Study of “Explaining Temporal Graph Models Through an Explorer-Navigator Framework"

CAPE: Context-Adaptive Positional Encoding for Length Extrapolation

Chain of Thoughtlessness? An Analysis of CoT in Planning

AutoCV: Empowering Reasoning with Automated Process Labeling via Confidence Variation

Are Graph Neural Networks Optimal Approximation Algorithms?

State Space Models on Temporal Graphs: A First-Principles Study

Mixture of Link Predictors on Graphs

DiGRAF: Diffeomorphic Graph-Adaptive Activation Function

The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks

Logical characterizations of recurrent graph neural networks with reals and floats

You May Better Reconstruct Anomalous over Normal Graphs: Analysis and a Simple Method for Reconstruction-based Graph-Level Anomaly Detection

GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules

Unitary Convolutions for Learning on Graphs and Groups

Online Relational Inference for Evolving Multi-agent Interacting System

Graph Neural Networks Do Not Always Oversmooth

Microstructures and Accuracy of Graph Recall by Large Language Models

Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks

Initialization is Critical to Whether Transformers Fit Composite Functions by Inference or Memorizing

Great Minds Think Alike: The Universal Convergence Trend of Input Salience

Conditional Density Estimation with Histogram Trees

LLM Circuit Analyses Are Consistent Across Training and Scale

DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models

Towards Human-AI Complementarity with Predictions Sets

Human Expertise in Algorithmic Prediction

RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation

Referring Human Pose and Mask Estimation In the Wild

Generative Semi-supervised Graph Anomaly Detection

Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval

Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model

Selective Explanations

Interpretable Image Classification with Adaptive Prototype-based Vision Transformers

The Representation Landscape of Few-Shot Learning and Fine-Tuning in Large Language Models

Model Lego: Creating Models Like Disassembling and Assembling Building Blocks

Refusal in Language Models Is Mediated by a Single Direction

Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling

SafeWorld: Geo-Diverse Safety Alignment

Evaluating and Eliciting Lateral Thinking of Large Language Models with Situation Puzzles

Semantics and Spatiality of Emergent Communication

Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum

Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers

Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms

LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search

Integrating Paralinguistics in Speech-Empowered Large Language Models for Natural Conversation

Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation

Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction

Aligning to Thousands of Varying Preferences via System Message Generalization

ContextCite: Attributing Model Generation to Context

To Believe or Not to Believe Your LLM

LLM-Check: Investigating Detection of Hallucinations in Large Language Models

Large language model validity via enhanced conformal prediction methods

Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies

Learning Hybrid Models for Digital Twins of Dynamical Systems

Revealing Distribution Discrepancy by Sampling Transfer in Unlabeled Data

Scalable DBSCAN with Random Projections

Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices

Diffeomorphic interpolation for efficient persistence-based topological optimization

Speeding up non-parametric regression via distribution compression

Density-based User Representation using Gaussian Process Regression for Multi-interest Personalized Retrieval

Neuronal Competition Groups with Supervised STDP for Spike-Based Classification

Quantifying the Gain in Weak-to-Strong Generalization

Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning

Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging

A Metalearned Neural Circuit for Nonparametric Bayesian Inference

A Practitioner's Guide to Real-World Continual Multimodal Pretraining

NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples

Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection

(FL)${}^2$: Overcoming Few Labels in Federated Semi-Supervised Learning

QBB: Quantization with Binary Bases for LLMs

On the cohesion and separability of average-link for hierarchical agglomerative clustering

Boosting Transferability and Discriminability for Time Series Domain Adaptation

$\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning

Learning from Offline Foundation Features with Tensor Augmentations

Learning Where to Edit Vision Transformers

Zero-Shot Transfer of Neural ODEs

DASH: Warm-Starting Neural Network Training Without Loss of Plasticity Under Stationarity

SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers

MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning

Probabilistic Conformal Distillation for Enhancing Missing Modality Robustness

Mitigating Object Hallucination via Concentric Causal Attention

Artemis: Towards Referential Understanding in Complex Videos

HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data

Dense Connector for MLLMs

SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models

Visual Perception by Large Language Model’s Weights

Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight

Why are Visually-Grounded Language Models Bad at Image Classification?

Continual Audio-Visual Sound Separation

RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions

HAWK: Learning to Understand Open-World Video Anomalies

Bridging 3D Scene and Large Language Models with Object Identifiers

Empowering Visible-Infrared Person Re-Identification with Large Foundation Models

Temporal Sentence Grounding with Relevance Feedback in Videos

What matters when building vision-language models?

MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence

Toward Robust Incomplete Multimodal Sentiment Analysis via Representation Factorization and Alignment

Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning

Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning

No Filter: Towards Cultural and Socioeconomic Diversity in Multimodal Systems

Generalization Beyond Data Imbalance: A Controlled Study on CLIP for Transferable Insights

Do CLIP Models Always Generalize Better than ImageNet Models?

Automated Multi-level Preference for MLLMs

Unified Lexical Representation for Interpretable Visual-Language Alignment

Deep Correlated Prompting for Visual Recognition with Missing Modalities

Evaluating alignment between humans and neural network representations in image-based learning tasks

NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction

Global Distortions from Local Rewards: Neural Coding Strategies in Path-Integrating Neural Systems

Neural networks with fast and bounded units learn flexible task abstractions

Inferring stochastic low-rank recurrent neural networks from neural data

Latent Learning Progress Drives Autonomous Goal Selection in Human Reinforcement Learning

LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model

Trading Place for Space: Increasing Location Resolution Reduces Contextual Capacity in Hippocampal Codes

Inference of Neural Dynamics Using Switching Recurrent Neural Networks

Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks

Learning Cortico-Muscular Dependence through Orthonormal Decomposition of Density Ratios

Model Based Inference of Synaptic Plasticity Rules

Active design of two-photon holographic stimulation for identifying neural population dynamics

Exploring Behavior-Relevant and Disentangled Neural Dynamics with Generative Diffusion Models

Flexible mapping of abstract domains by grid cells via self-supervised extraction and projection of generalized velocity signals

Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking

To Learn or Not to Learn, That is the Question

Compositional Generalization Across Distributional Shifts with Sparse Tree Operations

Latent Diffusion for Neural Spiking Data

Exploring the trade-off between deep-learning and explainable models for brain-machine interfaces

Multiple Physics Pretraining for Spatiotemporal Surrogate Models

Poseidon: Efficient Foundation Models for PDEs

Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs

Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling

Validating Climate Models with Spherical Convolutional Wasserstein Distance

Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks

A Recipe for Charge Density Prediction

Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing

Treeffuser: probabilistic prediction via conditional diffusions with gradient-boosted trees

An Efficient High-dimensional Gradient Estimator for Stochastic Differential Equations

Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks using the Marginal Likelihood

Preferential Normalizing Flows

Trajectory Diffusion for ObjectGoal Navigation

Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning

Entropy Coding of Large Unordered Data Structures

Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin Walk

Physics-Informed Variational State-Space Gaussian Processes

Nonstationary Sparse Spectral Permanental Process

Pre-trained Gaussian Processes for Bayesian Optimization

Minimizing Hyperspherical Energy for Diverse Deep Ensembling

Bayesian Adaptive Calibration and Optimal Design

Probabilistic size-and-shape functional mixed models

Conjugate Bayesian Two-step Change Point Detection for Hawkes Process

High Rank Path Development: an approach of learning the filtration of stochastic processes

EASI: Evolutionary Adversarial Simulator Identification for Sim-to-Real Transfer

Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving

Variational Distillation of Diffusion Policies into Mixture of Experts

DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection

ANT: Adaptive Noise Schedule for Time Series Diffusion Models

Scaling Law for Time Series Forecasting

TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables

Conformalized Time Series with Semantic Features

Con4m: Context-aware Consistency Learning Framework for Segmented Time Series Classification

"Studying How to Efficiently and Effectively Guide Models with Explanations" - A Reproducibility Study

An Analysis of Robustness of Non-Lipschitz Networks

Cooperate or Collapse: Emergence of Sustainability in a Society of LLM Agents

Rethinking LLM Memorization through the Lens of Adversarial Compression

Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models

Training for Stable Explanation for Free

Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models

Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation

Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously

ZeroMark: Towards Dataset Ownership Verification without Disclosing Dataset-specified Watermarks

Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack

The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection

Improved Generation of Adversarial Examples Against Safety-aligned LLMs

Federated Model Heterogeneous Matryoshka Representation Learning

Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models

Beyond Slow Signs in High-fidelity Model Extraction

Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets

LACIE: Listener-Aware Finetuning for Calibration in Large Language Models

RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models

Estimating Fréchet bounds for validating programmatic weak supervision

Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients

When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback

Optimistic Verifiable Training by Controlling Hardware Nondeterminism

Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models

Neural Model Checking

Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement

NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation

Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses

From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models

Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates

Bridging OOD Generalization and Detection: A Graph-Theoretic View

Pseudo-Private Data Guided Model Inversion Attacks

Dual-Personalizing Adapter for Federated Foundation Models

Vaccine: Perturbation-aware Alignment for Large Language Models Finetuning

Be Confident in What You Know: Bayesian Parameter Efficient Fine-Tuning of Foundation Models

Reconstruct and Match: Out-of-Distribution Robustness via Topological Homogeneity

Confidence Calibration of Classifiers with Many Classes

Large Language Model Unlearning via Embedding-Corrupted Prompts

4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on RDBs

$\texttt{ConflictBank}$: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMs

Near-Optimal Distributionally Robust RL with General $L_p$ Norms

GS-Hider: Hiding Messages into 3D Gaussian Splatting

Linear Regression using Heterogeneous Data Batches

DiTFastAtten: Accelerate Diffusion Transformers Through Efficient Attention Computation

Stratified Prediction-Powered Inference for Effective Hybrid Evaluation of Language Models

Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD

Any2Policy: Learning Visuomotor Policy with Any-Modality

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs

Probing the Decision Boundaries of In-context Learning in Large Language Models

ALOHA: from Attention to Likes – a unified mOdel for understanding HumAn responses to diverse visual content

The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models

Fairness without Harm: An Influence-Guided Active Sampling Approach

Satformer: Accurate and Robust Traffic Data Estimation for Satellite Networks

LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed Problems

In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization

State-free Reinforcement Learning

Déjà Vu Memorization in Vision–Language Models

QVAE-Mole: The Quantum VAE with Spherical Latent Variable Learning for 3-D Molecule Generation

Generative Hierarchical Materials Search

Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learning

EfficientCAPER: An End-to-End Framework for Fast and Robust Category-Level Articulated Object Pose Estimation

Blind Image Restoration via Fast Diffusion Inversion

Navigating Chemical Space with Latent Flows

Unified Covariate Adjustment for Causal Inference

ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence

Towards General Conceptual Model Editing via Adversarial Representation Engineering

Bayesian Identification of the Hamiltonian Inductive Bias in Dynamical Systems

Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation

Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model

Rethinking Optimal Transport in Offline Reinforcement Learning

GraphVis: Boosting LLMs with Visual Knowledge Graph Integration

Exploration by Learning Diverse Skills through Successor State Measures

Sequoia: Scalable and Robust Speculative Decoding

Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness

PERIA: Perceive, Reason, Imagine, Act via Holistic Language and Vision Planning for Manipulation

SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning

Transductive Active Learning: Theory and Applications

Gorilla: Teaching LLMs to Use Tools

(ends 2:00 PM)

noon

Expo Talk Panel:

Overcoming bottlenecks in AI development with flexible GPU cloud solutions

(ends 1:00 PM)

1 p.m.

Expo Talk Panel:

Deep tabular data

(ends 2:00 PM)

Expo Talk Panel:

Industrial Applications of Distributional Preference Alignment of LLMs via Optimal Transport

(ends 2:00 PM)

Expo Workshop:

Open-Sora: Democratizing Efficient Video Production for All

(ends 2:30 PM)

Expo Workshop:

AI for Enhanced Spacecraft Orientation

(ends 2:30 PM)

Expo Workshop:

Streamlining Computer Vision Data Annotation with Segment Anything 2.1

(ends 2:30 PM)

Expo Workshop:

Post-training LLMs: From Algorithms to Training Infrastructures

(ends 2:30 PM)

Break:

Lunch Break

(ends 2:30 PM)

2:30 p.m.

Invited Talk:

Invited Talk - FeiFei Li

Li Fei-Fei

(ends 3:30 PM)

3:30 p.m.

Oral Session 2A: Agents [3:30-4:30]

Enhancing Preference-based Linear Bandits via Human Response Time

Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making

AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents

(ends 4:30 PM)

Oral Session 2B: Reinforcement Learning [3:30-4:30]

Improving Environment Novelty Quantification for Effective Unsupervised Environment Design

The Sample-Communication Complexity Trade-off in Federated Q-Learning

Understanding, Rehearsing, and Introspecting: Learn a Policy from Textual Tutorial Books in Football Games

(ends 4:30 PM)

Oral Session 2C: Reinforcement Learning [3:30-4:30]

RL-GPT: Integrating Reinforcement Learning and Code-as-policy

Statistical Efficiency of Distributional Temporal Difference

SeeA*: Efficient Exploration-Enhanced A* Search by Selective Sampling

(ends 4:30 PM)

Oral Session 2D: Generative Models [3:30-4:30]

Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs

VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time

Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction

(ends 4:30 PM)

Overflow for Oral Session 2C: Reinforcement Learning [3:30-4:30]

(ends 4:30 PM)

Overflow for Oral Session 2B: Reinforcement Learning [3:30-4:30]

(ends 4:30 PM)

4:30 p.m.

Creative AI Session 4 [4:30-7:30]

Chairs: Jean Oh · Marcelo Coelho

s 4:30-7:30

[4:30] AI Nüshu

[4:30] AI TrackMate: Finally, Someone Who Will Give Your Music More Than Just “Sounds Great!”

[4:30] Ambiguity in AI: The Paradox of Gender Neutrality

[4:30] break me, genAI

[4:30] Creative Loss: Ambiguity, Uncertainty and Indeterminacy

[4:30] Diff4Steer: Steerable Diffusion Prior for Generative Music Retrieval with Semantic Guidance

[4:30] Learning to Move, Learning to Play, Learning to Animate

[4:30] Ørigin

[4:30] Perfect Syntax

[4:30] Redefining Artistic Boundaries: A Real-Time Interactive Painting Robot for Musicians

[4:30] Rhythm Bots: A Sensitive Improvisational Environment

[4:30] SketcherX: AI-Driven Interactive Robotic drawing with Diffusion model and Vectorization Techniques

[4:30] Sketchy Collections: Exploring Digital Museum Collections by Drawing via CLIP

[4:30] Tesseract.art, a real-time generative AI interactive painting robot for multidisciplinary art

[4:30] The Visual-Riddles Gallery: A Challenge of AI, Creativity and Ambiguity

[4:30] Towards a ‘Non-Universal‘ Architecture: Designing with Others through Gestures (1:1 Scale)

[4:30] Towards Kinetic Manipulation of the Latent Space

(ends 7:30 PM)

Expo Talk Panel:

Empirical Rigor at Scale – or, How Not to Fool Yourself

(ends 5:30 PM)

Expo Talk Panel:

Can AI Save Us From Ourselves? Generative AI and Content Moderation

(ends 5:30 PM)

Expo Talk Panel:

Mastering Distributed Training: Best Practices for Scalable Model Training

(ends 5:30 PM)

Expo Talk Panel:

MegaBeam-Mistral-7B: Advancing Long-Context Processing for Real-World AI Applications

(ends 5:30 PM)

Break:

Coffee Break

(ends 5:30 PM)

Expo Talk Panel:

Learnings From Teams Training Large-Scale Models: Challenges and Solutions for Monitoring at Hyperscale

(ends 5:30 PM)

Expo Talk:

EUREKA: Evaluating and Understanding Large Foundation Models

(ends 5:30 PM)

Expo Talk:

Logarithmic Math in accurate and efficient AI inference accelerators

(ends 5:30 PM)

Poster Session 2 West [4:30-7:30]

Posters 4:30-7:30

Causal Bandits for Linear Structural Equation Models

Causal-learn: Causal Discovery in Python

Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data

Higher-Order Causal Message Passing for Experimentation Under Unknown Interference

Intervention and Conditioning in Causal Bayesian Networks

DeepITE: Designing Variational Graph Autoencoders for Intervention Target Estimation

Causal Temporal Representation Learning with Nonstationary Sparse Transition

Proximal Causal Inference With Text Data

Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes

Identifiability Guarantees for Causal Disentanglement from Purely Observational Data

VastTrack: Vast Category Visual Object Tracking

RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content

AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents

FindingEmo: An Image Dataset for Emotion Recognition in the Wild

Causal Discovery from Event Sequences by Local Cause-Effect Attribution

Causal discovery in the presence of endogenous context variables

Do causal predictors generalize better to new domains?

Sample Efficient Bayesian Learning of Causal Graphs from Interventions

Ordering-Based Causal Discovery for Linear and Nonlinear Relations

Natural Counterfactuals With Necessary Backtracking

Marrying Causal Representation Learning with Dynamical Systems for Science

Through the Looking-Glass: Tracing Shifts in AI Data Consent across the Web

ActionAtlas: A VideoQA Benchmark for Fine-grained Action Recognition

StreamBench: Towards Benchmarking Continuous Improvement of Language Agents

Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias

PUZZLES: A Benchmark for Neural Algorithmic Reasoning

Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation

The Multimodal Universe: Enabling Large-Scale Machine Learning with 70TBs of Astronomical Scientific Data

IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos

NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking

SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution

BeanCounter: A low-toxicity, large-scale, and open dataset of business-oriented text

RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation

RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from Scripts

SLICE-100K: A Multimodal Dataset for Extrusion-based 3D Printing

SubjECTive-QA: A dataset for the subjective evaluation of answers in Earnings Call Transcripts (ECTs)

DECO-Bench: Unified Benchmark for Decoupled Task-Agnostic Synthetic Data Release

Evaluating Numerical Reasoning in Text-to-Image Models

NovoBench: Benchmarking Deep Learning-based \emph{De Novo} Sequencing Methods in Proteomics

MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding

ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Ablation Capability for Large Vision-Language Models

WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks

Noisy Ostracods: A Fine-Grained, Imbalanced Real-World Dataset for Benchmarking Robust Machine Learning and Label Correction Methods

Benchmarking LLMs via Uncertainty Quantification

SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation

Norms for Managing Datasets: A Systematic Review of NeurIPS Datasets

BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays

Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making

MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models

Nuclear Fusion Diamond Polishing Dataset

MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations

BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages

RealMAN: A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization

SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset

FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection

Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking

SureMap: Simultaneous mean estimation for single-task and multi-task disaggregated evaluation

Fairness-Aware Estimation of Graphical Models

Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images

Proportional Fairness in Non-Centroid Clustering

Towards Harmless Rawlsian Fairness Regardless of Demographic Prior

Fair and Welfare-Efficient Constrained Multi-Matchings under Uncertainty

Do Counterfactually Fair Image Classifiers Satisfy Group Fairness? -- A Theoretical and Empirical Study

FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Models

Reproducibility study of "Robust Fair Clustering: A Novel Fairness Attack and Defense Framework"

Reproducibility Study of "Robust Fair Clustering: A Novel Fairness Attack and Defense Framework"

Can LLMs Implicitly Learn Numeric Parameter Constraints in Data Science APIs?

Fairness-Aware Meta-Learning via Nash Bargaining

Improving Logits-based Detector without Logits from Black-box LLMs

On the Computational Landscape of Replicable Learning

Is Cross-validation the Gold Standard to Evaluate Model Performance?

Provable Benefit of Cutout and CutMix for Feature Learning

Oracle-Efficient Differentially Private Learning with Public Data

Distribution Learning with Valid Outputs Beyond the Worst-Case

Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer

On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries

Near-Optimality of Contrastive Divergence Algorithms

Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics

Derandomizing Multi-Distribution Learning

Online Estimation via Offline Estimation: An Information-Theoretic Framework

Solving Sparse \& High-Dimensional-Output Regression via Compression

Metric Transforms and Low Rank Representations of Kernels

The Price of Implicit Bias in Adversarially Robust Generalization

Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data

Credit Attribution and Stable Compression

Entropy testing and its application to testing Bayesian networks

4+3 Phases of Compute-Optimal Neural Scaling Laws

Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics

Robust Mixture Learning when Outliers Overwhelm Small Groups

Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization

An Adaptive Approach for Infinitely Many-armed Bandits under Generalized Rotting Constraints

Robust Neural Contextual Bandit against Adversarial Corruptions

Saliency-driven Experience Replay for Continual Learning

Online Non-convex Learning in Dynamic Environments

Sample Complexity of Posted Pricing for a Single Item

Communication Bounds for the Distributed Experts Problem

Online Control with Adversarial Disturbance for Continuous-time Linear Systems

Online Composite Optimization Between Stochastic and Adversarial Environments

Towards Efficient and Optimal Covariance-Adaptive Algorithms for Combinatorial Semi-Bandits

Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits

FUGAL: Feature-fortified Unrestricted Graph Alignment

Multidimensional Fractional Programming for Normalized Cuts

Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations

Semidefinite Relaxations of the Gromov-Wasserstein Distance

Nesterov acceleration despite very noisy gradients

SkipPredict: When to Invest in Predictions for Scheduling

From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization

Why Warmup the Learning Rate? Underlying Mechanisms and Improvements

An Improved Empirical Fisher Approximation for Natural Gradient Descent

The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms

Bandits with Abstention under Expert Advice

Piecewise-Stationary Bandits with Knapsacks

Revisiting Ensembling in One-Shot Federated Learning

CoBo: Collaborative Learning via Bilevel Optimization

BitDelta: Your Fine-Tune May Only Be Worth One Bit

FIARSE: Model-Heterogeneity Federated Learning via Importance-Aware Submodel Extraction

Fundamental Convergence Analysis of Sharpness-Aware Minimization

Collaboration! Towards Robust Neural Methods for Routing Problems

Generalization Bound and Learning Methods for Data-Driven Projections in Linear Programming

Learning to Solve Quadratic Unconstrained Binary Optimization in a Classification Way

A Novel Approach to Loss Landscape Characterization without Over-Parametrization

A Locally Optimal Portfolio for m-Sparse Sharpe Ratio Maximization

Nonconvex Federated Learning on Compact Smooth Submanifolds With Heterogeneous Data

Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction

Adam with model exponential moving average is effective for nonconvex optimization

Differentially Private Optimization with Sparse Gradients

Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training

Stepping Forward on the Last Mile

Approximation-Aware Bayesian Optimization

Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal

Stopping Bayesian Optimization with Probabilistic Regret Bounds

Minimizing UCB: a Better Local Search Strategy in Local Bayesian Optimization

Decision-Focused Learning with Directional Gradients

Localized Adaptive Risk Control

Conformal Inverse Optimization

Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network

Private Edge Density Estimation for Random Graphs: Optimal, Efficient and Robust

Disentangled Style Domain for Implicit $z$-Watermark Towards Copyright Protection

Sample-Efficient Private Learning of Mixtures of Gaussians

DataStealing: Steal Data from Diffusion Models in Federated Learning with Multiple Trojans

Exactly Minimax-Optimal Locally Differentially Private Sampling

LLM Dataset Inference: Detect Datasets, not Strings

Differential Privacy in Scalable General Kernel Learning via $K$-means Nystr{\"o}m Random Features

A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy

Nearly Tight Black-Box Auditing of Differentially Private Machine Learning

Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy

Reimagining Mutual Information for Enhanced Defense against Data Leakage in Collaborative Inference

Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach

Neural Combinatorial Optimization for Robust Routing Problem with Uncertain Travel Times

Genetic-guided GFlowNets for Sample Efficient Molecular Optimization

Off-Policy Selection for Initiating Human-Centric Experimental Design

Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs

Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning

GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning

Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning

An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning

On Differentially Private U Statistics

Encrypted Data Pruning for Confidential Training of Deep Neural Networks

Diversity from the Void: Training Adaptive Agents in Open-Ended Simulators

Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn

Multi-turn Reinforcement Learning with Preference Human Feedback

Federated Ensemble-Directed Offline Reinforcement Learning

Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning

Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs

Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control

Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning

Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games

A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning

Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning

Policy Mirror Descent with Lookahead

SeeA*: Efficient Exploration-Enhanced A* Search by Selective Sampling

SkiLD: Unsupervised Skill Discovery Guided by Local Dependencies

Belief-State Query Policies for Planning With Preferences Under Partial Observability

Parallelizing Model-based Reinforcement Learning Over the Sequence Length

Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference

A Generative Approach to Control Complex Physical Systems

Reward Machines for Deep RL in Noisy and Uncertain Environments

Learning to Cooperate with Humans using Generative Agents

Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning

RL-GPT: Integrating Reinforcement Learning and Code-as-policy

Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following

Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment

Learning World Models for Unconstrained Goal Navigation

Speculative Monte-Carlo Tree Search

Learn Incrementally from An Ongoing Trajectory: A Provable In-Trajectory Inverse Reinforcement Learning Framework

Focus On What Matters: Separated Models For Visual-Based RL Generalization

Multi-Reward Best Policy Identification

Externally Valid Policy Evaluation from Randomized Trials Using Additional Observational Data

Boosted Conformal Prediction Intervals

Initializing Services in Interactive ML Systems for Diverse Users

Adaptive Sampling for Efficient Softmax Approximation

Contracting with a Learning Agent

Efficiency of the First-Price Auction in the Autobidding World

Aggregating Quantitative Relative Judgments: From Social Choice to Ranking Prediction

Maximizing utility in multi-agent environments by anticipating the behavior of other learners

IODA: Instance-Guided One-shot Domain Adaptation for Super-Resolution

TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight

Cloud Object Detector Adaptation by Integrating Different Source Knowledge

CLIPCEIL: Boosting Domain Generalization for CLIP by Channel rEfinement and Image-text aLignment

Safe Time-Varying Optimization based on Gaussian Processes with Spatio-Temporal Kernel

Batched Energy-Entropy acquisition for Bayesian Optimization

Optimal Design for Human Feedback

Is Knowledge Power? Dissecting Information Asymmetry In Repeated Games

Putting Gale & Shapley to Work: Guaranteeing Stability Through Learning

Mechanism design augmented with output advice

Autobidder's Dilemma: Why More Sophisticated Autobidders Lead to Worse Auction Efficiency

Polynomial-Time Computation of Exact $\Phi$-Equilibria in Polyhedral Games

Dueling over Dessert, Mastering the Art of Repeated Cake Cutting

Policy Aggregation

A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement Learning

Improved Regret of Linear Ensemble Sampling

Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality

MetaCURL: Non-stationary Concave Utility Reinforcement Learning

Near-Optimal Approximation of Matrix Functions by the Lanczos Method

Adaptive Experimentation When You Can't Experiment

Learning from Noisy Labels via Conditional Distributionally Robust Optimization

Towards Fast Exact Conformalization of Generalized Parametric Estimation

Off-policy estimation with adaptively collected data: the power of online learning

Progressive Entropic Optimal Transport Solvers

Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem

Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification

Reinforcement Learning with Lookahead Information

Statistical Efficiency of Distributional Temporal Difference

Balancing Context Length and Mixing Times for Reinforcement Learning at Scale

Learning-Augmented Approximation Algorithms for Maximization Problems

The Space Complexity of Approximating Logistic Loss

MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations

FineStyle: Fine-grained Controllable Style Personalization for Text-to-image Models

B-ary Tree Push-Pull Method is Provably Efficient for Distributed Learning on Heterogeneous Data

Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers

Adaptable Logical Control for Large Language Models

The Sample-Communication Complexity Trade-off in Federated Q-Learning

Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing

Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency

Model Collapse Demystified: The Case of Regression

Transformers Represent Belief State Geometry in their Residual Stream

Spiking Transformer with Experts Mixture

MILP-StuDio: MILP Instance Generation via Block Structure Decomposition

SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain

VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance

Last-Iterate Convergence for Generalized Frank-Wolfe in Monotone Variational Inequalities

Matching the Statistical Query Lower Bound for $k$-Sparse Parity Problems with Stochastic Gradient Descent

Understanding, Rehearsing, and Introspecting: Learn a Policy from Textual Tutorial Books in Football Games

FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection

Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning

Distributional regression: CRPS-error bounds for model fitting, model selection and convex aggregation

Improving Generalization and Convergence by Enhancing Implicit Regularization

Wasserstein Gradient Boosting: A General Framework with Applications to Posterior Regression

On Weak Regret Analysis for Dueling Bandits

Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks

Sparsity-Agnostic Linear Bandits with Adaptive Adversaries

DiffPO: A causal diffusion model for predicting potential outcomes of treatments

VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks

Self-playing Adversarial Language Game Enhances LLM Reasoning

Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Generation

Stochastic Optimal Control Matching

Unified Generative and Discriminative Training for Multi-modal Large Language Models

Low Precision Local Training is Enough for Federated Learning

Generalized Eigenvalue Problems with Generative Priors

Entity Alignment with Noisy Annotations from Large Language Models

CAT: Coordinating Anatomical-Textual Prompts for Multi-Organ and Tumor Segmentation

(ends 7:30 PM)

Poster Session 2 East [4:30-7:30]

Posters 4:30-7:30

P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics

SplitNeRF: Split Sum Approximation Neural Field for Joint Geometry, Illumination, and Material Estimation

LLaMo: Large Language Model-based Molecular Graph Assistant

CoSW: Conditional Sample Weighting for Smoke Segmentation with Label Noise

LLMDFA: Analyzing Dataflow in Code with Large Language Models

Relationship Prompt Learning is Enough for Open-Vocabulary Semantic Segmentation

Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-shot Molecular Property Prediction

Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms

Evidential Stochastic Differential Equations for Time-Aware Sequential Recommendation

ProtGO: Function-Guided Protein Modeling for Unified Representation Learning

IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents

EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records

On Softmax Direct Preference Optimization for Recommendation

Arboretum: A Large Multimodal Dataset Enabling AI for Biodiversity

AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction

BEACON: Benchmark for Comprehensive RNA Tasks and Language Models

Reactzyme: A Benchmark for Enzyme-Reaction Prediction

ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention

Score-based 3D molecule generation with neural fields

MSA Generation with Seqs2Seqs Pretraining: Advancing Protein Structure Predictions

Neural Network Reparametrization for Accelerated Optimization in Molecular Simulations

Association Pattern-aware Fusion for Biological Entity Relationship Prediction

Bridge-IF: Learning Inverse Protein Folding with Markov Bridges

GENOT: A Neural Optimal Transport Framework for Single Cell Genomics

Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting

Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data

SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow

Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images

InterDreamer: Less Supervision for More Generalizable Text-Driven 3D Human-Object Interaction Synthesis

Is Your LiDAR Placement Optimized for 3D Scene Understanding?

PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding

Goal Conditioned Reinforcement Learning for Photo Finishing Tuning

Lexicon3D: Probing Visual Encoding Models for Complex 3D Scene Understanding

Subsurface Scattering for Gaussian Splatting

S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule Search

Multi-Scale Representation Learning for Protein Fitness Prediction

StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences

CLIP in Mirror: Disentangling text from visual images through reflection

LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Control and Rendering

ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Process

TopoFR: A Closer Look at Topology Alignment on Face Recognition

TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes

Parameter-Inverted Image Pyramid Networks

WildGaussians: 3D Gaussian Splatting In the Wild

Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting

LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment

MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks

PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyond

MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space

Efficient Temporal Action Segmentation via Boundary-aware Query Voting

Generalizable and Animatable Gaussian Head Avatar

GOMAA-Geo: GOal Modality Agnostic Active Geo-localization

Rethinking Imbalance in Image Super-Resolution for Efficient Inference

DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators

Splatter a Video: Video Gaussian Representation for Versatile Processing

VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction

Reconstruction of Manipulated Garment with Guided Deformation Prior

GenRec: Unifying Video Generation and Recognition with Diffusion Models

MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Step

Multi-times Monte Carlo Rendering for Inter-reflection Reconstruction

Latent Intrinsics Emerge from Training to Relight

AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection

Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models

DeBaRA: Denoising-Based 3D Room Arrangement Generation

Temporally Consistent Atmospheric Turbulence Mitigation with Neural Representations

ResAD: A Simple Framework for Class Generalizable Anomaly Detection

Rethinking No-reference Image Exposure Assessment from Holism to Pixel: Models, Datasets and Benchmarks

Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler

Generate Universal Adversarial Perturbations for Few-Shot Learning

Continual Learning in the Frequency Domain

Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning

Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model

Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks

How Control Information Influences Multilingual Text Image Generation and Editing?

AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation

Constant Acceleration Flow

In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment

Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion

Conditional Controllable Image Fusion

Aligning Diffusion Models by Optimizing Human Utility

Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation

Exploring Low-Dimensional Subspace in Diffusion Models for Controllable Image Editing

Codec Avatar Studio: Paired Human Captures for Complete, Driveable, and Generalizable Avatars

AirSketch: Generative Motion to Sketch

CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition

Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets

Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation

Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation

SpelsNet: Surface Primitive Elements Segmentation by B-Rep Graph Structure Supervision

Federated Black-Box Adaptation for Semantic Segmentation

Weakly Supervised Referring Image Segmentation via Progressive Comprehension

Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentation

SlimSAM: 0.1% Data Makes Segment Anything Slim

Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels

Uncertainty-aware Fine-tuning of Segmentation Foundation Models

Extending Video Masked Autoencoders to 128 frames

Streaming Long Video Understanding with Large Language Models

DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos

ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model

From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos

Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability

VideoTetris: Towards Compositional Text-to-Video Generation

Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation

VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time

Boosting Text-to-Video Generative Model with MLLMs Feedback

3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors

Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain

Video Token Merging for Long Video Understanding

Data Distribution Valuation

Enhancing Data Quality via Training Dynamics from Private Domains for Collaborative Fine-Tuning of Large Language Models

The AlCHEmist: Automated Labeling 500x CHEaper than LLM Data Annotators

$\texttt{dattri}$: A Library for Efficient Data Attribution

Image Textualization: An Automatic Framework for Generating Rich and Detailed Image Descriptions

Pearls from Pebbles: Improved Confidence Functions for Auto-labeling

CSPG: Crossing Sparse Proximity Graphs for Approximate Nearest Neighbor Search

Improving Neural ODE Training with Temporal Adaptive Batch Normalization

A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization

Are nuclear masks all you need for improved out-of-domain generalization? A closer look at cancer classification in histopathology.

CondTSF: One-line Plugin of Dataset Condensation for Time Series Forecasting

Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling

Unraveling the Gradient Descent Dynamics of Transformers

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis

QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion

Demystify Mamba in Vision: A Linear Attention Perspective

On the Use of Anchoring for Training Vision Models

BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference

Efficient Leverage Score Sampling for Tensor Train Decomposition

Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers

Amortized Eigendecomposition for Neural Networks

SlimGPT: Layer-wise Structured Pruning for Large Language Models

Graph Convolutions Enrich the Self-Attention in Transformers!

Set-Based Prompting: Provably Solving the Language Model Order Dependency Problem

Robustly overfitting latents for flexible neural image compression

Asynchronous Perception Machine for Test Time Training

Unified Insights: Harnessing Multi-modal Data for Phenotype Imputation via View Decoupling

Semi-Open 3D Object Retrieval via Hypergraph-Based Hierarchical Equilibrium Representation

Transferring disentangled representations: bridging the gap between synthetic and real images

Dual-Perspective Activation: Efficient Channel Denoising via Joint Forward-Backward Criterion for Artificial Neural Networks

A Gradient Accumulation Method for Dense Retriever under Memory Constraint

Learning Structure-Aware Representations of Dependent Types

Neural Isometries: Taming Transformations for Equivariant ML

D2R2: Diffusion-based Representation with Random Distance Matching for Tabular Few-shot Learning

LoCo: Learning 3D Location-Consistent Image Features with a Memory-Efficient Ranking Loss

Self-supervised Transformation Learning for Equivariant Representations

You Don't Need Data-Augmentations in Self-Supervised Learning

Achieving Domain-Independent Certified Robustness via Knowledge Continuity

Robust Graph Neural Networks via Unbiased Aggregation

Predicting the Performance of Foundation Models via Agreement-on-the-Line

DiffHammer: Rethinking the Robustness of Diffusion-Based Adversarial Purification

Precise Relational DNN Verification With Cross Executional Branching

Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification

Learning Structured Representations with Hyperbolic Embeddings

Improving Equivariant Model Training via Constraint Relaxation

Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models

Cross-video Identity Correlating for Person Re-identification Pre-training

Symmetries In-Context: Universal Self-Supervised Learning through Contextual World Models

On the Implicit Bias of Predicting in Latent Space in Self Supervised Learning

Your contrastive learning problem is secretly a distribution alignment problem

Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression

Reparameterization invariance in approximate Bayesian inference

Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models

Separations in the Representational Capabilities of Transformers and Recurrent Architectures

Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes

Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion

Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages

The Implicit Bias of Gradient Descent on Separable Multiclass Data

How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers

Implicit Bias of Mirror Flow on Separable Data

Average gradient outer product as a mechanism for deep neural collapse

Super Consistency of Neural Network Landscapes and Learning Rate Transfer

Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling

Can neural operators always be continuously discretized?

Provable Tempered Overfitting of Minimal Nets and Typical Nets

The Impact of Geometric Complexity on Neural Collapse in Transfer Learning

A Closer Look at Deep Learning Phenomena Through A Telescoping Lens

Non-asymptotic Convergence of Training Transformers for Next-token Prediction

Towards a theory of how the structure of language is acquired by deep neural networks

On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models

Ex Uno Pluria: Insights on Ensembling in Low Precision Number Systems

FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion

Mixture of Nested Experts: Adaptive Processing of Visual Tokens

SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training

Layer-Adaptive $\mathcal{H}_\infty$ State Pruning for Deep Diagonal State Space Model Compression

NoiseGPT: Label Noise Detection and Rectification through Probability Curvature

DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models

MatFormer: Nested Transformer for Elastic Inference

Toward Efficient Inference for Mixtures of Experts

Taming the Long Tail in Human Mobility Prediction

Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text

SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction

Dynamical Conditional Optimal Transport through Simulation-Free Flows

SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

GAVEL: Generating Games via Evolution and Language Models

Data Attribution for Text-to-Image Models by Unlearning Synthesized Images

DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion

TrajCLIP: Pedestrian trajectory prediction method using contrastive learning and idempotent networks

Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling

SpaceByte: Towards Deleting Tokenization from Large Language Modeling

MeshXL: Neural Coordinate Field for Generative 3D Foundation Models

GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling

Prediction-Powered Ranking of Large Language Models

Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication

Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation

Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series

Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems

ReplaceAnything3D: Text-Guided Object Replacement in 3D Scenes with Compositional Scene Representations

Generative Modelling of Structurally Constrained Graphs

On improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models

Divide-and-Conquer Posterior Sampling for Denoising Diffusion priors

Consistency Diffusion Bridge Models

Conditioning non-linear and infinite-dimensional diffusion processes

EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching

RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models

Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting

MIDGArD: Modular Interpretable Diffusion over Graphs for Articulated Designs

EM Distillation for One-step Diffusion Models

Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing

An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations

DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction

On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)

Understanding Hallucinations in Diffusion Models through Mode Interpolation

Video Diffusion Models are Training-free Motion Interpreter and Controller

Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models

Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention

Gradient Guidance for Diffusion Models: An Optimization Perspective

Diffusing Differentiable Representations

Association of Objects May Engender Stereotypes: Mitigating Association-Engendered Stereotypes in Text-to-Image Generation

LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language

Towards Global Optimal Visual In-Context Learning Prompt Selection

Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models

Exploring Prompting Methods for Mitigating Class Imbalance through Synthetic Data Generation with Large Language Models

In-Context Learning State Vector with Inner and Momentum Optimization

UDKAG: Augmenting Large Vision-Language Models with Up-to-Date Knowledge

Base of RoPE Bounds Context Length

Elo Uncovered: Robustness and Best Practices in Language Model Evaluation

Molecule Design by Latent Prompt Transformer

INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness

Risk-Averse Finetuning of Large Language Models

TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs

OccamLLM: Fast and Exact Language Model Arithmetic in a Single Step

Calibrating Reasoning in Language Models with Internal Consistency

Learning to Reason via Program Generation, Emulation, and Search

Can Graph Learning Improve Task Planning?

Mr.Bean: A Comprehensive Meta-Reasoning Benchmark for Analyzing Large Language Models

How Far Can Transformers Reason? The Locality Barrier and Inductive Scratchpad

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs

DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging

Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction

ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models

BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts

Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights

ProG: A Graph Prompt Learning Benchmark

IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors

TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering

On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks

Improving Neural Network Surface Processing with Principal Curvatures

DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks

Schur Nets: exploiting local structure for equivariance in higher order graph neural networks

FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference

Semantic Routing via Autoregressive Modeling

Probabilistic Graph Rewiring via Virtual Nodes

Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections

[Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models

Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch

Posture-Informed Muscular Force Learning for Robust Hand Pressure Estimation

Beyond Single Stationary Policies: Meta-Task Players as Naturally Superior Collaborators

UniGAD: Unifying Multi-level Graph Anomaly Detection

A Canonization Perspective on Invariant and Equivariant Learning

DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment

SpeAr: A Spectral Approach for Zero-Shot Node Classification

Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks

Continuous Product Graph Neural Networks

Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning

HGDL: Heterogeneous Graph Label Distribution Learning

shapiq: Shapley Interactions for Machine Learning

Training Data Attribution via Approximate Unrolling

Vision Mamba Mender

Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory

I Bet You Did Not Mean That: Semantic Importance of Any Classifier via Betting

One Sample Fits All: Approximating All Probabilistic Values Simultaneously and Efficiently

What Makes Safety Fine-tuning Methods Safe? A Mechanistic Study

A Concept-Based Explainability Framework for Large Multimodal Models

Parallel Backpropagation for Shared-Feature Visualization

Iteration Head: A Mechanistic Study of Chain-of-Thought

Coarse-to-Fine Concept Bottleneck Models

Interpretable Concept-Based Memory Reasoning

Reward Learning from Human Demonstration Improves Supervised Fine-tuning for LLM Alignment

Model Fusion through Bayesian Optimization in Language Model Fine-Tuning

LoFiT: Localized Fine-tuning on LLM Representations

WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models

D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment

FASTopic: A Fast, Adaptive, Stable, and Transferable Topic Modeling Paradigm

Block Transformer: Global-to-Local Language Modeling for Fast Inference

OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI

Symmetry Discovery Beyond Affine Transformations

Algorithmic Capabilities of Random Transformers

Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents

Enhancing LLM’s Cognition via Structurization

FLAME : Factuality-Aware Alignment for Large Language Models

Enhancing Large Language Models through Adaptive Tokenizers

Decoding-Time Language Model Alignment with Multiple Objectives

Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models

How Do Large Language Models Acquire Factual Knowledge During Pretraining?

Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation

REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR

Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models

SILENCE: Protecting privacy in offloaded speech understanding on wimpy devices

Gradients of Functions of Large Matrices

EMR-Merging: Tuning-Free High-Performance Model Merging

DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection

Mind the Gap Between Prototypes and Images in Cross-domain Few-shot Classification

On the Stability and Generalization of Meta-Learning

Model Sensitivity Aware Continual Learning

DOFEN: Deep Oblivious Forest ENsemble

Soft Tensor Product Representations for Fully Continuous, Compositional Visual Representations

Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning

Inverse M-Kernels for Linear Universal Approximators of Non-Negative Functions

The Minimax Rate of HSIC Estimation for Translation-Invariant Kernels

Learning to Embed Distributions via Maximum Kernel Entropy

The Selective $G$-Bispectrum and its Inversion: Applications to $G$-Invariant Networks

RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier

CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions

KFNN: K-Free Nearest Neighbor For Crowdsourcing

Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models

II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models

Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning

SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation

Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited Modalities

Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs

FlexCap: Describe Anything in Images in Controllable Detail

Facilitating Multimodal Classification via Dynamically Learning Modality Gap

What Factors Affect Multi-modal In-Context Learning? An In-Depth Exploration

Can Transformers Smell Like Humans?

Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation

Balancing Multimodal Learning with Classifier-guided Gradient Modulation

A Rank-Based Metric for Evaluating Large Language Models

Membership Inference Attacks against Large Vision-Language Models

InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD

Towards Robust Multimodal Sentiment Analysis with Incomplete Data

Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing

Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models

CigTime: Corrective Instruction Generation Through Inverse Motion Editing

CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models

DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor

Provably Optimal Memory Capacity for Modern Hopfield Models

Learning Conjunctive Representations

A Unifying Normative Framework of Decision Confidence

Divergences between Language Models and Human Brains

Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning

Structured flexibility in recurrent neural networks via neuromodulation

Binding in hippocampal-entorhinal circuits enables compositionality in cognitive maps

Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem

The motion planning neural circuit in goal-directed navigation as Lie group operator search

EnOF: Training Accurate Spiking Neural Networks via Enhancing the Output Feature Representation

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics

Biologically-Motivated Learning Model for Instructed Visual Processing

Understanding the expressivity and trainability of Fourier Neural Operator

The Challenges of the Nonlinear Regime for Physics-Informed Neural Netowrks

MG-Net: Automatically Customize QAOA with Quantum Hardware Constraints for Enhanced Performance

SEA: State-Exchange Attention for High-Fidelity Physics-Based Transformers

DEL: Discrete Element Learner for Learning 3D Dynamics from 2D Observations

Identifying spatio-temporal relations between anomalies and extreme events

Integrating GNN and Neural ODEs for Estimating Two-Body Interactions in Mixed-Species Collective Motion

Towards Universal Mesh Movement Networks

Physics-Constrained Comprehensive Optical Neural Networks

Controlled maximal variability along with reliable performance in recurrent neural networks

Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation

Advancing Spiking Neural Networks for Sequential Modeling through Central Pattern Generators

DiffusionPDE: Generative PDE-Solving under Partial Observation

Fearless Stochasticity in Expectation Propagation

HyperDDPM: Estimating Epistemic and Aleatoric Uncertainty with a Single Model

Random Cycle Coding: Lossless Compression of Cluster Assignments via Bits-Back Coding

Small coresets via negative dependence: DPPs, linear statistics, and concentration

Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems

Block Sparse Bayesian Learning: A Diversified Scheme

Generating Origin-Destination Matrices in Neural Spatial Interaction Models

Sample-efficient Simulation-based Inference for Urban Travel Demand Calibration

Cost-aware Bayesian optimization via the Pandora's box Gittins index

Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors

Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation

DeformableTST: Transformer for Time Series Forecasting without Over-reliance on Patching

Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series

Unlocking the Potential of Global Human Expertise

Probing Social Bias in Labor Market Text Generation by ChatGPT: A Masked Language Model Approach

Can Large Language Model Agents Simulate Human Trust Behavior?

DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization

Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees

Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution

QueST: Self-Supervised Skill Abstractions for Learning Continuous Control

BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction

BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO

OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding

Rethinking Fourier Transform for Long-term Time Series Forecasting: A Basis Functions Perspective

Addressing Spatial-Temporal Heterogeneity: General Mixed Time Series Analysis via Latent Continuity Recovery and Alignment

AutoTimes: Autoregressive Time Series Forecasters via Large Language Models

Frequency Adaptive Normalization For Non-stationary Time Series Forecasting

Exploiting Representation Curvature for Boundary Detection in Time Series

SARAD: Spatial Association-Aware Anomaly Detection and Diagnosis for Multivariate Time Series

PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecasting

Segment, Shuffle, and Stitch: A Simple Mechanism for Improving Time-Series Representations

Evaluating Copyright Takedown Methods for Language Models

UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models

Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights

Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutions

Uncovering Safety Risks of Large Language Models through Concept Activation Vector

A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis

Typicalness-Aware Learning for Failure Detection

On scalable oversight with weak LLMs judging strong LLMs

Semantic Density: Uncertainty Quantification in Semantic Space for Large Language Models

Rejection via Learning Density Ratios

What Makes Partial-Label Learning Algorithms Effective?

Exploiting LLM Quantization

WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off

Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning

Kernel PCA for Out-of-Distribution Detection

Human-Assisted Out-of-Distribution Generalization and Detection

Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor

Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line

Selective Generation for Language Models

Certified Adversarial Robustness via Randomized $\alpha$-Smoothing for Regression Models

LT-Defense: Searching-free Backdoor Defense via Exploiting Long-Tailed Effect

RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation

Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation

Few-Shot Adversarial Prompt Learning on Vision-Language Models

Learning the Latent Causal Structure for Modeling Label Noise

SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functions

Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes

Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation

Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models

On the Optimality of Dilated Entropy and Lower Bounds for Online Learning in Extensive-Form Games

Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models

The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning

Expressive Gaussian Human Avatars from Monocular RGB Video

Accelerating Best-of-N via Speculative Rejection

Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model

DiffuserLite: Towards Real-time Diffusion Planning

Learning-Augmented Algorithms with Explicit Predictors

FlexMol: A Flexible Toolkit for Benchmarking Molecular Relational Learning

Task Me Anything

LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding

Amortized Active Causal Induction with Deep Reinforcement Learning

A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers

End-to-end Learnable Clustering for Intent Learning in Recommendation

Fully Unconstrained Online Learning

Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models

DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion

ARC: A Generalist Graph Anomaly Detector with In-Context Learning

A Local Method for Satisfying Interventional Fairness with Partially Known Causal Graphs

ST$_k$: A Scalable Module for Solving Top-k problems

Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training

Aligning Audio-Visual Joint Representations with an Agentic Workflow

Achieving Tractable Minimax Optimal Regret in Average Reward MDPs

Truthful High Dimensional Sparse Linear Regression

Normalization and effective learning rates in reinforcement learning

Provably Efficient Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs

FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention

Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse Experts

Personalized Federated Learning via Feature Distribution Adaptation

Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis

LoRA-GA: Low-Rank Adaptation with Gradient Approximation

Reproducibility of predictive networks for mouse visual cortex

Improving Environment Novelty Quantification for Effective Unsupervised Environment Design

Unveiling The Matthew Effect Across Channels: Assessing Layer Width Sufficiency via Weight Norm Variance

One-Step Effective Diffusion Network for Real-World Image Super-Resolution

Segment Anything without Supervision

Enhancing Preference-based Linear Bandits via Human Response Time

TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy

Approximately Equivariant Neural Processes

Advantage-Aware Policy Optimization for Offline Reinforcement Learning

3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection

Induced Model Matching: Restricted Models Help Train Full-Featured Models

CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics

Sequential Harmful Shift Detection Without Labels

Large Language Models Play StarCraft II:Benchmarks and A Chain of Summarization Approach

PaCE: Parsimonious Concept Engineering for Large Language Models

End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning

A Theoretical Perspective for Speculative Decoding Algorithm

ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer

Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series

The Impact of Initialization on the Finetuning Dynamics in LoRA

MiniCache: KV Cache Compression in Depth Dimension for Large Language Models

Self-Play Fine-tuning of Diffusion Models for Text-to-image Generation

Structural Inference of Dynamical Systems with Conjoined State Space Models

(ends 7:30 PM)

7:30 p.m.

THU 12 DEC

7:30 a.m.

Registration (East & West)

(ends 6:00 PM)

Break:

Coffee Break

(ends 8:30 AM)

8:30 a.m.

Invited Talk:

Invited Talk - Lidong Zhou

Lidong Zhou

(ends 9:30 AM)

9:30 a.m.

Break:

Coffee Break

(ends 10:00 AM)

10 a.m.

Oral Session 3A: Generative Models [10:00-11:00]

Not All Tokens Are What You Need for Pretraining

Return of Unconditional Generation: A Self-supervised Representation Generation Method

HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning

(ends 11:00 AM)

Oral Session 3B: Natural Language Processing [10:00-11:00]

Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions

Solving Intricate Problems with Human-like Decomposition and Rethinking

Questioning the Survey Responses of Large Language Models

(ends 11:00 AM)

Oral Session 3C: Natural Language Processing [10:00-11:00]

PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression

LLM Evaluators Recognize and Favor Their Own Generations

Unlocking the Boundaries of Thought: A Reasoning Granularity Framework to Quantify and Optimize Chain-of-Thought

(ends 11:00 AM)

Oral Session 3D: Natural Language Processing [10:00-11:00]

Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation

DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs

Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models

(ends 11:00 AM)

Overflow for Oral Session 3C: Natural Language Processing [10:00-11:00]

(ends 11:00 AM)

Overflow for Oral Session 3B: Natural Language Processing [10:00-11:00]

(ends 11:00 AM)

11 a.m.

Creative AI Session 5 [11:00-2:00]

Chairs: Jean Oh · Marcelo Coelho · Lia Coleman · Yingtao Tian

s 11:00-2:00

[11:00] Autonoetic Intelligence: A Human-AI System for Being with the Time Being

[11:00] Be the Beat: AI-Powered Boombox for Music Generation from Freestyle Dance

[11:00] Dialogue with the Machine and Dialogue with the Art World: A Method for Evaluating AI as a Tool for Creativity

[11:00] DreamLLM-3D: Affective Dream Reliving using Large Language Model and 3D Generative AI

[11:00] E(*)star, navigating the landscape of emotion language

[11:00] Exposed to AI: The Paradox of Trust and Vulnerability in Human-Machine Interactions

[11:00] For All Mankind

[11:00] Memoroscope

[11:00] Navigating Ambiguity: Investigative gameplay with a Large Language Object in "A Mystery for You"

[11:00] Neural Artefact Black

[11:00] Neural MONOBLOC Black

[11:00] Neural Tides: Oceanic Neural Granular Synthesizer

[11:00] Poespin-Wherever your body reach, there is a poetry

[11:00] Symbiosis

[11:00] Text2Tradition: From Epistemological Tensions to AI-Mediated Cultural Co-Creation

(ends 2:00 PM)

Poster Session 3 West [11:00-2:00]

Posters 11:00-2:00

Complete Graphical Criterion for Sequential Covariate Adjustment in Causal Inference

Efficiently Learning Significant Fourier Feature Pairs for Statistical Independence Testing

Structured Learning of Compositional Sequential Interventions

Smoke and Mirrors in Causal Downstream Tasks

Covariate Shift Corrected Conditional Randomization Test

Efficient Policy Evaluation Across Multiple Different Experimental Datasets

Qualitative Mechanism Independence

Causal Contrastive Learning for Counterfactual Regression Over Time

Learning Discrete Concepts in Latent Hierarchical Models

Is the MMI Criterion Necessary for Explanation? Degenerating Non-causal Features to Plain Noise

The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding

T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition

The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning

Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand

Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits

Disentangled Representation Learning in Non-Markovian Causal Systems

When to Act and When to Ask: Policy Learning With Deferral Under Hidden Confounding

From Causal to Concept-Based Representation Learning

Unveiling the Potential of Robustness in Selecting Conditional Average Treatment Effect Estimators

Identifying General Mechanism Shifts in Linear Causal Representations

End-To-End Causal Effect Estimation from Unstructured Text Data

Benchmarking Estimators for Natural Experiments: A Novel Dataset and a Doubly Robust Algorithm

Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge

OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset

ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos

SciCode: A Research Coding Benchmark Curated by Scientists

cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Papers

Sim2Real-Fire: A Multi-modal Simulation Dataset for Forecast and Backtracking of Real-world Forest Fire

Infer Induced Sentiment of Comment Response to Video: A New Task, Dataset and Baseline

Muscles in Time: Learning to Understand Human Motion In-Depth by Simulating Muscle Activations

Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models

Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark

OAM-TCD: A globally diverse dataset of high-resolution tree cover maps

Towards General Loop Invariant Generation: A Benchmark of Programs with Memory Manipulation

Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

Archaeoscape: Bringing Aerial Laser Scanning Archaeology to the Deep Learning Era

SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark

DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation

The State of Data Curation at NeurIPS: An Assessment of Dataset Development Practices in the Datasets and Benchmarks Track

AFBench: A Large-scale Benchmark for Airfoil Design

APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets

When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models

AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries

$\texttt{pfl-research}$: simulation framework for accelerating research in Private Federated Learning

Off to new Shores: A Dataset & Benchmark for (near-)coastal Flood Inundation Forecasting

Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking

WikiDBs: A Large-Scale Corpus Of Relational Databases From Wikidata

Implicit Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes

TaskBench: Benchmarking Large Language Models for Task Automation

Assemblage: Automatic Binary Dataset Construction for Machine Learning

μBench: A Microscopy Benchmark for Vision-Language Understanding

ViLCo-Bench: VIdeo Language COntinual learning Benchmark

APEBench: A Benchmark for Autoregressive Neural Emulators of PDEs

OpenCDA-Loop: A Closed-loop Benchmarking Platform for End-to-end Evaluation of Cooperative Perception

MARPLE: A Benchmark for Long-Horizon Inference

MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset

User-item fairness tradeoffs in recommendations

On Socially Fair Low-Rank Approximation and Column Subset Selection

Multi-Group Proportional Representation

Prejudice and Volatility: A Statistical Framework for Measuring Social Discrimination in Large Language Models

Reproducibility Study of "ITI-GEN: Inclusive Text-to-Image Generation"

Reproducibility Study: Equal Improvability: A New Fairness Notion Considering the Long-Term Impact

Deep Learning in Medical Image Registration: Magic or Mirage?

Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions

Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking

Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks

Mercury: A Code Efficiency Benchmark for Code Large Language Models

Fair GLASSO: Estimating Fair Graphical Models with Unbiased Statistical Behavior

Interpolating Item and User Fairness in Multi-Sided Recommendations

GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting

Tight Bounds for Learning RUMs from Small Slates

Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms

Fast Rates for Bandit PAC Multiclass Classification

Error Analysis of Spherically Constrained Least Squares Reformulation in Solving the Stackelberg Prediction Game

Dimension-free deterministic equivalents for random feature regression

Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization

Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts

Tolerant Algorithms for Learning with Arbitrary Covariate Shift

Continual Learning with Global Alignment

Adversarially Robust Multi-task Representation Learning

Sample-Efficient Agnostic Boosting

Optimal Algorithms for Augmented Testing of Discrete Distributions

Generalization Bounds via Conditional $f$-Information

Analytic Nonlinear Dynamical System Identification with Non-asymptotic Guarantees

Soft ascent-descent as a stable and flexible alternative to flooding

Cardinality-Aware Set Prediction and Top-$k$ Classification

Cryptographic Hardness of Score Estimation

Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms

Trade-Offs of Diagonal Fisher Information Matrix Estimators

Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning

Local and Adaptive Mirror Descents in Extensive-Form Games

Gradient Methods for Online DR-Submodular Maximization with Stochastic Long Term Constraints

Optimal Algorithms for Online Convex Optimization with Adversarial Constraints

Optimal Top-Two Method for Best Arm Identification and Fluid Analysis

Optimal Multi-Fidelity Best-Arm Identification

Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints

Improved Algorithms for Contextual Dynamic Pricing

Regret Minimization in Stackelberg Games with Side Information

Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations

Binary Search Tree with Distributional Predictions

Approximately Pareto-optimal Solutions for Bi-Objective k-Clustering

Accelerating Matroid Optimization through Fast Imprecise Oracles

John Ellipsoids via Lazy Updates

S-SOS: Stochastic Sum-Of-Squares for Parametric Polynomial Optimization

Functional Bilevel Optimization for Machine Learning

Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach

First-Order Minimax Bilevel Optimization

Unveiling LoRA Intrinsic Ranks via Salience Analysis

Penalty-based Methods for Simple Bilevel Optimization under Hölderian Error Bounds

Weight decay induces low-rank attention layers

Boundary Decomposition for Nadir Objective Vector Estimation

Mirror and Preconditioned Gradient Descent in Wasserstein Space

Online Budgeted Matching with General Bids

HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation

Learning-Augmented Dynamic Submodular Maximization

Controlling Continuous Relaxation for Combinatorial Optimization

Sketching for Distributed Deep Learning: A Sharper Analysis

Randomized Minor-Value Rectification: A Novel Matrix Sparsification Algorithm for Solving Constrained Optimizations in Cancer Radiation Therapy

Implicit Regularization of Decentralized Gradient Descent for Sparse Regression

Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity

Resource-Aware Federated Self-Supervised Learning with Global Class Representations

Stabilized Proximal Point Methods for Federated Optimization

Dual Lagrangian Learning for Conic Optimization

FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning

Ordered Momentum for Asynchronous SGD

Instance-Optimal Private Density Estimation in the Wasserstein Distance

Noise-Aware Differentially Private Regression via Meta-Learning

Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning

PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action

A Synthetic Dataset for Personal Attribute Inference

This Too Shall Pass: Removing Stale Observations in Dynamic Bayesian Optimization

Random Function Descent

Decentralized Noncooperative Games with Coupled Decision-Dependent Distributions

On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions

Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks

Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional Optimization

Locally Private and Robust Multi-Armed Bandits

DAGER: Exact Gradient Inversion for Large Language Models

On provable privacy vulnerabilities of graph representations

Continual Counting with Gradual Privacy Expiration

Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable

Efficient and Private Marginal Reconstruction with Local Non-Negativity

How to Solve Contextual Goal-Oriented Problems with Offline Datasets?

Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning

Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data Coverage

Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression

Explaining RL Decisions with Trajectories': A Reproducibility Study

Discovering Creative Behaviours through DUPLEX: Diverse Universal Features for Policy Exploration

Can Learned Optimization Make Reinforcement Learning Less Difficult?

Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning

Pick up the PACE: A Parameter-Free Optimizer for Lifelong Reinforcement Learning

Reinforcing Language Agents via Policy Optimization with Action Decomposition

Pre-Trained Multi-Goal Transformers with Prompt Optimization for Efficient Online Adaptation

Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees

Diffusion Imitation from Observation

Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers

e-COP : Episodic Constrained Optimization of Policies

Efficient Multi-task Reinforcement Learning with Cross-Task Policy Guidance

Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps

Optimizing Automatic Differentiation with Deep Reinforcement Learning

QGFN: Controllable Greediness with Action Values

Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow

Recurrent Reinforcement Learning with Memoroids

Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate

Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient

Achieving Constant Regret in Linear Markov Decision Processes

Learning to Assist Humans without Inferring Rewards

ICAL: Continual Learning of Multimodal Agents by Transforming Trajectories into Actionable Insights

AutoManual: Generating Instruction Manuals by LLM Agents via Interactive Environmental Learning

Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation

Statistical Multicriteria Benchmarking via the GSD-Front

Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning

Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts

Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs

Bilevel Optimization with Lower-Level Contextual MDPs

DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning

Sim-to-Real Transfer Can Make Naive Exploration Efficient in Reinforcement Learning

Using Unity to Help Solve Reinforcement Learning

Thought of Search: Planning with Language Models Through The Lens of Efficiency

Predicting Future Actions of Reinforcement Learning Agents

Label Alignment Regularization for Distribution Shift

Beyond task diversity: provable representation transfer for sequential multitask linear bandits

L-TTA: Lightweight Test-Time Adaptation Using a Versatile Stem Layer

Extensive-Form Game Solving via Blackwell Approachability on Treeplexes

No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests

MAC Advice for facility location mechanism design

Intrinsic Robustness of Prophet Inequality to Strategic Reward Signaling

Honor Among Bandits: No-Regret Learning for Online Fair Division

Learning Optimal Tax Design in Nonatomic Congestion Games

Understanding Model Selection for Learning in Strategic Environments

Randomized Strategic Facility Location with Predictions

Efficient $\Phi$-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games

Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Play

Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit

Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates

Provable Partially Observable Reinforcement Learning with Privileged Information

Reinforcement Learning with LTL and $\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards

Foundations of Multivariate Distributional Reinforcement Learning

Risk-sensitive control as inference with Rényi divergence

Periodic agent-state based Q-learning for POMDPs

Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback

Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes

An Analysis of Elo Rating Systems via Markov Chains

Accelerating Relative Entropy Coding with Space Partitioning

On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation

Statistical Inference for Fairness Auditing

A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits

Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods

Community Detection Guarantees using Embeddings Learned by Node2Vec

Beyond Assouad, Fano, and Le Cam: Toward Unified Lower Bounds for Statistical Estimation and Interactive Decision Making

On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models

Learning-Augmented Priority Queues

Navigable Graphs for High-Dimensional Nearest Neighbor Search: Constructions and Limits

Aligning Model Properties via Conformal Risk Control

Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training

RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models

Error Correction Output Codes for Robust Neural Networks against Weight-errors: A Neural Tangent Kernel Point of View

CogVLM: Visual Expert for Pretrained Language Models

Transformers on Markov data: Constant depth suffices

Hierarchical and Density-based Causal Clustering

Calibrated Preference Optimization for Direct Language Model Alignment

Recurrent neural networks: vanishing and exploding gradients are not the end of the story

Theoretical Foundations of Deep Selective State-Space Models

Can Models Learn Skill Composition from Examples?

ODRL: A Benchmark for Off-Dynamics Reinforcement Learning

Metrizing Weak Convergence with Maximum Mean Discrepancies

Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration

Conformalized Multiple Testing after Data-dependent Selection

Autonomous Driving with Spiking Neural Networks

VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions

Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in LLMs

3D Structure Prediction of Atomic Systems with Flow-based Direct Preference Optimization

Improving Gloss-free Sign Language Translation by Reducing Representation Density

FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?

Cross-Modality Perturbation Synergy Attack for Person Re-identification

You Only Look Around: Learning Illumination-Invariant Feature for Low-light Object Detection

AvaTaR: Optimizing LLM Agents for Tool-Assisted Knowledge Retrieval

MemVLT: Vision-Language Tracking with Adaptive Memory-based Prompts

Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing

Reparameterizable Tree-structured Variational Inference for Instance-level Correlation Capturing

Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models

A Tractable Inference Perspective of Offline RL

Exocentric-to-Egocentric Video Generation

Targeted Sequential Indirect Experiment Design

Diffusion-Inspired Truncated Sampler for Text-Video Retrieval

Mixture of In-Context Experts Enhance LLMs' Long Context Awareness

Improved Sample Complexity Bounds for Diffusion Model Training

Data Augmentation with Diffusion for Open-Set Semi-Supervised Learning

Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution

ChatQA: Surpassing GPT-4 on Conversational QA and RAG

Secret Collusion among Generative AI Agents

Causal language modeling can elicit search and reasoning capabilities on sudoku puzzles

Rethinking 3D Convolution in $\ell_p$-norm Space

Time-Reversal Provides Unsupervised Feedback to LLMs

Cost-efficient Knowledge-based Question Answering with Large Language Models

Monomial Matrix Group Equivariant Neural Functional Networks

Explaining Text Datasets with Language Parameters

RoPINN: Region Optimized Physics-Informed Neural Networks

DDK: Distilling Domain Knowledge for Efficient Large Language Models

Color-Oriented Redundancy Reduction in Dataset Distillation

(ends 2:00 PM)

Poster Session 3 East [11:00-2:00]

Posters 11:00-2:00

Propensity Score Alignment of Unpaired Multimodal Data

xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology

Exploring Molecular Pretraining Model at Scale

PROSPECT PTMs: Rich Labeled Tandem Mass Spectrometry Dataset of Modified Peptides for Machine Learning in Proteomics

A benchmark for prediction of transcriptomic responses to chemical perturbations across cell types

Med-Real2Sim: Non-Invasive Medical Digital Twins using Physics-Informed Self-Supervised Learning

MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution

Sharing Key Semantics in Transformer Makes Efficient Image Restoration

Detecting Bugs with Substantial Monetary Consequences by LLM and Rule-based Reasoning

Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation

PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging

End-to-End Ontology Learning with Large Language Models

RGFN: Synthesizable Molecular Generation Using GFlowNets

MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training

Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions

A Benchmark Dataset for Event-Guided Human Pose Estimation and Tracking in Extreme Conditions

ImageNet3D: Towards General-Purpose Object-Level 3D Understanding

ScaleKD: Strong Vision Transformers Could Be Excellent Teachers

Not Just Object, But State: Compositional Incremental Learning without Forgetting

BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation

Learning to Decouple the Lights for 3D Face Texture Modeling

D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup

LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS

DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features

Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual Information Minimization

ChatCam: Empowering Camera Control through Conversational AI

1-bit quanta video reconstruction via self-supervised photon prediction

Animate3D: Animating Any 3D Model with Multi-view Video Diffusion

CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for Bird's Eye View Object Detection

DiChaViT: Diverse Representations Boosts Channel-Adaptive Vision Transformers

HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting

Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand Avatars

Causal Context Adjustment Loss for Learned Image Compression

Learning Transferable Features for Implicit Neural Representations

Optimal Transport-based Labor-free Text Prompt Modeling for Sketch Re-identification

Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis

DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection

Dual-Diffusion for Binocular 3D Human Pose Estimation

When does perceptual alignment benefit vision representations?

GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting

Neural Localization Fields for Continuous 3D Human Pose and Shape Estimation

CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition

SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection

SuperVLAD: Compact and Robust Image Descriptors for Visual Place Recognition

Multistable Shape from Shading Emerges from Patch Diffusion

A Unified Framework for 3D Scene Understanding

GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation

R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction

Toward Approaches to Scalability in 3D Human Pose Estimation

Learning to Edit Visual Programs with Self-Supervision

Prune and Repaint: Content-Aware Image Retargeting for any Ratio

Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers

Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba

LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate

DiffSF: Diffusion Models for Scene Flow Estimation

Rad-NeRF: Ray-decoupled Training of Neural Radiance Field

FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training

Text-Infused Attention and Foreground-Aware Modeling for Zero-Shot Temporal Action Detection

UDON: Universal Dynamic Online distillatioN for generic image representations

Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis

ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation

Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization

TrAct: Making First-layer Pre-Activations Trainable

Factorized Diffusion Architectures for Unsupervised Image Generation and Segmentation

ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization

Autoregressive Image Generation without Vector Quantization

Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference

Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models

HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation

Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models

PromptFix: You Prompt and We Fix the Photo

Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning

Variational Multi-scale Representation for Estimating Uncertainty in 3D Gaussian Splatting

Tetrahedron Splatting for 3D Generation

Hierarchical Object-Aware Dual-Level Contrastive Learning for Domain Generalized Stereo Matching

Learning Segmentation from Point Trajectories

A Simple Image Segmentation Framework via In-Context Examples

Geometric Exploitation for Indoor Panoramic Semantic Segmentation

UniDSeg: Unified Cross-Domain 3D Semantic Segmentation via Visual Foundation Models Prior

MVSDet: Multi-View Indoor 3D Object Detection via Efficient Plane Sweeps

Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models

Infusing Synthetic Data with Real-World Patterns for Zero-Shot Material State Segmentation

Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model

LG-VQ: Language-Guided Codebook Learning

HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation

CV-VAE: A Compatible Video VAE for Latent Generative Video Models

HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness

Single Forward Video Generation Model

Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models

Fast and Memory-Efficient Video Diffusion Using Streamlined Inference

MotionCraft: Physics-Based Zero-Shot Video Generation

ReVideo: Remake a Video with Motion and Content Control

TAPVid-3D: A Benchmark for Tracking Any Point in 3D

CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes

OPEL: Optimal Transport Guided ProcedurE Learning

Biomedical Visual Instruction Tuning with Clinician Preference Alignment

Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning

Data curation via joint example selection further accelerates multimodal learning

Intrinsic Self-Supervision for Data Quality Audits

IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation

DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers

Turning Indirect Knowledge into Direct Demonstrations for Computer Agents at Scale

Right this way: Can VLMs Guide Us to See More to Answer Questions?

Elucidating the Design Space of Dataset Condensation

Just Add $100 More: Augmenting Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem

Offline Behavior Distillation

EEVR: A Virtual Reality-Based Emotion Dataset Featuring Paired Physiological Signals and Textual Descriptions

Croissant: A Metadata Format for ML-Ready Datasets

On the Inductive Bias of Stacking Towards Improving Reasoning

B$\oplus$LD: Boolean Logic Deep Learning

Simulation-Free Training of Neural ODEs on Paired Data

Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning

Adaptive Depth Networks with Skippable Sub-Paths

Stepping on the Edge: Curvature Aware Learning Rate Tuners

Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming

Alias-Free Mamba Neural Operator

Learn To be Efficient: Build Structured Sparsity in Large Language Models

MOTE-NAS: Multi-Objective Training-based Estimate for Efficient Neural Architecture Search

Compressing Large Language Models using Low Rank and Low Precision Decomposition

DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs

PLIP: Language-Image Pre-training for Person Representation Learning

Discrete Dictionary-based Decomposition Layer for Structured Representation Learning

Learning Low-Rank Feature for Thorax Disease Classification

Linguistic Collapse: Neural Collapse in (Large) Language Models

Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery

In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness

Rough Transformers: Lightweight Continuous-Time Sequence Modelling with Path Signatures

SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Scaling White-Box Transformers for Vision

Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recovery

Convergence Analysis of Split Federated Learning on Heterogeneous Data

Once Read is Enough: Finetuning-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain Knowledge

The Benefits of Balance: From Information Projections to Variance Reduction

Neural Experts: Mixture of Experts for Implicit Neural Representations

Neural Concept Binder

Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers

Compositional Estimation of Lipschitz Constants for Deep Neural Networks

HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning

AdanCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer

DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms

On the Scalability of Certified Adversarial Robustness with Generated Data

ProTransformer: Robustify Transformers via Plug-and-Play Paradigm

Energy-based Hopfield Boosting for Out-of-Distribution Detection

Learning and Transferring Sparse Contextual Bigrams with Linear Transformers

How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective

Benign overfitting in leaky ReLU networks with moderate input dimension

FUNGI: Features From Unsupervised Gradients

Contrastive-Equivariant Self-Supervised Learning Improves Alignment with Primate Visual Area IT

Learning from Pattern Completion: Self-supervised Controllable Generation

PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models

RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations

A theoretical design of concept sets: improving the predictability of Concept Bottleneck Models

NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes

Wormhole Loss for Partial Shape Matching

A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective

Improving Adaptivity via Over-Parameterization in Sequence Models

The Prevalence of Neural Collapse in Neural Multivariate Regression

Mission Impossible: A Statistical Perspective on Jailbreaking LLMs

Optimal deep learning of holomorphic operators between Banach spaces

SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining

Cross-model Control: Improving Multiple Large Language Models in One-time Training

Rethinking Deep Thinking

Sparse High Rank Adapters

Instruction Tuning With Loss Over Instructions

Image Reconstruction Via Autoencoding Sequential Deep Image Prior

Adversarial Schrödinger Bridge Matching

Transcendence: Generative Models Can Outperform The Experts That Train Them

InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint

Graph Diffusion Policy Optimization

Score Distillation via Reparametrized DDIM

Equivariant Neural Diffusion for Molecule Generation

Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering

IR-CM: The Fast and Universal Image Restoration Method Based on Consistency Model

Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention

HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning

Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems

Physically Compatible 3D Object Modeling from a Single Image

Harmonizing Visual Text Comprehension and Generation

Metric Flow Matching for Smooth Interpolations on the Data Manifold

DEFT: Efficient Finetuning of Conditional Diffusion Models by Learning the Generalised $h$-transform

Interpreting the Weight Space of Customized Diffusion Models

Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization

Constrained Synthesis with Projected Diffusion Models

Confusion-Resistant Federated Learning via Diffusion-Based Data Harmonization on Non-IID Data

Simple and Effective Masked Diffusion Language Models

TFG: Unified Training-Free Guidance for Diffusion Models

CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching

DreamSteerer: Enhancing Source Image Conditioned Editability using Personalized Diffusion Models

Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models

Stochastic Optimal Control for Diffusion Bridges in Function Spaces

Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations

Diffusion Models are Certifiably Robust Classifiers

Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer

Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis

Fast samplers for Inverse Problems in Iterative Refinement models

LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models

Improving the Training of Rectified Flows

Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment

AdjointDEIS: Efficient Gradients for Diffusion Models

The Convergence of Variance Exploding Diffusion Models under the Manifold Hypothesis

Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy

Discrete-state Continuous-time Diffusion for Graph Generation

MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank Experts

Permutation-Invariant Autoregressive Diffusion for Graph Generation

Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion

On the Noise Robustness of In-Context Learning for Text Generation

BERTs are Generative In-Context Learners

Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving

Universal In-Context Approximation By Prompting Fully Recurrent Models

Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective

MixEval: Fast and Dynamic Human Preference Approximation with LLM Benchmark Mixtures

Questioning the Survey Responses of Large Language Models

Cascade Speculative Drafting for Even Faster LLM Inference

Learning Distributions on Manifolds with Free-Form Flows

Learning Goal-Conditioned Representations in Reward Models for Aligning Language Models

Unlocking the Boundaries of Thought: A Reasoning Granularity Framework to Quantify and Optimize Chain-of-Thought

AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback

Learning Better Representations From Less Data For Propositional Satisfiability

Solving Intricate Problems with Human-like Decomposition and Rethinking

Chain of Agents: Large Language Models Collaborating on Long-Context Tasks

Recursive Introspection: Teaching Foundation Model Agents How to Self-Improve

Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models

Iterative Reasoning Preference Optimization

TableRAG: Million-Token Tabular Reasoning with Large Language Models

TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools

Multi-Head Mixture-of-Experts

Generative Forests

Can Language Models Learn to Skip Steps?

Can Large Language Models Analyze Graphs like Professionals? A Benchmark and Dataset

Computation Tree: A Transferable Pattern Towards Graph Foundation Models

Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual Structures

Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention

Towards Dynamic Message Passing on Graphs

Graph neural networks and non-commuting operators

Energy-based Epistemic Uncertainty for Graph Neural Networks

Dissecting the Failure of Invariant Learning on Graphs

Enhancing Chess Reinforcement Learning with Graph Representation

Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach

What Is Missing For Graph Homophily? Disentangling Graph Homophily For Graph Neural Networks

GRANOLA: Adaptive Normalization for Graph Neural Networks

Learning on Large Graphs using Intersecting Communities

Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level

Deep Graph Mating

Unifying Generation and Prediction on Graphs with Latent Graph Diffusion

Distributed-Order Fractional Graph Operating Network

HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning

Pure Message Passing Can Estimate Common Neighbor for Link Prediction

Boosting Graph Pooling with Persistent Homology

Deep Equilibrium Algorithmic Reasoning

Even Sparser Graph Transformers

A Foundation Model for Zero-shot Logical Query Reasoning

Graph Coarsening with Message-Passing Guarantees

Supra-Laplacian Encoding for Transformer on Dynamic Graphs

Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters

VideoGUI: A Benchmark for GUI Automation from Instructional Videos

Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Ugly

Confidence Regulation Neurons in Language Models

Provable Guarantees for Model Performance via Mechanistic Intepretability

CoSy: Evaluating Textual Explanations of Neurons

B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable

Demystifying Encoding: Detecting Explanations that Hide Information in the Selection

Causal Dependence Plots

FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors

Spectral Editing of Activations for Large Language Model Alignment

WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia

IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering

Reranking Laws for Language Generation: A Communication-Theoretic Perspective

The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More

How do Large Language Models Handle Multilingualism?

PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression

HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction

LLM Evaluators Recognize and Favor Their Own Generations

ChronoEpilogi: Scalable Time Series Selection with Multiple Solutions

Analysing the Generalisation and Reliability of Steering Vectors

Interpretable Machine Learning for Datasets with Missing Values

Geometric-Averaged Preference Optimization for Soft Preference Labels

Unchosen Experts Can Contribute Too: Unleashing MoE Models’ Power by Self-Contrast

Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass

AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data

Discovering Preference Optimization Algorithms with and for Large Language Models

Panacea: Pareto Alignment via Preference Adaptation for LLMs

Delving into the Reversal Curse: How Far Can Large Language Models Generalize?

CorDA: Context-Oriented Decomposition Adaptation of Large Language Models

Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models

Knowledge Graph Completion by Intermediate Variables Regularization

HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models

Agent Planning with World Knowledge Model

Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world Corruptions

Entrywise error bounds for low-rank approximations of kernel matrices

Reciprocal Learning

Exponential Quantum Communication Advantage in Distributed Inference and Learning

Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods

Identifying Equivalent Training Dynamics

AGILE: A Novel Framework of LLM Agent

QTIP: Quantization with Trellises and Incoherence Processing

Handling Learnwares from Heterogeneous Feature Spaces with Explicit Label Exploitation

An Autoencoder-Like Nonnegative Matrix Co-Factorization for Improved Student Cognitive Modeling

SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection

Knowledge Graph Fine-Tuning Upon Open-World Knowledge from Large Language Models

Learning Representations for Hierarchies with Minimal Support

Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models

Implicit Regularization Paths of Weighted Neural Representations

V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark

Meta-Learning Universal Priors Using Non-Injective Change of Variables

On Affine Homotopy between Language Encoders

Knowledge Composition using Task Vectors with Learned Anisotropic Scaling

Transfer Learning for Latent Variable Network Models

Disentangling and mitigating the impact of task similarity for continual learning

A Closer Look at the CLS Token for Cross-Domain Few-Shot Learning

TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning

Topological Hidden Markov Models

Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding

Test-Time Dynamic Image Fusion

WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences

VHELM: A Holistic Evaluation of Vision Language Models

MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens

OwMatch: Conditional Self-Labeling with Consistency for Open-world Semi-Supervised Learning

Protected Test-Time Domain Adaptation via Online Entropy Matching

Hierarchical data visualization via PCA trees

Why the Metric Backbone Preserves Community Structure

Bridging Gaps: Federated Multi-View Clustering in Heterogeneous Hybrid Views

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection

Unsupervised Anomaly Detection Algorithms on Real-world Data: How Many Do We Need?

Unveiling Encoder-Free Vision-Language Models

Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning

MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models

Advancing Cross-domain Discriminability in Continual Learning of Vison-Language Models

Are We on the Right Way for Evaluating Large Vision-Language Models?

Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration

Yo'LLaVA: Your Personalized Language and Vision Assistant

FRIEREN: Efficient Video-to-Audio Generation with Rectified Flow Matching

Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs

An Any-to-Any Vision Model for Tens of Tasks and Modalities

Unveiling the Tapestry of Consistency in Large Vision-Language Models

LOVA3: Learning to Visual Question Answering, Asking and Assessment

Towards a "Universal Translator" for Neural Dynamics at Single-Cell, Single-Spike Resolution

Crafting Interpretable Embeddings by Asking LLMs Questions

Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signals

EEGPT: Pretrained Transformer for Universal and Reliable Representation of EEG Signals

Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification

Back to the Continuous Attractors

Learning predictable and robust neural representations by straightening image sequences

The Bayesian sampling in a canonical recurrent circuit with a diversity of inhibitory interneurons

MonkeySee: Space-time-resolved reconstructions of natural images from macaque multi-unit activity

Spike-based Neuromorphic Model for Sound Source Localization

$\textit{NeuroPath}$: A Neural Pathway Transformer for Joining the Dots of Human Connectomes

Linking In-context Learning in Transformers to Human Episodic Memory

RTify: Aligning Deep Neural Networks with Human Behavioral Decisions

Neuro-Vision to Language: Enhancing Visual Reconstruction and Language Interaction through Brain Recordings

Learning Macroscopic Dynamics from Partial Microscopic Observations

Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators

PACE: Pacing Operator Learning to Accurate Optical Field Simulation for Complicated Photonic Devices

Probablistic Emulation of a Global Climate Model with Spherical DYffusion

Scaling transformer neural networks for skillful and reliable medium-range weather forecasting

Precipitation Downscaling with Spatiotemporal Video Diffusion

AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields

Quantum Deep Equilibrium Models

Scientific Consistency Improves upon Multi-Task Learning in Molecular Science

Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics

Gaussian Process Bandits for Top-k Recommendations

Marginalized Hamiltonian Monte Carlo for Linear Mixed-Effects Models

BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models

Compressive Sensing with Sparsity Inducing Conditionally Gaussian Generative Models

TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks

FasMe: Fast and Sample-efficient Meta Estimator for Precision Matrix Learning in Small Sample Settings

Interaction-Force Transport Gradient Flows

Probabilistic Federated Prompt-Tuning in Data Imbalance Settings

Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing

Abductive Reasoning in Logical Credal Networks

Space-Time Continuous PDE Forecasting using Equivariant Neural Fields

Learning to Predict Structural Vibrations

Principled Bayesian Optimization in Collaboration with Human Experts

Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference

Fast Channel Simulation via Error-Correcting Codes

Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient

A Neural Network Approach for Efficiently Answering Most Probable Explanation Queries in Probabilistic Models

VISA: Variational Inference with Sequential Sample-Average Approximations

Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions

SurgicAI: A Fine-grained Platform for Data Collection and Benchmarking in Surgical Policy Learning

RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar

AED: Adaptable Error Detection for Few-shot Imitation Policy

Active Perception for Grasp Detection via Neural Graspness Field

RoboMamba: Multimodal State Space Model for Efficient Robot Reasoning and Manipulation

DDN: Dual-domain Dynamic Normalization for Non-stationary Time Series Forecasting

Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting

Knowledge-Empowered Dynamic Graph Network for Irregularly Sampled Medical Time Series

Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model

Apathetic or Empathetic? Evaluating LLMs' Emotional Alignments with Humans

Vision-Language Navigation with Energy-Based Policy

BAKU: An Efficient Transformer for Multi-Task Policy Learning

Prediction with Action: Visual Policy Learning via Joint Denoising Process

HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid

PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation

Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers

MO-DDN: A Coarse-to-Fine Attribute-based Exploration Agent for Multi-Object Demand-driven Navigation

Frequency-aware Generative Models for Multivariate Time-series Imputation

SDformer: Similarity-driven Discrete Transformer For Time Series Generation

Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting

Task-oriented Time Series Imputation Evaluation via Generalized Representers

UNITS: A Unified Multi-Task Time Series Model

Large Pre-trained time series models for cross-domain Time series analysis tasks

MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models

The Art of Saying No: Contextual Noncompliance in Language Models

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs

DeNetDM: Debiasing by Network Depth Modulation

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment

A Swiss Army Knife for Heterogeneous Federated Learning: Flexible Coupling via Trace Norm

Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibration

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Class-wise Transformation Is All You Need

Exploring Adversarial Robustness of Deep State Space Models

Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents

Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection

BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens

Noisy Label Learning with Instance-Dependent Outliers: Identifiability via Crowd Wisdom

ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users

Large Language Model Unlearning

Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective

DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain

What If the Input is Expanded in OOD Detection?

United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial Trajectories

Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control

Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift

Fast yet Safe: Early-Exiting with Risk Control

Towards Evaluation of Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models

Trajectory Volatility for Out-of-Distribution Detection in Mathematical Reasoning

Post-Robustness of Backdoor Purification

Protecting Your LLMs with Information Bottleneck

Learning from Uncertain Data: From Possible Worlds to Possible Models

Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature

Multilingual Diversity Improves Vision-Language Representations

Not All Tokens Are What You Need for Pretraining

MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch

FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models

Distributed Sparse Regression via Penalization

More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime validity

RashomonGB: Analyzing the Rashomon Effect and Mitigating Predictive Multiplicity in Gradient Boosting

Aligning Large Language Models with Representation Editing: A Control Perspective

FedGMark: Certifiably Robust Watermarking for Federated Graph Learning

Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection

T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback

Transfer Q-star : Principled Decoding for LLM Alignment

Efficient Adversarial Training in LLMs with Continuous Attacks

GO4Align: Group Optimization for Multi-Task Alignment

SLowcalSGD : Slow Query Points Improve Local-SGD for Stochastic Convex Optimization

Neuro-Symbolic Data Generation for Math Reasoning

Make Continual Learning Stronger via C-Flat

Edit Distance Robust Watermarks via Indexing Pseudorandom Codes

A Modular Conditional Diffusion Framework for Image Reconstruction

Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms

Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning

VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation

Unrolled denoising networks that provably learn to perform optimal Bayesian inference

BAN: Detecting Backdoors Activated by Neuron Noise

Graph-based Uncertainty Metrics for Long-form Language Model Generations

Why Transformers Need Adam: A Hessian Perspective

Generalized Protein Pocket Generation with Prior-Informed Flow Matching

MediQ: Question-Asking LLMs for Adaptive and Reliable Medical Reasoning

$\textit{Bifr\"ost}$: 3D-Aware Image Composing with Language Instructions

Language Hierarchical Self-training for Detecting Twenty-thousand Classes using Image-level Supervision

Confident Natural Policy Gradient for Local Planning in $q_\pi$-realizable Constrained MDPs

Universal Rates for Active Learning

Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization

Geometric Trajectory Diffusion Models

Fine-Grained Dynamic Framework for Bias-Variance Joint Optimization on Data Missing Not at Random

Customizing Language Models with Instance-wise LoRA for Sequential Recommendation

Revisiting Score Propagation in Graph Out-of-Distribution Detection

Relation-Driven Diffusion for Human-Object Interaction Detection

One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection

Identify Then Recommend: Towards Unsupervised Group Recommendation

Synthesize, Partition, then Adapt: Eliciting Diverse Samples from Foundation Models

Neural Collapse Inspired Feature Alignment for Out-of-Distribution Generalization

Multi-modal Transfer Learning between Biological Foundation Models

Communication-Efficient Federated Group Distributionally Robust Optimization

Bridging Geometric States via Generative Modeling

(ends 2:00 PM)

noon

Affinity Workshop:

Neurodiversity Workshop

(ends 2:00 PM)

1 p.m.

Break:

Lunch Break

(ends 2:30 PM)

2:30 p.m.

Invited Talk:

Invited Talk - Arnaud Doucet

Arnaud Doucet

(ends 3:30 PM)

Affinity Workshop:

Indigenous in AI/ML

(ends 7:00 PM)

3:30 p.m.

Oral Session 4A: Natural Language Processing [3:30-4:30]

DevBench: A multimodal developmental benchmark for language learning

CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark

LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low Resource and Extinct Languages

(ends 4:30 PM)

Oral Session 4B: Diffusion-based Models [3:30-4:30]

CAT3D: Create Anything in 3D with Multi-View Diffusion Models

Stylus: Automatic Adapter Selection for Diffusion Models

Guiding a Diffusion Model with a Bad Version of Itself

(ends 4:30 PM)

Oral Session 4C: Diffusion-based Models, Mathematics [3:30-4:30]

DenoiseReID: Denoising Model for Representation Learning of Person Re-Identification

Improved Distribution Matching Distillation for Fast Image Synthesis

OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset

(ends 4:30 PM)

Oral Session 4D: Machine Vision [3:30-4:30]

Gaussian-Informed Continuum for Physical Property Identification and Simulation

MeshFormer : High-Quality Mesh Generation with 3D-Guided Reconstruction Model

E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection

(ends 4:30 PM)

Overflow for Oral Session 4D: Machine Vision [3:30-4:30]

(ends 4:30 PM)

Overflow for Oral Session 4A: Natural Language Processing [3:30-4:30]

(ends 4:30 PM)

4:30 p.m.

Creative AI Session 6 [4:30-7:30]

Chairs: Jean Oh · Marcelo Coelho · Lia Coleman · Yingtao Tian

s 4:30-7:30

[4:30] Autonoetic Intelligence: A Human-AI System for Being with the Time Being

[4:30] Be the Beat: AI-Powered Boombox for Music Generation from Freestyle Dance

[4:30] Dialogue with the Machine and Dialogue with the Art World: A Method for Evaluating AI as a Tool for Creativity

[4:30] DreamLLM-3D: Affective Dream Reliving using Large Language Model and 3D Generative AI

[4:30] E(*)star, navigating the landscape of emotion language

[4:30] Exposed to AI: The Paradox of Trust and Vulnerability in Human-Machine Interactions

[4:30] For All Mankind

[4:30] Memoroscope

[4:30] Navigating Ambiguity: Investigative gameplay with a Large Language Object in "A Mystery for You"

[4:30] Neural Artefact Black

[4:30] Neural MONOBLOC Black

[4:30] Neural Tides: Oceanic Neural Granular Synthesizer

[4:30] Poespin-Wherever your body reach, there is a poetry

[4:30] Symbiosis

[4:30] Text2Tradition: From Epistemological Tensions to AI-Mediated Cultural Co-Creation

(ends 7:30 PM)

Break:

Coffee Break

(ends 5:30 PM)

Poster Session 4 West [4:30-7:30]

Posters 4:30-7:30

Optimization-based Causal Estimation from Heterogeneous Environments

Learning Discrete Latent Variable Structures with Tensor Rank Conditions

Causal Imitation for Markov Decision Processes: a Partial Identification Approach

Who’s Gaming the System? A Causally-Motivated Approach for Detecting Strategic Adaptation

Interventionally Consistent Surrogates for Complex Simulation Models

Learning Mixtures of Unknown Causal Interventions

Interventional Causal Discovery in a Mixture of DAGs

Discovery of the Hidden World with Large Language Models

Causal vs. Anticausal merging of predictors

Kuro Siwo: 33 billion $m^2$ under the water. A global multi-temporal satellite dataset for rapid flood mapping

FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic Understanding

HelpSteer 2: Open-source dataset for training top-performing reward models

SCRREAM : SCan, Register, REnder And Map: A Framework for Annotating Accurate and Dense 3D Indoor Scenes with a Benchmark

LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation

GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI

SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation

IncomeSCM: From tabular data set to time-series simulator and causal estimation benchmark

GeoLife: Spacial Plant Species Prediction Dataset

WikiDO: Evaluating Out-of-Distribution Generalization of Vision-Language Models in Cross-Modal Retrieval

HourVideo: 1-Hour Video-Language Understanding

CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark

A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences

VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images

Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models

MedCalc-Bench: Evaluating Large Language Models for Medical Calculations

MAN TruckScenes: A multimodal dataset for autonomous trucking in diverse conditions

MultiOrg: A Multi-rater Organoid-detection Dataset

EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries

Quantifying the Bitter Lesson: How Safety Benchmarks Measure Capabilities Instead of Safety

EyeGraph: Modularity-aware Spatio Temporal Graph Clustering for Continuous Event-based Eye Tracking

Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks

LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low Resource and Extinct Languages

IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization

RedCode: Multi-dimensional Safety Benchmark for Code Agents

AgentGym: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents

VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding

Benchmarking Structural Inference Methods for Interacting Dynamical Systems with Synthetic Data

NYU CTF Dataset: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security

Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization

CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence

ConceptFactory: Facilitate 3D Object Knowledge Annotation with Object Conceptualization

BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices

SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagery

Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets

FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models

The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

UltraMedical: Building Specialized Generalists in Biomedicine

Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and Toolbox

Topic-Conversation Relevance (TCR) Dataset and Benchmarks

PowerGraph: A power grid benchmark dataset for graph neural networks

WhodunitBench: Evaluating Large Multimodal Agents via Murder Mystery Games

UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles

Do Multimodal Foundation Models Understand Enterprise Workflows? A Benchmark for Business Process Management Tasks

Benchmarking Out-of-Distribution Generalization and Adaptation for Electromyography

MEQA: A Benchmark for Multi-hop Event-centric Question Answering with Explanations

kGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution

The Sample Complexity of Gradient Descent in Stochastic Convex Optimization

A Unified Recipe for Deriving (Time-Uniform) PAC-Bayes Bounds

Wasserstein Distributionally Robust Optimization through the Lens of Structural Causal Models and Individual Fairness

Mind the Gap: A Causal Perspective on Bias Amplification in Prediction & Decision-Making

FairWire: Fair Graph Generation

When is Multicalibration Post-Processing Necessary?

Enhancing Robustness of Last Layer Two-Stage Fair Model Corrections

The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning

Reproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentations

GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations

DevBench: A multimodal developmental benchmark for language learning

How Does Black-Box Impact the Learning Guarantee of Stochastic Compositional Optimization?

Learning Social Welfare Functions

Overfitting Behaviour of Gaussian Kernel Ridge Regression: Varying Bandwidth or Dimensionality

Credal Learning Theory

Contextual Decision-Making with Knapsacks beyond the Worst Case

On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability

Data subsampling for Poisson regression

Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting

Language Generation in the Limit

A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems

The Reliability of OKRidge Method in Solving Sparse Ridge Regression Problems

Accelerating ERM for data-driven algorithm design using output-sensitive techniques

Sample Complexity of Algorithm Selection Using Neural Networks and Its Applications to Branch-and-Cut

Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization

Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity

Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD

A Universal Growth Rate for Learning with Smooth Surrogate Losses

Least Squares Regression Can Exhibit Under-Parameterized Double Descent

Only Strict Saddles in the Energy Landscape of Predictive Coding Networks?

Transductive Sample Complexities Are Compact

Prospective Learning: Learning for a Dynamic Future

Optimal Hypothesis Selection in (Almost) Linear Time

Predicting Ground State Properties: Constant Sample Complexity and Deep Learning Algorithms

Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models

Optimal Clustering with Bandit Feedback

Queueing Matching Bandits with Preference Feedback

WATT: Weight Average Test Time Adaptation of CLIP

Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs

Dealing with Synthetic Data Contamination in Online Continual Learning

Barely Random Algorithms for Metrical Task Systems

Online Adaptation of Language Models with a Memory of Amortized Contexts

Bandits with Ranking Feedback

Improved Regret for Bandit Convex Optimization with Delayed Feedback

Invariant subspaces and PCA in nearly matrix multiplication time

MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence

Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models

Polyak Meets Parameter-free Clipped Gradient Descent

SAMPa: Sharpness-aware Minimization Parallelized

Efficient Multi-task LLM Quantization and Serving for Multiple LoRA Adapters

Linear Time Approximation Algorithm for Column Subset Selection with Local Search

Optimal Scalarizations for Sublinear Hypervolume Regret

Accelerating Non-Maximum Suppression: A Graph Theory Perspective

Universal Online Convex Optimization with $1$ Projection per Round

Adaptive Passive-Aggressive Framework for Online Regression with Side Information

Mixture of Experts Meets Prompt-Based Continual Learning

Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks

Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization

Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling

A Framework for Bilevel Optimization on Riemannian Manifolds

Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization

Safe and Sparse Newton Method for Entropic-Regularized Optimal Transport

Inexact Augmented Lagrangian Methods for Conic Optimization: Quadratic Growth and Linear Convergence

Directional Smoothness and Gradient Methods: Convergence and Adaptivity

Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction

Large Language Models as Hyper-Heuristics for Combinatorial Optimization

Learning Cut Generating Functions for Integer Programming

Discretely beyond $1/e$: Guided Combinatorial Algortihms for Submodular Maximization

Neur2BiLO: Neural Bilevel Optimization

Self-Labeling the Job Shop Scheduling Problem

OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations

Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity

Efficient Pipeline Parallelism with Controllable Memory

LoQT: Low Rank Adapters for Quantized Training

Achieving Linear Convergence with Parameter-Free Algorithms in Decentralized Optimization

Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability

Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach

Rethinking Memory and Communication Costs for Efficient Large Language Model Training

OptCM: The Optimization Consistency Models for Solving Combinatorial Problems in Few Shots

Efficient Combinatorial Optimization via Heat Diffusion

Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective

ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate

Optimization Can Learn Johnson Lindenstrauss Embeddings

Generative Adversarial Bayesian Optimization for Surrogate Objectives

Disentangling Linear Quadratic Control with Untrusted ML Predictions

Stochastic Optimization Schemes for Performative Prediction with Nonconvex Loss

Contextual Linear Optimization with Bandit Feedback

Robust and Faster Zeroth-order Minimax Optimization: Complexity and Applications

How to Boost Any Loss Function

Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniques

ReLIZO: Sample Reusable Linear Interpolation-based Zeroth-order Optimization

Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model

SPEAR: Exact Gradient Inversion of Batches in Federated Learning

Public-data Assisted Private Stochastic Optimization: Power and Limitations

Attack-Aware Noise Calibration for Differential Privacy

Certified Machine Unlearning via Noisy Stochastic Gradient Descent

Faster Differentially Private Top-$k$ Selection: A Joint Exponential Mechanism with Pruning

On the Computational Complexity of Private High-dimensional Model Selection

Towards More Efficient Property Inference Attacks on Graph Neural Networks

Banded Square Root Matrix Factorization for Differentially Private Model Training

Scalable DP-SGD: Shuffling vs. Poisson Subsampling

Revisiting Differentially Private ReLU Regression

Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation

Mitigating Covariate Shift in Behavioral Cloning via Robust Distribution Correction Estimation

Is Value Function Learning Really the Main Bottleneck of Offline RL?

QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers

CALE: Continuous Arcade Learning Environment

A Simple Framework for Generalization in Visual RL under Dynamic Scene Perturbations

iVideoGPT: Interactive VideoGPTs are Scalable World Models

First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs

Distributional Reinforcement Learning with Regularized Wasserstein Loss

Skill-aware Mutual Information Optimisation for Zero-shot Generalisation in Reinforcement Learning

State Chrono Representation for Enhancing Generalization in Reinforcement Learning

Learning Distinguishable Trajectory Representation with Contrastive Loss

Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning

Diversity Is Not All You Need: Training A Robust Cooperative Agent Needs Specialist Partners

Sample-Efficient Constrained Reinforcement Learning with General Parameterization

Learning Successor Features the Simple Way

Diffusion Actor-Critic with Entropy Regulator

Safety through feedback in Constrained RL

Adversarial Robust Decision Transformer: Enhancing RvS Robustness via Minimax Returns

Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization

PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning

Model-Based Transfer Learning for Contextual Reinforcement Learning

Language Grounded Multi-Agent Communication for Ad-hoc Teamwork

Policy Improvement using Language Feedback Models

Few-Shot Task Learning Through Inverse Generative Modeling

Imitating Language via Scalable Inverse Reinforcement Learning

Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning

Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search

Adaptive Exploration for Data-Efficient General Value Function Evaluations

Finding good policies in average-reward Markov Decision Processes without prior knowledge

Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning

Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model

Oracle-Efficient Reinforcement Learning for Max Value Ensembles

Reinforcement Learning with Adaptive Control Regularization for Safe Control of Critical Systems

Simplifying Constraint Inference with Inverse Reinforcement Learning

Efficient Discrepancy Testing for Learning with Distribution Shift

Persistent Test-time Adaptation in Recurring Testing Scenarios

One-to-Multiple: A Progressive Style Transfer Unsupervised Domain-Adaptive Framework for Kidney Tumor Segmentation

Universality in Transfer Learning for Linear Models

Empowering Active Learning for 3D Molecular Graphs with Geometric Graph Isomorphism

Gated Inference Network: Inferencing and Learning State-Space Models

Text-Aware Diffusion for Policy Learning

Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation

Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity

Opponent Modeling with In-context Search

NeoRL: Efficient Exploration for Nonepisodic RL

On Tractable $\Phi$-Equilibria in Non-Concave Games

Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games

The Secretary Problem with Predicted Additive Gap

Paths to Equilibrium in Games

Safe Exploitative Play in Stochastic Bayesian Games with Untrusted Type Beliefs

Randomized Truthful Auctions with Learning Agents

Fair Allocation in Dynamic Mechanism Design

Accelerated Regularized Learning in Finite N-Person Games

DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation

Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning

Constrained Binary Decision Making

[Re] Classwise-Shapley values for data valuation

No Free Delivery Service: Epistemic limits of passive data collection in complex social systems

The Power of Hard Attention Transformers on Data Sequences: A formal language theoretic perspective

Fixed points of nonnegative neural networks

Oja's Algorithm for Sparse PCA

Diffusion-based Curriculum Reinforcement Learning

The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure

Operator World Models for Reinforcement Learning

A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch

Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^\pi$-Realizability and Concentrability

Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem

EffiBench: Benchmarking the Efficiency of Automatically Generated Code

$\texttt{Model-GLUE}$: Democratized LLM Scaling for A Large Model Zoo in the Wild

DarkSAM: Fooling Segment Anything Model to Segment Nothing

Score-Optimal Diffusion Schedules

Efficient Multi-modal Models via Stage-wise Visual Context Compression

Optimal Batched Best Arm Identification

CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense

Fast Sampling via Discrete Non-Markov Diffusion Models

BackTime: Backdoor Attacks on Multivariate Time Series Forecasting

Mixtures of Experts for Audio-Visual Learning

SGLang: Efficient Execution of Structured Language Model Programs

Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources

Amortizing intractable inference in diffusion models for vision, language, and control

Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning

MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model

Training LLMs to Better Self-Debug and Explain Code

Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization

VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections

Easy Regional Contrastive Learning of Expressive Visual Fashion Representations

Text-Guided Image Editing in Around 7 Steps with Invertible Consistency Distillation

Robust Sparse Regression with Non-Isotropic Designs

IPO: Interpretable Prompt Optimization for Vision-Language Models

In-Context Learning with Representations: Contextual Generalization of Trained Transformers

Replicable Uniformity Testing

From Chaos to Clarity: 3DGS in the Dark

Calibrated Self-Rewarding Vision Language Models

Persistence Homology Distillation for Semi-supervised Continual Learning

CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning

Mixture of Demonstrations for In-Context Learning

Test-Time Debiasing of Vision-Language Embeddings

Learning Bregman Divergences with Application to Robustness

(ends 7:30 PM)

Poster Session 4 East [4:30-7:30]

Posters 4:30-7:30

Ultrafast classical phylogenetic method beats large protein language models on variant effect prediction

Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization

Practical Guide for Designing Cell-Type-Specific Promoter Sequences Using Conservative Model-Based Optimization

Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generation

Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers

Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis

Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation

MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems

Gaussian-Informed Continuum for Physical Property Identification and Simulation

Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Search

Fine Tuning Out-of-Vocabulary Item Recommendation with User Sequence Imagination

Towards Visual Text Design Transfer Across Languages

Generating Highly Designable Proteins with Geometric Algebra Flow Matching

PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection

Toward Reliable, Reproducible, and Practical Human Evaluation Protocol for Text-to-Video Models

HOPE: Shape Matching Via Aligning Different K-hop Neighbourhoods

Toward Semantic Gaze Target Detection

Progressive Cross-Scale Self-Supervised Blind Image Deconvolution via Implicit Neural Representation

LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes

Tensor-Based Synchronization and the Low-Rankness of the Block Trifocal Tensor

STONE: A Submodular Optimization Framework for Active 3D Object Detection

Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation

SimGen: Simulator-conditioned Driving Scene Generation

PointMamba: A Simple State Space Model for Point Cloud Analysis

Crafting Hierarchical Strand-based Hair Geometry with Frequency-decomposed Representative Guide Curves

Towards Unsupervised Model Selection for Domain Adaptive Object Detection

Fast Encoder-Based 3D from Casual Videos via Point Track Processing

Vivid-ZOO: Multi-View Video Generation with Diffusion Model

CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle Detectors

Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model

Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts

Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation

Virtual Scanning: Unsupervised Non-line-of-sight Imaging from Irregularly Undersampled Transients

DenoiseReID: Denoising Model for Representation Learning of Person Re-Identification

RETR: Multi-View Radar Detection Transformer for Indoor Perception

Learning 1D Causal Visual Representation with De-focus Attention Networks

MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Images

Normal-GS: 3D Gaussian Splatting with Normal-Involved Rendering

DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering

3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction

OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries

Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting

One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection

YOLOv10: Real-Time End-to-End Object Detection

Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis

MeshFormer : High-Quality Mesh Generation with 3D-Guided Reconstruction Model

RCDN: Towards Robust Camera-Insensitivity Collaborative Perception via Dynamic Feature-based 3D Neural Modeling

RobIR: Robust Inverse Rendering for High-Illumination Scenes

Improved Distribution Matching Distillation for Fast Image Synthesis

GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing

TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control

Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation

Multimodal Large Language Models Make Text-to-Image Generative Models Align Better

EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models

Optimization Efficient Open-World Visual Region Recognition

HydraViT: Stacking Heads for a Scalable ViT

Sm: enhanced localization in Multiple Instance Learning for medical imaging classification

Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading

Linearly Decomposing and Recomposing Vision Transformers for Diverse-Scale Models

Expanding Sparse Tuning for Low Memory Usage

SegVol: Universal and Interactive Volumetric Medical Image Segmentation

TARSS-Net: Temporal-Aware Radar Semantic Segmentation Network

Unsupervised Hierarchy-Agnostic Segmentation: Parsing Semantic Image Structure

Generated and Pseudo Content guided Prototype Refinement for Few-shot Point Cloud Segmentation

Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts

Understanding Multi-Granularity for Open-Vocabulary Part Segmentation

Bridge the Points: Graph-based Few-shot Segment Anything Semantically

From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $\alpha$-NeuS

Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly

Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis

Alleviating Attention Bias for Visual-Informed Text Generation

LAVIB: A Large-scale Video Interpolation Benchmark

Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning

PURE: Prompt Evolution with Graph ODE for Out-of-distribution Fluid Dynamics Modeling

The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better

Depth Anything V2

Moving Off-the-Grid: Scene-Grounded Video Representations

SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM

HENASY: Learning to Assemble Scene-Entities for Interpretable Egocentric Video-Language Model

Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos

Vript: A Video Is Worth Thousands of Words

FIFO-Diffusion: Generating Infinite Videos from Text without Training

CAT3D: Create Anything in 3D with Multi-View Diffusion Models

ChronoMagic: A Benchmark for Metamorphic Evaluation of Time-lapse Text-to-Video Generation

ImageNet++: A Large-Scale Benchmark of Data Curation Strategies

Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?

Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions

Make Your LLM Fully Utilize the Context

Fetch and Forge: Efficient Dataset Condensation for Object Detection

Group and Shuffle: Efficient Structured Orthogonal Parametrization

Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformations

NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation

Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation

A Single-Step, Sharpness-Aware Minimization is All You Need to Achieve Efficient and Accurate Sparse Training

DEPrune: Depth-wise Separable Convolution Pruning for Maximizing GPU Parallelism

Infusing Self-Consistency into Quantum Hamiltonian Prediction via Deep Equilibrium Models

On the Role of Attention Masks and LayerNorm in Transformers

Gated Slot Attention for Efficient Linear-Time Sequence Modeling

Bridging the Divide: Reconsidering Softmax and Linear Attention

Selective Attention: Enhancing Transformer through Principled Context Control

A Comprehensive Investigation of Sparse Rate Reduction in Transformer-like Models

xLSTM: Extended Long Short-Term Memory

Transformers need glasses! Information over-squashing in language tasks

Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios

Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems

CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization

Analyzing & Reducing the Need for Learning Rate Warmup in Neural Network Optimization

MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encoding

Who Needs Features? On the Surprising Effectiveness of Attention Transfer for Vision Transformers

Vector Quantization Prompting for Continual Learning

ProxyFusion: Face Feature Aggregation Through Sparse Experts

Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning

Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control

Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement

Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe

RMLR: Extending Multinomial Logistic Regression into General Geometries

Zipfian Whitening

Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment

Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication

A StrongREJECT for Empty Jailbreaks

A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention

Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes

PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders

Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization

Self-Guided Masked Autoencoder

Multi-view Masked Contrastive Representation Learning for Endoscopic Video Analysis

Curriculum Fine-tuning of Vision Foundation Model for Medical Image Classification Under Label Noise

Full-Distance Evasion of Pedestrian Detectors in the Physical World

Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers

Sample Selection via Contrastive Fragmentation for Noisy Label Regression

Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space

Ask, Attend, Attack: A Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models

Information-theoretic Limits of Online Classification with Noisy Labels

Approximation Rate of the Transformer Architecture for Sequence Modeling

Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning

The Expressive Capacity of State Space Models: A Formal Language Perspective

Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling

Unsupervised Object Detection with Theoretical Guarantees

Mixture of Tokens: Continuous MoE through Cross-Example Aggregation

FM-Delta: Lossless Compression for Storing Massive Fine-tuned Foundation Models

SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning

MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization

SpeedLoader: An I/O efficient scheme for heterogeneous and distributed LLM operation

QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

The GAN is dead; long live the GAN! A Modern GAN Baseline

Nearest Neighbor Speculative Decoding for LLM Generation and Attribution

Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses

Exploring & Improving Multi-token Prediction (Block Draft) in Language Modeling

Open LLMs are Necessary for Private Adaptations and Outperform their Closed Alternatives

Stylus: Automatic Adapter Selection for Diffusion Models

CIFD: Controlled Information Flow to Enhance Knowledge Distillation

SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors

Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss

einspace: Searching for Neural Architectures from Fundamental Operations

Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers

A Label is Worth A Thousand Images in Dataset Distillation

Dual Encoder GAN Inversion for High-Fidelity 3D Head Reconstruction from Single Images

Evaluating the World Model Implicit in a Generative Model

Light Unbalanced Optimal Transport

Hallo3D: Multi-Modal Hallucination Detection and Mitigation for Consistent 3D Content Generation

Universal Sample Coding

Mesa-Extrapolation: A Weave Position Encoding Method for Enhanced Extrapolation in LLMs

AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising

Transfer Learning for Diffusion Models

CLIPAway: Harmonizing focused embeddings for removing objects via diffusion models

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features

Online Posterior Sampling with a Diffusion Prior

What does guidance do? A fine-grained analysis in a simple setting

Conditional Synthesis of 3D Molecules with Time Correction Sampler

Exploring DCN-like architecture for fast image generation with arbitrary resolution

Constrained Diffusion with Trust Sampling

BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models

Guiding a Diffusion Model with a Bad Version of Itself

Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching

DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning

ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling

Meta-Diffu$B$: A Contextualized Sequence-to-Sequence Text Diffusion Model with Meta-Exploration

Generating compositional scenes via Text-to-image RGBA Instance Generation

Few-Shot Diffusion Models Escape the Curse of Dimensionality

Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity

On conditional diffusion models for PDE simulations

Identifying and Solving Conditional Image Leakage in Image-to-Video Generation

PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator

GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping

Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models

Out-of-Distribution Detection with a Single Unconditional Diffusion Model

Retrieval & Fine-Tuning for In-Context Tabular Models

Can large language models explore in-context?

Learnable In-Context Vector for Visual Question Answering

ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction

BonBon Alignment for Large Language Models: on the Sweetness of Best-of-n Sampling

Synthetic Programming Elicitation and Repair for Text-to-Code in Very Low-Resource Programming Languages

GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning

DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph

Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?

A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning

OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset

Chain-of-Thought Unfaithfulness as Disguised Accuracy

Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models

Smoothie: Label Free Language Model Routing

Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads

HYDRA: Model Factorization Framework for Black-Box LLM Personalization

Expectile Regularization for Fast and Accurate Training of Neural Optimal Transport

InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling

AutoMix: Automatically Mixing Language Models

Is Programming by Example solved by LLMs?

GLBench: A Comprehensive Benchmark for Graph with Large Language Models

Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation

Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification

Graph Classification via Reference Distribution Learning: Theory and Practice

Temporal Graph Neural Tangent Kernel with Graphon-Guaranteed

Faster Local Solvers for Graph Diffusion Equations

Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs

Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases

Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?

Enhancing Graph Transformers with Hierarchical Distance Structural Encoding

Relational Concept Bottleneck Models

GPT as Visual Explainer

Evidence of Learned Look-Ahead in a Chess-Playing Neural Network

Hypothesis Testing the Circuit Hypothesis in LLMs

MambaLRP: Explaining Selective State Space Sequence Models

Testing Calibration in Nearly-Linear Time

On the Reproducibility of: "Learning Perturbations to Explain Time Series Predictions"

Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning

Long-range Brain Graph Transformer

Extracting Training Data from Molecular Pre-trained Models

Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks

Spiking Graph Neural Network on Riemannian Manifolds

Transcoders find interpretable LLM feature circuits

Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models

MeLLoC: Lossless Compression with High-order Mechanism Learning

Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP

A Functional Extension of Semi-Structured Networks

Diffusion PID: Interpreting Diffusion via Partial Information Decomposition

InversionView: A General-Purpose Method for Reading Information from Neural Activations

Who’s asking? User personas and the mechanics of latent misalignment

Pretrained Large Language Models Use Fourier Features to Compute Addition

AR-Pro: Anomaly Explanation and Repair with Formal Properties

Hyperbolic Embeddings of Supervised Models

Capability v.s. Behavior in Compositional Generalization: A Learning Dynamics Perspective

Long-form factuality in large language models

StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses

Limits of Transformer Language Models on Learning to Compose Algorithms

Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning

WizardArena: Post-training Large Language Models via Simulated Offline Chatbot Arena

Zero-Shot Tokenizer Transfer

Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback

Aligning LLM Agents by Learning Latent Preference from User Edits

Toxicity Detection for Free

Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders

Reasons and solutions for the decline in model performance after editing

Understanding Information Storage and Transfer in Multi-Modal Large Language Models

HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection

ReMoDetect: Reward Models Recognize Aligned LLM's Generations

GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages

Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization

ALS: Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment

D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models

Preference Learning Algorithms Do Not Learn Preference Rankings

$\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$

QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation

Alignment for Honesty

COLD: Causal reasOning in cLosed Daily activities

UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction

Hierarchical Hybrid Sliced Wasserstein: A Scalable Metric for Heterogeneous Joint Distributions

Multi-Instance Partial-Label Learning with Margin Adjustment

Data-Driven Discovery of Dynamical Systems in Pharmacology using Large Language Models

ESPACE: Dimensionality Reduction of Activations for Model Compression

FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation

Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs

Large Language Model-Driven Audio Codec is a Few-Shot Audio Task Learner

SSDM: Scalable Speech Dysfluency Modeling

SCOREQ: Speech Quality Assessment with Contrastive Regression

SongCreator: Lyrics-based Universal Song Generation

Should We Really Edit Language Models? On the Evaluation of Edited Language Models

Knowledge Circuit in Transformers

Efficient Convex Algorithms for Universal Kernel Learning

Wasserstein convergence of Cech persistence diagrams for samplings of submanifolds

Enriching Disentanglement: From Logical Definitions to Quantitative Metrics

FedNE: Surrogate-Assisted Federated Neighbor Embedding for Privacy-Preserving Dimensionality Reduction

Better by default: Strong pre-tuned MLPs and boosted trees on tabular data

Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization

Test-time Adaptation in Non-stationary Environments via Adaptive Representation Alignment

Enhancing Domain Adaptation through Prompt Gradient Alignment

Transferable Reinforcement Learning via Generalized Occupancy Models

SAFE: Slow and Fast Parameter-Efﬁcient Tuning for Continual Learning with Pre-Trained Models

Mixture of Adversarial LoRAs: Boosting Robust Generalization in Meta-tuning

Federated Learning over Connected Modes

CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming

Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition

Efficient Centroid-Linkage Clustering

Inference on the Change Point under a High Dimensional Covariance Shift

Generic Unsupervised Optimization for a Latent Variable Model With Exponential Family Observables

Semantic Feature Learning for Universal Unsupervised Cross-Domain Retrieval

Dynamic Neural Regeneration: Enhancing Deep Learning Generalization on Small Datasets

Learning De-Biased Representations for Remote-Sensing Imagery

TinyTTA: Efficient Test-time Adaptation via Early-exit Ensembles on Edge Devices

Large Scale Transfer Learning for Tabular Data via Language Modeling

Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learner

Structured Unrestricted-Rank Matrices for Parameter Efficient Finetuning

IWBVT: Instance Weighting-based Bias-Variance Trade-off for Crowdsourcing

Boosting Vision-Language Models with Transduction

Happy: A Debiased Learning Framework for Continual Generalized Category Discovery

Instructor-inspired Machine Learning for Robust Molecular Property Prediction

FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models

VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark

Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry

Bridge the Modality and Capacity Gaps in Vision-Language Model Selection

AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis

MQT-LLaVA: Matryoshka Query Transformer for Large Vision-Language Models

LLaNA: Large Language and NeRF Assistant

Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models

Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models

Black-Box Forgetting

LocCa: Visual Pretraining with Location-aware Captioners

FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion

Q-VLM: Post-training Quantization for Large Vision-Language Models

CountGD: Multi-Modal Open-World Counting

DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ

VisMin: Visual Minimal-Change Understanding

An End-To-End Graph Attention Network Hash for Cross-Modal Retrieval

Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration

Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment

Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models

Flexible Context-Driven Sensory Processing in Dynamical Vision Models

Temporal-Difference Learning Using Distributed Error Signals

QKFormer: Hierarchical Spiking Transformer using Q-K Attention

MiSO: Optimizing brain stimulation to create neural activity states

Neural Embedding Ranks: Aligning 3D latent dynamics with movement for long-term and cross-area decoding

Geometry of naturalistic object representations in recurrent neural network models of working memory

FEEL-SNN: Robust Spiking Neural Networks with Frequency Encoding and Evolutionary Leak Factor

Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery

Recurrent neural network dynamical systems for biological vision

Poisson Variational Autoencoder

A scalable generative model for dynamical system reconstruction from neuroimaging data

Nonlinear dynamics of localization in neural receptive fields

DeepLag: Discovering Deep Lagrangian Dynamics for Intuitive Fluid Prediction

Quadratic Quantum Variational Monte Carlo

Dual Cone Gradient Descent for Training Physics-Informed Neural Networks

Towards training digitally-tied analog blocks via hybrid gradient computation

Rethinking Parity Check Enhanced Symmetry-Preserving Ansatz

Amortized Fourier Neural Operators

From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach

Fourier Neural Operator with Learned Deformations for PDEs on General Geometries

Fourier Amplitude and Correlation Loss: Beyond Using L2 loss for Skillful Precipitation Nowcasting

Physics-Regularized Multi-Modal Image Assimilation for Brain Tumor Localization

Continuous Spatiotemporal Events Decoupling through Spike-based Bayesian Computation

A Polar Coordinate System Explicitly Represents Syntax in Language Models

Low Degree Hardness for Broadcasting on Trees

HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis

Inflationary Flows: Calibrated Bayesian Inference with Diffusion-Based Models

Hyper-opinion Evidential Deep Learning for Out-of-Distribution Detection

Hierarchical Uncertainty Exploration via Feedforward Posterior Trees

Foundation Inference Models for Markov Jump Processes

Diffusion Model-based Numerical Tabular Data Imputation: A Wasserstein Gradient Flow Perspective

FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning

eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling

Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines

Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processes

Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference

EMVP: Embracing Visual Foundation Model for Visual Place Recognition with Centroid-Free Probing

Grasp as You Say: Language-guided Dexterous Grasp Generation

GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance

Humanoid Locomotion as Next Token Prediction

MeMo: Meaningful, Modular Controllers via Noise Injection

Map It Anywhere: Empowering BEV Map Prediction using Large-scale Public Datasets

A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics

Unscrambling disease progression at scale: fast inference of event permutations with optimal transport

Mutual Information Estimation via Normalizing Flows

Bayesian Online Natural Gradient (BONG)

Constrained Sampling with Primal-Dual Langevin Monte Carlo

Efficient Streaming Algorithms for Graphlet Sampling

Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments

LaKD: Length-agnostic Knowledge Distillation for Trajectory Prediction with Any Length Observations

Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Space

Learning Cooperative Trajectory Representations for Motion Forecasting

On-Road Object Importance Estimation: A New Dataset and A Model with Multi-Fold Top-Down Guidance

CausalStock: Deep End-to-end Causal Discovery for News-driven Multi-stock Movement Prediction

UniMTS: Unified Pre-training for Motion Time Series

Shape analysis for time series

ReMAP: Neural Model Reprogramming with Network Inversion and Retrieval-Augmented Mapping for Adaptive Motion Forecasting

Are Self-Attentions Effective for Time Series Forecasting?

Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models

CALANet: Cheap All-Layer Aggregation for Human Activity Recognition

DP-SGD with Fixed-Size Minibatches: Tighter Guarantees with or without Replacement

Provably Safe Neural Network Controllers via Differential Dynamic Logic

Data-Efficient Learning with Neural Programs

Counterfactual Fairness by Combining Factual and Counterfactual Predictions

Pre-training Differentially Private Models with Limited Public Data

When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search

Self-Calibrating Conformal Prediction

TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases

WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbations

SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model

Abstracted Shapes as Tokens - A Generalizable and Interpretable Model for Time-series Classification

WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models

SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification

OSLO: One-Shot Label-Only Membership Inference Attacks

PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics

UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation

Context-aware testing: A new paradigm for tabular model testing

The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations

Representation noising effectively prevents harmful fine-tuning on LLMs

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks

Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation

MaNo: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts

Fight Back Against Jailbreaking via Prompt Adversarial Tuning

Compute-efficient LLM Training via Online Batch Selection

MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization

Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving

Language Without Borders: A Dataset and Benchmark for Code-Switching Lip Reading

Benchmarking Complex Instruction-Following with Multiple Constraints Composition

ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty

$\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise

Seeing is NOT Always Believing! Unveiling the True Symmetric Moral Consistency of Large Language Models

Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness

Learning Human-like Representations to Enable Learning Human Values

Stealth edits to large language models

Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation

Multiclass Transductive Online Learning

E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection

Active, anytime-valid risk controlling prediction sets

SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction

SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion

Learning Identifiable Factorized Causal Representations of Cellular Responses

SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures

Length Optimization in Conformal Prediction

Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning

Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution

Elliptical Attention

Leveraging an ECG Beat Diffusion Model for Morphological Reconstruction from Indirect Signals

Slight Corruption in Pre-training Data Makes Better Diffusion Models

Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection

Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models

Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction

RankRAG: Unifying Retrieval-Augmented Generation and Context Ranking in LLMs

KnowGPT: Knowledge Graph based Prompting for Large Language Models

L4GM: Large 4D Gaussian Reconstruction Model

G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering

Online Classification with Predictions

Emu3D: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials

Approaching Human-Level Forecasting with Language Models

DoFIT: Domain-aware Federated Instruction Tuning with Alleviated Catastrophic Forgetting

Embedding-Aligned Language Models

Fine-Tuning is Fine, if Calibrated

Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network

realSEUDO for real-time calcium imaging analysis

Towards Next-Generation Logic Synthesis: A Scalable Neural Circuit Generation Framework

Cell ontology guided transcriptome foundation model

InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory

Revisiting motion information for RGB-Event tracking with MOT philosophy

Instruction-Guided Visual Masking

OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents

EGSST: Event-based Graph Spatiotemporal Sensitive Transformer for Object Detection

Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity

On the Necessity of Collaboration for Online Model Selection with Decentralized Data

Loss Symmetry and Noise Equilibrium of Stochastic Gradient Descent

MoVA: Adapting Mixture of Vision Experts to Multimodal Context

DisCEdit: Model Editing by Identifying Discriminative Components

UPS: Unified Projection Sharing for Lightweight Single-Image Super-resolution and Beyond

Continual learning with the neural tangent ensemble

Scalable Constrained Policy Optimization for Safe Multi-agent Reinforcement Learning

On the Power of Decision Trees in Auto-Regressive Language Modeling

Towards Neuron Attributions in Multi-Modal Large Language Models

Set-based Neural Network Encoding Without Weight Tying

LLMs Can Evolve Continually on Modality for $\mathbb{X}$-Modal Reasoning

Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient

Harnessing Heuristics for Deep Reinforcement Learning via Constrained Optimization

Flaws can be Applause: Unleashing Potential of Segmenting Ambiguous Objects in SAM

$\text{ID}^3$: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition

Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient

(ends 7:30 PM)

7:30 p.m.

Affinity Workshop:

Bridging the Future

(ends 9:30 PM)

FRI 13 DEC

7:30 a.m.

Registration (East & West)

(ends 6:00 PM)

Break:

Coffee Break

(ends 8:30 AM)

8:30 a.m.

Invited Talk:

Learning for Interaction and Interaction for Learning

Danica Kragic

(ends 9:30 AM)

9:30 a.m.

Break:

Coffee Break

(ends 10:00 AM)

10 a.m.

Oral Session 5A: Graph Neural Networks [10:00-11:00]

Learning rigid-body simulators over implicit shapes for large-scale scenes and vision

Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning

Scale Equivariant Graph Meta Networks

(ends 11:00 AM)

Oral Session 5B: Graph Neural Networks, Causal Inference [10:00-11:00]

Exploitation of a Latent Mechanism in Graph Contrastive Learning: Representation Scattering

Do Finetti: On Causal Effects for Exchangeable Data

Identification and Estimation of the Bi-Directional MR with Some Invalid Instruments

(ends 11:00 AM)

Oral Session 5C: Machine Vision [10:00-11:00]

Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery

Convolutional Differentiable Logic Gate Networks

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

(ends 11:00 AM)

Oral Session 5D: Machine Learning and Science [10:00-11:00]

Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework

Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators

Learning Formal Mathematics From Intrinsic Motivation

(ends 11:00 AM)

Overflow for Oral Session 5B: Graph Neural Networks, Causal Inference [10:00-11:00]

(ends 11:00 AM)

Overflow for Oral Session 5D: Machine Learning and Science [10:00-11:00]

(ends 11:00 AM)

11 a.m.

Poster Session 5 West [11:00-2:00]

Posters 11:00-2:00

Do Finetti: On Causal Effects for Exchangeable Data

Identifiability Analysis of Linear ODE Systems with Hidden Confounders

QWO: Speeding Up Permutation-Based Causal Discovery in LiGAMs

Identification and Estimation of the Bi-Directional MR with Some Invalid Instruments

Detecting and Measuring Confounding Using Causal Mechanism Shifts

Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data

Identifying Selections for Unsupervised Subtask Discovery

Causal Effect Identification in a Sub-Population with Latent Variables

On Causal Discovery in the Presence of Deterministic Relations

Towards Estimating Bounds on the Effect of Policies under Unobserved Confounding

InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models

ShopBench: A Massive Multi-Task Online Shopping Benchmark for Large Language Models

PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition

BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity

ReMI: A Dataset for Reasoning with Multiple Images

IaC-Eval: A code generation benchmark for Infrastructure-as-Code programs

Building Timeseries Dataset: Empowering Large-Scale Building Analytics

OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking

Beyond Aesthetics: Cultural Competence in Text-to-Image Models

StackEval: Benchmarking LLMs in Coding Assistance

IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS

PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models

emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography

Is Function Similarity Over-Engineered? Building a Benchmark

SETBENCH: Assessing the Analytical and Semantic Robustness of Language Models

Multi-modal Situated Reasoning in 3D Scenes

CARE: a Benchmark Suite for the Classification and Retrieval of Enzymes

DreamCatcher: A Wearer-aware Multi-modal Sleep Event Dataset Based on Earables in Non-restrictive Environments

The iNaturalist Sounds Dataset

BertaQA: How Much Do Language Models Know About Local Culture?

OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Construction

WelQrate: Defining the Gold Standard in Small Molecule Drug Discovery Benchmarking

DF40: Toward Next-Generation Deepfake Detection

BLURD: Benchmarking and Learning using a Unified Rendering and Diffusion Model

EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes

FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving

CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs

DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents

emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation

GTA: A Benchmark for General Tool Agents

PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs

CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities

$\texttt{dopanim}$: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans

Copycats: the many lives of a publicly available medical imaging dataset

BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval

Indoor Air Quality Dataset with Activities of Daily Living in Low to Middle-income Communities

FT-AED: Benchmark Dataset for Early Freeway Traffic Anomalous Event Detection

STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics

RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation

CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding

Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline

Vocal Call Locator Benchmark (VCL'24) for localizing rodent vocalizations from multi-channel audio

Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models

ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models

Fit for our purpose, not yours: Benchmark for a low-resource, Indigenous language

Seshat Global History Databank Text Dataset and Benchmark of Large Language Models' History Knowledge

Testably Learning Polynomial Threshold Functions

Wide Two-Layer Networks can Learn from Adversarial Perturbations

Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering Playlists

Improving Subgroup Robustness via Data Selection

CultureLLM: Incorporating Cultural Differences into Large Language Models

Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium

The Fairness-Quality Tradeoff in Clustering

Mind the Graph When Balancing Data for Fairness or Robustness

Proportional Fairness in Clustering: A Social Choice Perspective

FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation

SeafloorGenAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey

On the Efficiency of ERM in Feature Learning

Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random

Fair Online Bilateral Trade

Building a stable classifier with the inflated argmax

Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss

Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise

Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method

On the Limitations of Fractal Dimension as a Measure of Generalization

Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness

Dynamics of Supervised and Reinforcement Learning in the Non-Linear Perceptron

Online Consistency of the Nearest Neighbor Rule

Online Learning with Sublinear Best-Action Queries

Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment

Multi-Label Learning with Stronger Consistency Guarantees

Implicit Optimization Bias of Next-token Prediction in Linear Models

The Implicit Bias of Adam on Separable Data

Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance

Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input

Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks

How many classifiers do we need?

Improved Sample Complexity for Multiclass PAC Learning

Understanding the Gains from Repeated Self-Distillation

Generalized Linear Bandits with Limited Adaptivity

Dynamic Service Fee Pricing under Strategic Behavior: Actions as Instruments and Phase Transition

Nearly Minimax Optimal Submodular Maximization with Bandit Feedback

Symmetric Linear Bandits with Hidden Symmetry

Truthfulness of Calibration Measures

Online Convex Optimisation: The Optimal Switching Regret for all Segmentations Simultaneously

The Minimax Regret of Sequential Probability Assignment, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood

Bandits with Preference Feedback: A Stackelberg Game Perspective

Optimization Algorithm Design via Electric Circuits

Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training

Sparse maximal update parameterization: A holistic approach to sparse training dynamics

Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences

A Bayesian Approach to Data Point Selection

SymILO: A Symmetry-Aware Learning Framework for Integer Linear Optimization

Cronos: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks

Scalable Kernel Inverse Optimization

The Power of Extrapolation in Federated Learning

Learning with Fitzpatrick Losses

A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints

SPARKLE: A Unified Single-Loop Primal-Dual Framework for Decentralized Bilevel Optimization

An Accelerated Gradient Method for Convex Smooth Simple Bilevel Optimization

Tighter Convergence Bounds for Shuffled SGD via Primal-Dual Perspective

Sample-Efficient Geometry Reconstruction from Euclidean Distances using Non-Convex Optimization

Quantitative Convergences of Lie Group Momentum Optimizers

Single-loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions

High-probability complexity bounds for stochastic non-convex minimax optimization

Sample-efficient Bayesian Optimisation Using Known Invariances

Query-Efficient Correlation Clustering with Noisy Oracle

Transition Constrained Bayesian Optimization via Markov Decision Processes

Active Set Ordering

Bayesian Optimization of Functions over Node Subsets in Graphs

Private Attribute Inference from Images with Vision-Language Models

PANORAMIA: Efficient Privacy Auditing of Machine Learning Models without Retraining

Universal Exact Compression of Differentially Private Mechanisms

On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift

Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning

Exclusively Penalized Q-learning for Offline Reinforcement Learning

DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors

DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction

Differentially Private Equivalence Testing for Continuous Distributions and Application

Pandora's Box: Towards Building Universal Attackers against Real-World Large Vision-Language Models

Private Online Learning via Lazy Algorithms

Private Geometric Median

Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity

PrivCirNet: Efficient Private Inference via Block Circulant Transformation

Membership Inference Attacks against Large Language Models via Self-prompt Calibration

Trap-MID: Trapdoor-based Defense against Model Inversion Attacks

Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning

Multi-Task Prompt Decision Transformer for Efficient Unseen Task Generalization

Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control

OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators

Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?

Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning

XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX

The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space

Do's and Don'ts: Learning Desirable Skills with Instruction Videos

Effective Exploration Based on the Structural Information Principles

Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration

Policy-shaped prediction: avoiding distractions in model-based RL

Bigger, Regularized, Optimistic: scaling for compute and sample efficient continuous control

Robust Reinforcement Learning from Corrupted Human Feedback

Building Network Architectures for Continual Reinforcement Learning with Parseval Regularization

Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers

Diffusion for World Modeling: Visual Details Matter in Atari

DiffTOP: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning

Adaptive Preference Scaling for Reinforcement Learning with Human Feedback

Hierarchical Programmatic Option Framework for Solving Long and Repetitive Tasks

Deep Policy Gradient Without Batch Updates or a Replay Buffer

C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory

Regularized Q-Learning

The Power of Resets in Online Reinforcement Learning

Efficient Algorithm and Improved Regret for RL with Multinomial Logit Function Approximation

N-agent Ad Hoc Teamwork

Episodic Future Thinking Reinforcement Learning for Social Decision-making

Inverse Factorized Soft Q-Learning for Cooperative Multi-agent Imitation Learning

Flipping-based Policy for Chance-Constrained Markov Decision Processes

Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning

Robust Reinforcement Learning with General Utility

Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning

Task-Agnostic Machine Learning-Assisted Inference

Contrastive dimension reduction: when and how?

Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator

Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms

Fixed Confidence Best Arm Identification in the Bayesian Setting

A Robust Mixed-Effects Bandit Algorithm for Assessing Mobile Health Interventions

Strategic Linear Contextual Bandits

How to Scale Inverse RL to Large State Spaces? A Provably Efficient Approach

WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment

The surprising efficiency of temporal difference learning for rare event prediction

Linear Causal Bandits: Unknown Graph and Soft Interventions

Robust group and simultaneous inferences for high-dimensional single index model

Toward Conditional Distribution Calibration in Survival Prediction

Conditional Outcome Equivalence: A Quantile Alternative to CATE

Robust Offline Active Learning on Graphs

Active preference learning for ordering items in- and out-of-sample

Sample Complexity Reduction through Policy Difference Estimation in RL

Near-Equivalence Between Bounded Regret and Delay Robustness in Interactive Decision Making

Theoretical Analysis of Weak-to-Strong Generalization

FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning

Interpret Your Decision: Logical Reasoning Regularization for Generalization in Visual Classification

PACE: marrying the generalization of PArameter-efficient fine-tuning with Consistency rEgularization

Label Noise: Ignorance Is Bliss

Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift

Nonparametric Evaluation of Noisy ICA Solutions

Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies

Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithm

Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation

How Does Variance Shape the Regret in Contextual Bandits?

Mutual Information Estimation via $f$-Divergence and Data Derangements

User-Creator Feature Dynamics in Recommender Systems with Dual Influence

Incentivizing Quality Text Generation via Statistical Contracts

Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms

Bias Detection via Signaling

Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits

Adversarially Robust Dense-Sparse Tradeoffs via Heavy-Hitters

Minimum Entropy Coupling with Bottleneck

In-and-Out: Algorithmic Diffusion for Sampling Convex Bodies

Fairness and Efficiency in Online Class Matching

On the Ability of Developers' Training Data Preservation of Learnware

Optimal Algorithms for Learning Partitions with Faulty Oracles

HEMM: Holistic Evaluation of Multimodal Foundation Models

Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos

Private and Personalized Frequency Estimation in a Federated Setting

Learning to Shape In-distribution Feature Space for Out-of-distribution Detection

Online Feature Updates Improve Online (Generalized) Label Shift Adaptation

GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration

Diffusion Representation for Reinforcement Learning

Optimizing the coalition gain in Online Auctions with Greedy Structured Bandits

Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models

Diffusion Policies creating a Trust Region for Offline Reinforcement Learning

SIRIUS : Contexual Sparisty with Correction for Efficient LLMs

Dynamic Subgroup Identification in Covariate-adjusted Response-adaptive Randomization Experiments

Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models

Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation

I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing

Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization

Understanding Visual Feature Reliance through the Lens of Complexity

GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning

Local to Global: Learning Dynamics and Effect of Initialization for Transformers

MergeMinds: Boosting Multilingual Reasoning with the Built-in Capabilities of LLMs

A Theoretical Understanding of Self-Correction through In-context Alignment

Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration Bonus

Exploitation of a Latent Mechanism in Graph Contrastive Learning: Representation Scattering

Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learner

The Closeness of In-Context Learning and Weight Shifting for Softmax Regression

ContextGS : Compact 3D Gaussian Splatting with Anchor Level Context Model

Label Delay in Online Continual Learning

S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity

Flex-MoE: Addressing Missing Modalities in Alzheimer’s Disease with Flexible Mixture-of-Experts

Action Imitation in Common Action Space for Customized Action Image Synthesis

ReFT: Representation Finetuning for Language Models

What Rotary Position Embedding Can Tell Us: Identifying Query and Key Weights Corresponding to Basic Syntactic or High-level Semantic Information

UDC: A Unified Neural Divide-and-Conquer Framework for Large-Scale Combinatorial Optimization Problems

Don't Look Twice: Faster Video Transformers with Run-Length Tokenization

Symmetry-Informed Governing Equation Discovery

Learning Elastic Costs to Shape Monge Displacements

On Feature Learning in Structured State Space Models

LotCLIP: Improving Language-Image Pre-training for Long Text Understanding

Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit

Learning from Highly Sparse Spatio-temporal Data

Everyday Object Meets Vision-and-Language Navigation Agent via Backdoor

Quantum Algorithms for Non-smooth Non-convex Optimization

Large Scene Model: Real-time Unposed Images to Semantic 3D

(ends 2:00 PM)

Poster Session 5 East [11:00-2:00]

Posters 11:00-2:00

G2D: From Global to Dense Radiography Representation Learning via Vision-Language Pre-training

Differentiable Modal Synthesis for Physical Modeling of Planar String Sound and Motion Simulation

Trajectory Flow Matching with Applications to Clinical Time Series Modelling

FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making

Learning to compute Gröbner bases

Unsupervised Discovery of Formulas for Mathematical Constants

Hybrid Generative AI for De Novo Design of Co-Crystals with Enhanced Tabletability

Newton Informed Neural Operator for Computing Multiple Solutions of Nonlinear Partials Differential Equations

Self-Guiding Exploration for Combinatorial Problems

DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data

Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy

Enhancing vision-language models for medical imaging: bridging the 3D gap with innovative slice selection

Pruning neural network models for gene regulatory dynamics using data and domain knowledge

Gene-Gene Relationship Modeling Based on Genetic Evidence for Single-Cell RNA-Seq Data Imputation

Training Compute-Optimal Protein Language Models

GenAI Arena: An Open Evaluation Platform for Generative Models

Multiview Scene Graph

Improving Ab-Initio Cryo-EM Reconstruction with Semi-Amortized Pose Inference

Exploring Fixed Point in Image Editing: Theoretical Support and Convergence Optimization

Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features

DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation

Slot-VLM: Object-Event Slots for Video-Language Modeling

AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos

ContactField: Implicit Field Representation for Multi-Person Interaction Geometry

Pseudo-Siamese Directional Transformers for Self-Supervised Real-World Denoising

Seeing Beyond the Crop: Using Language Priors for Out-of-Bounding Box Keypoint Prediction

OpenDlign: Enhancing Open-World 3D Learning with Depth-Aligned Images

Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priors

Metric from Human: Zero-shot Monocular Metric Depth Estimation via Test-time Adaptation

ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings

UV-free Texture Generation with Denoising and Heat Diffusion

Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent Coding

Context and Geometry Aware Voxel Transformer for Semantic Scene Completion

SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams

Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials

All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation

Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration

Diffusion Priors for Variational Image Denoising

Accelerating Transformers with Spectrum-Preserving Token Merging

DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Rendering

PhyRecon: Physically Plausible Neural Scene Reconstruction

ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images

Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos

Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections

QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model

MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging

Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach

MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing

DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model

Visual Fourier Prompt Tuning

A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation

Quality-Improved and Property-Preserved Polarimetric Imaging via Complementarily Fusing

IllumiNeRF: 3D Relighting without Inverse Rendering

Adaptive Domain Learning for Cross-domain Image Denoising

Fully Explicit Dynamic Gaussian Splatting

Grid4D: 4D Decomposed Hash Encoding for High-fidelity Dynamic Scene Rendering

Learning Truncated Causal History Model for Video Restoration

OPS: Occupancy Prediction as A Sparse Set

Generalizable Implicit Motion Modeling for Video Frame Interpolation

A Simple yet Universal Framework for Depth Completion

Revisiting the Integration of Convolution and Attention for Vision Backbone

Skinned Motion Retargeting with Dense Geometric Interaction Perception

Can We Leave Deepfake Data Behind in Training Deepfake Detector?

Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms

Binarized Diffusion Model for Image Super-Resolution

A Prompt Learning based Regulation Framework for Generalizable Point Cloud Analysis

Vision-Language Models are Strong Noisy Label Detectors

To Err like Human: Affective Bias-Inspired Measures for Visual Emotion Recognition Evaluation

Recovering Complete Actions for Cross-dataset Skeleton Action Recognition

Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization

AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation

ACFun: Abstract-Concrete Fusion Facial Stylization

Towards Learning Group-Equivariant Features for Domain Adaptive 3D Detection

E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation

Hybrid Mamba for Few-Shot Segmentation

InstructG2I: Synthesizing Images from Multimodal Attributed Graphs

An Image is Worth 32 Tokens for Reconstruction and Generation

Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling

Scaling the Codebook Size of VQ-GAN to 100,000 with a Utilization Rate of 99%

ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis

How Diffusion Models Learn to Factorize and Compose

RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance

Smoothed Energy Guidance: Guiding Diffusion Models by Attenuating Energy Curvature of Attention

Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models.

Learning Frequency-aware Vision Foundation Model for Domain Generalized Semantic Segmentation

DeiSAM: Segment Anything with Deictic Prompting

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation

GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs

Toward Real Ultra Image Segmentation: Leveraging Surrounding Context to Cultivate General Segmentation Model

Unleashing Multispectral Video's Potential in Semantic Segmentation: A Semi-supervised Viewpoint and New UAV-View Benchmark

SyncVIS: Synchronized Video Instance Segmentation

General Detection-based Text Line Recognition

MVSplat360: Benchmarking 360$\textdegree$ Generalizable 3D Novel View Synthesis from Sparse Views

StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation

A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation

Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning

Provable and Efficient Dataset Distillation for Kernel Ridge Regression

Distribution-Aware Data Expansion with Diffusion Models

Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization

Boundary Matters: A Bi-Level Active Finetuning Method

TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Series

TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation

OnlineTAS: An Online Baseline for Temporal Action Segmentation

Is Multiple Object Tracking a Matter of Specialization?

Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection?

MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning

GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching

Evaluation of Text-to-Video Generation Models: A Dynamics Perspective

Distilling Costly Set Functions to Parametric Families

Data Selection for Task-Specific Model Finetuning

[Re] CUDA: Curriculum of Data Augmentation for Long‐tailed Recognition

FedAvP: Augment Local Data via Shared Policy in Federated Learning

Most Influential Subset Selection: Challenges, Promises, and Beyond

2D-OOB: Attributing Data Contribution through Joint Valuation Framework

Make the Most of Your Data: Changing the Training Data Distribution to Improve Generalization

DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving

Compact Language Models via Pruning and Knowledge Distillation

4-bit Shampoo for Memory-Efficient Network Training

ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization

On Sampling Strategies for Spectral Model Sharding

Efficient Attention using Low-Dimensional Keys

Activating Self-Attention for Multi-Scene Absolute Pose Regression

Real-time Core-Periphery Guided ViT with Smart Data Layout Selection on Mobile Devices

Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding

Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers

Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers

The Fine-Grained Complexity of Gradient Computation for Training Large Language Models

Improving Deep Learning Performance through Constrained Parameter Regularization

VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks

Scalable and Stable Parallelization of Nonlinear RNNs

Diversify, Contextualize, and Adapt: Efficient Entropy Modeling for Neural Image Codec

Exploring Context Window of Large Language Models via Decomposed Positional Vectors

Gradient-free Decoder Inversion in Latent Diffusion Models

Learning Complete Protein Representation by Dynamically Coupling of Sequence and Structure

Embedding Dimension of Contrastive Learning and $k$-Nearest Neighbors

Classification Done Right for Vision-Language Pre-Training

Efficiency for Free: Ideal Data Are Transportable Representations

Interactive Deep Clustering via Value Mining

Latent functional maps

What Variables Affect Out-Of-Distribution Generalization in Pretrained Models?

MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts

Critically Assessing the State of the Art in Neural Network Verification

Is Your HD Map Constructor Reliable under Sensor Corruptions?

Topological obstruction to the training of shallow ReLU neural networks

Harnessing small projectors and multiple views for efficient vision pretraining

Accelerating Self-supervised Learning Pretraining

SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations

Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations

GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models

Adaptive Labeling for Efficient Out-of-distribution Model Evaluation

SuperDeepFool: a new fast and accurate minimal adversarial attack

The Implicit Bias of Gradient Descent toward Collaboration between Layers: A Dynamic Analysis of Multilayer Perceptions

Improving self-training under distribution shifts via anchored confidence with theoretical guarantees

WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks

Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection

On Learning Physical Neural Representations of Dynamical Data

Deep Support Vectors

How does PDE order affect the convergence of PINNs?

A New Neural Kernel Regime: The Inductive Bias of Multi-Task Training

Clustering in Causal Attention Masking

Polyhedral Complex Derivation from Piecewise Trilinear Networks

Debiasing Synthetic Data Generated by Deep Generative Models

An exactly solvable model for emergence and scaling laws

Hardness of Learning Neural Networks under the Manifold Hypothesis

Nature-Inspired Local Propagation

Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension

MINI-SEQUENCE TRANSFORMER: Optimizing Intermediate Memory for Long Sequences Training

Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning

Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models

Understanding and Minimising Outlier Features in Neural Network Training

UQ-Guided Hyperparameter Optimization for Iterative Learners

$\textit{Read-ME}$: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design

MatrixNet: Learning over symmetry groups using learned group representations

A structure-aware framework for learning device placements on computation graphs

NeuralThink: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks

Where Do Large Learning Rates Lead Us?

Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers

Resolving Discrepancies in Compute-Optimal Scaling of Language Models

Convolutional Differentiable Logic Gate Networks

OccFusion: Rendering Occluded Humans with Generative Diffusion Priors

GuardT2I: Defending Text-to-Image Models from Adversarial Prompts

A Critical Evaluation of AI Feedback for Aligning Large Language Models

Energy-Guided Continuous Entropic Barycenter Estimation for General Costs

Pessimistic Backward Policy for GFlowNets

Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling

Group Robust Preference Optimization in Reward-free RLHF

Grounded Answers for Multi-agent Decision-making Problem through Generative World Model

Voila-A: Aligning Vision-Language Models with User's Gaze Attention

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models

Optimal Flow Matching: Learning Straight Trajectories in Just One Step

TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency Models

Unified Guidance for Geometry-Conditioned Molecular Generation

Discrete Flow Matching

Understanding and Improving Training-free Loss-based Diffusion Guidance

Multistep Distillation of Diffusion Models via Moment Matching

Simple and Fast Distillation of Diffusion Models

DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models

Fisher Flow Matching for Discrete Data

Locating What You Need: Towards Adapting Diffusion Models to OOD Concepts In-the-Wild

Efficient LLM Scheduling by Learning to Rank

Adversarial Generation of Hierarchical Gaussians for 3D Generative Model

SnapKV: LLM Knows What You are Looking for Before Generation

Search for Efficient Large Language Models

HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors

BrainBits: How Much of the Brain are Generative Reconstruction Methods Using?

KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis

PTQ4DiT: Post-training Quantization for Diffusion Transformers

AID: Attention Interpolation of Text-to-Image Diffusion

How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?

YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals

Optical Diffusion Models for Image Generation

Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion models

ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models

Images that Sound: Composing Images and Sounds on a Single Canvas

Diffusion Twigs with Loop Guidance for Conditional Graph Generation

Efficient Prompt Optimization Through the Lens of Best Arm Identification

UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation

Fine-grained Analysis of In-context Linear Estimation

Localized Zeroth-Order Prompt Optimization

Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars

Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning

Solving Inverse Problems via Diffusion Optimal Control

Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs

Towards Editing Time Series

A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models

Phased Consistency Model

SubgDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning

Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models

Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inference

Are Large Language Models Good Statisticians?

Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity

Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs

On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion

Leveraging Environment Interaction for Automated PDDL Generation and Planning with Large Language Models

Transformers Can Do Arithmetic with the Right Embeddings

Code Repair with LLMs gives an Exploration-Exploitation Tradeoff

Learning Formal Mathematics From Intrinsic Motivation

NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noise

Uncovering the Redundancy in Graph Self-supervised Learning Models

Generalizing CNNs to graphs with learnable neighborhood quantization

Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptative Residual Module

Improving Temporal Link Prediction via Temporal Walk Matrix Projection

The Intelligible and Effective Graph Neural Additive Network

Learning rigid-body simulators over implicit shapes for large-scale scenes and vision

Analysis of Corrected Graph Convolutions

Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective

Almost Surely Asymptotically Constant Graph Neural Networks

A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening

Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning

Scale Equivariant Graph Meta Networks

On the Expressivity and Sample Complexity of Node-Individualized Graph Neural Networks

An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning

Graph Neural Networks Need Cluster-Normalize-Activate Modules

Long-range Meta-path Search on Large-scale Heterogeneous Graphs

On the Scalability of GNNs for Molecular Graphs

DisenGCD: A Meta Multigraph-assisted Disentangled Graph Learning Framework for Cognitive Diagnosis

If You Want to Be Robust, Be Wary of Initialization

Enhancing Robustness of Graph Neural Networks on Social Media with Explainable Inverse Reinforcement Learning

Autonomous Agent for Collaborative Task under Information Asymmetry

SEL-BALD: Deep Bayesian Active Learning for Selective Labeling with Instance Rejection

InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques

Towards Multi-dimensional Explanation Alignment for Medical Classification

Finding Transformer Circuits With Edge Pruning

A hierarchical decomposition for explaining ML performance discrepancies

Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge

Listenable Maps for Zero-Shot Audio Classifiers

Data-faithful Feature Attribution: Mitigating Unobservable Confounders via Instrumental Variables

Learning to Understand: Identifying Interactions via the Möbius Transform

Navigating the Effect of Parametrization for Dimensionality Reduction

Using Noise to Infer Aspects of Simplicity Without Learning

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models

STL: Still Tricky Logic (for System Validation, Even When Showing Your Work)

Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Models

Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?

Ensuring Right Prediction With Right Rationale

Measuring Per-Unit Interpretability at Scale Without Humans

Interpreting Learned Feedback Patterns in Large Language Models

Understanding Emergent Abilities of Language Models from the Loss Perspective

Improving Context-Aware Preference Modeling for Language Models

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search

Bias Amplification in Language Model Evolution: An Iterated Learning Perspective

Self-Retrieval: End-to-End Information Retrieval with One Large Language Model

Do LLMs Build World Representations? Probing Through the Lens of State Abstraction

PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications

CiteME: Can Language Models Accurately Cite Scientific Claims?

ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models

Self-Evolution Decoding for Improving Factuality in Large Language Models

Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases

MKGL: Mastery of a Three-Word Language

Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance

Evaluate calibration of language models with folktexts

Image-aware Evaluation of Generated Medical Reports

IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons

Understanding Transformers via N-Gram Statistics

Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models

MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models

ConStat: Performance-Based Contamination Detection in Large Language Models

SimPO: Simple Preference Optimization with a Reference-Free Reward

ProgressGym: Alignment with a Millennium of Moral Progress

FINALLY: fast and universal speech enhancement with studio-like quality

CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations

CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing

Post-Hoc Reversal: Are We Selecting Models Prematurely?

Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators

A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Need

Multi-Label Open Set Recognition

Dense Associative Memory Through the Lens of Random Features

Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution

Collaborative Refining for Learning from Inaccurate Labels

Transfer Learning with Informative Priors: Simple Baselines Better than Previously Reported

Implicit regularization of multi-task learning and finetuning: multiple regimes of feature reuse

Renovating Names in Open-Vocabulary Segmentation Benchmarks

Cross-modal Representation Flattening for Multi-modal Domain Generalization

An eye for an ear: zero-shot audio description leveraging an image captioner with audio-visual token distribution matching

Scaling Sign Language Translation

Training-Free Visual Prompt Learning for Multimodal Large Language Models

Tackling Uncertain Correspondences for Multi-Modal Entity Alignment

Grounding Multimodal Large Language Models in Actions

ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs

Image2Struct: A Benchmark for Evaluating Vision-Language Models in Extracting Structured Information from Images

Continuous Partitioning for Graph-Based Semi-Supervised Learning

Reinforcement Learning-Guided Semi-Supervised Learning

Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

GrootVL: Tree Topology is All You Need in State Space Model

Unity by Diversity: Improved Representation Learning for Multimodal VAEs

UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models

Frustratingly Easy Test-Time Adaptation of Vision-Language Models

Adaptive Image Quality Assessment via Teaching Large Multimodal Models to Compare

CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models

Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering

Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning

RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models

Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex.

Bridging semantics and pragmatics in information-theoretic emergent communication

Long-Range Feedback Spiking Network Captures Dynamic and Static Representations of the Visual Cortex under Movie Stimuli

Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception

fMRI predictors based on language models of increasing complexity recover brain left lateralization

Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion

Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuli

Neural decoding from stereotactic EEG: accounting for electrode variability across subjects

Visual Pinwheel Center Act as Geometric Saliency Detector

Partial observation can induce mechanistic mismatches in data-constrained models of neural dynamics

Spectral Learning of Shared Dynamics Between Generalized-Linear Processes

NeuMA: Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics

Rethinking the Dynamics of Spiking Neural Networks

Unconditional stability of a recurrent neural circuit implementing divisive normalization

SpikedAttention: Training-Free and Fully Spike-Driven Transformer-to-SNN Conversion with Winner-Oriented Spike Shift for Softmax Operation

Du-IN: Discrete units-guided mask modeling for decoding speech from Intracranial Neural signals

Feedback control guides credit assignment in biological circuits

Combining Observational Data and Language for Species Range Estimation

Neural Persistence Dynamics

FNP: Fourier Neural Processes for Arbitrary-Resolution Data Assimilation

DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks

Symbolic Regression with a Learned Concept Library

Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model

Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning

The Importance of Being Scalable: Efficient Architectures for Neural Network Potentials

NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory

Robust Gaussian Processes via Relevance Pursuit

Amortized Bayesian Experimental Design for Decision-Making

Practical Bayesian Algorithm Execution via Posterior Sampling

BMRS: Bayesian Model Reduction for Structured Pruning

Deep Bayesian Active Learning for Preference Modeling in Large Language Models

Learning via Surrogate PAC-Bayes

Sourcerer: Sample-based Maximum Entropy Source Distribution Estimation

Neural Conditional Probability for Inference

Avoiding Undesired Future with Minimal Cost in Non-Stationary Environments

Expected Probabilistic Hierarchies

Streaming Bayes GFlowNets

Parametric model reduction of mean-field and stochastic systems via higher-order action matching

Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes

Gradient-based Discrete Sampling with Automatic Cyclical Scheduling

Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion

Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows

Globally Convergent Variational Inference

Asymptotics of Alpha-Divergence Variational Inference Algorithms with Exponential Families

Particle Semi-Implicit Variational Inference

ClevrSkills: Compositional Language And Visual Understanding in Robotics

Simulated Humanoid Grasping on Diverse Objects

Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks

GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation

DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control

From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection

Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction

Retrieval-Augumented Diffusion Models for Time Series Forecasting

Multivariate Probabilistic Time Series Forecasting with Correlated Errors

From Similarity to Superiority: Channel Clustering for Time Series Forecasting

Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting

Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective

Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis

Mechanism Design Through Exploration Control: Optimizing the Trade-Off Between User and Creator Engagement

The Effectiveness of Surprisingly Popular Voting with Partial Preferences

Pricing and Competition for Generative AI

Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving

Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework

Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting

Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study

PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

On the Adversarial Robustness of Benjamini Hochberg

MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities

The Best of Both Worlds: Toward an Honest and Helpful Large Language Model

Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness

Towards Calibrated Robust Fine-Tuning of Vision-Language Models

Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models

SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents

HyperLogic: Enhancing Diversity and Accuracy in Rule Learning with HyperNets

Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning

Unelicitable Backdoors via Cryptographic Transformer Circuits

Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data

Designs for Enabling Collaboration in Human-Machine Teaming via Interactive and Explainable Systems

Faster Repeated Evasion Attacks in Tree Ensembles

Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning

Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups

MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability

Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness

ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation

Provable Editing of Deep Neural Networks using Parametric Linear Relaxation

Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities

Query-Based Adversarial Prompt Generation

Efficient multi-prompt evaluation of LLMs

RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees

CoLLaM: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models

GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shifts

Terra: A Multimodal Spatio-Temporal Dataset Spanning the Earth

UniTox: Leveraging LLMs to Curate a Unified Dataset of Drug-Induced Toxicity from FDA Labels

LibAMM: Empirical Insights into Approximate Computing for Accelerating Matrix Multiplication

Learning Superconductivity from Ordered and Disordered Material Structures

INQUIRE: A Natural World Text-to-Image Retrieval Benchmark

FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner

Noise Contrastive Alignment of Language Models with Explicit Rewards

SOAP: Enhancing Efficiency of generated Code via Self-Optimization

Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting

Non-convolutional graph neural networks.

SpecExec: Massively Parallel Speculative Decoding For Interactive LLM Inference on Consumer Devices

OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation

Achievable distributional robustness when the robust risk is only partially identified

Enhancing Large Vision Language Models with Self-Training on Image Comprehension

Spatio-Spectral Graph Neural Networks

Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery

Invisible Image Watermarks Are Provably Removable Using Generative AI

IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation

Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models

Observational Scaling Laws and the Predictability of Langauge Model Performance

Leveraging Separated World Model for Exploration in Visually Distracted Environments

GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts

U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers

Online Iterative Reinforcement Learning from Human Feedback with General Preference Model

Universal Neural Functionals

UniIF: Unified Molecule Inverse Folding

FUSE: Fast Unified Simulation and Estimation for PDEs

Domain Adaptation for Large-Vocabulary Object Detectors

Noether's Razor: Learning Conserved Quantities

Generalization Analysis for Label-Specific Representation Learning

Auditing Local Explanations is Hard

Octopus: A Multi-modal LLM with Parallel Recognition and Sequential Understanding

Infinite Limits of Multi-head Transformer Dynamics

Direct Preference-Based Evolutionary Multi-Objective Optimization with Dueling Bandits

SparseLLM: Towards Global Pruning of Pre-trained Language Models

Tell What You Hear From What You See - Video to Audio Generation Through Text

RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation

Convergence of $\log(1/\epsilon)$ for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis

AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models

Exploring Token Pruning in Vision State Space Models

(ends 2:00 PM)

1 p.m.

Break:

Lunch Break

(ends 2:30 PM)

1:45 p.m.

Test Of Time:

Test of Time

(ends 2:30 PM)

2:30 p.m.

Invited Talk:

How to optimize what matters most?

Rosalind Picard

(ends 3:30 PM)

3:30 p.m.

Oral Session 6A: Machine Learning and Science, Safety [3:30-4:30]

Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations

MDAgents: An Adaptive Collaboration of LLMs for Medical Decision Making

Graph Diffusion Transformer for Multi-Conditional Molecular Generation

(ends 4:30 PM)

Oral Session 6B: Safety, New Data [3:30-4:30]

Achieving Efficient Alignment through Learned Correction

Bayesian-Guided Label Mapping for Visual Reprogramming

A Taxonomy of Challenges to Curating Fair Datasets

(ends 4:30 PM)

Oral Session 6C: New Data [3:30-4:30]

MedCalc-Bench: Evaluating Large Language Models for Medical Calculations

Brain Treebank: Large-scale intracranial recordings from naturalistic language stimuli

ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction

(ends 4:30 PM)

Oral Session 6D: Deep Learning Architecture, Infrastructure [3:30-4:30]

DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices

You Only Cache Once: Decoder-Decoder Architectures for Language Models

MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map

(ends 4:30 PM)

Overflow for Oral Session 6B: Safety, New Data [3:30-4:30]

(ends 4:30 PM)

Overflow for Oral Session 6C: New Data [3:30-4:30]

(ends 4:30 PM)

4:30 p.m.

Break:

Coffee Break

(ends 5:30 PM)

Poster Session 6 West [4:30-7:30]

Posters 4:30-7:30

Partial Transportability for Domain Generalization

Automated Efficient Estimation using Monte Carlo Efficient Influence Functions

Graph Structure Inference with BAM: Introducing the Bilinear Attention Mechanism

Tangent Space Causal Inference: Leveraging Vector Fields for Causal Discovery in Dynamical Systems

Consistency of Neural Causal Partial Identification

Identifying Causal Effects Under Functional Dependencies

On the Complexity of Identification in Linear Structural Causal Models

A Simple yet Scalable Granger Causal Structural Learning from Topological Event Sequences

A Benchmark Suite for Systematically Evaluating Reasoning Shortcuts

UrbanDataLayer: A Unified Data Pipeline for Urban Science

Lean Workbook: A large-scale Lean problem set formalized from natural language math problems

Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

MathPile: A Billion-Token-Scale Pretraining Corpus for Math

CRAG - Comprehensive RAG Benchmark

NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates

3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition

Streaming Detection of Queried Event Start

Instruction Tuning Large Language Models to Understand Electronic Health Records

TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning

DataComp-LM: In search of the next generation of training sets for language models

MassSpecGym: A benchmark for the discovery and identification of molecules

RelBench: A Benchmark for Deep Learning on Relational Databases

ClashEval: Quantifying the tug-of-war between an LLM’s internal prior and external evidence

WindsorML - High-Fidelity Computational Fluid Dynamics Dataset For Automotive Aerodynamics

Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset

Benchmark Repositories for Better Benchmarking

CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models

WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark

PEACE: A Dataset of Pharmaceutical Care for Cancer Pain Analgesia Evaluation and Medication Decision

EgoSim: An Egocentric Multi-view Simulator for Body-worn Cameras during Human Motion

Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving

UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling

On the Effects of Data Scale on Computer Control Agents

LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment

Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments

MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs

ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction

Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox

EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations

A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data

A New Multi-Source Light Detection Benchmark and Semi-Supervised Focal Light Detection

LucidAction: A Hierarchical and Multi-model Dataset for Comprehensive Action Quality Assessment

HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection

Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs

Paloma: A Benchmark for Evaluating Language Model Fit

Efficient Lifelong Model Evaluation in an Era of Rapid Progress

Fair Kernel K-Means: from Single Kernel towards Multiple Kernel

Achievable Fairness on Your Data With Utility Guarantees

A Closer Look at AUROC and AUPRC under Class Imbalance

Fairness in Social Influence Maximization via Optimal Transport

Fair Wasserstein Coresets

Scale-invariant Optimal Sampling for Rare-events Data and Sparse Models

Universal Rates of Empirical Risk Minimization

PAC-Bayes-Chernoff bounds for unbounded losses

Learning the Infinitesimal Generator of Stochastic Diffusion Processes

Global Rewards in Restless Multi-Armed Bandits

On $f$-Divergence Principled Domain Adaptation: An Improved Framework

A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness

Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process

Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound

How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression

On the Sparsity of the Strong Lottery Ticket Hypothesis

Compositional PAC-Bayes: Generalization of GNNs with persistence and beyond

One-Layer Transformer Provably Learns One-Nearest Neighbor In Context

High-dimensional (Group) Adversarial Training in Linear Regression

Nearly Minimax Optimal Regret for Multinomial Logistic Bandit

A Theory of Optimistically Universal Online Learnability for General Concept Classes

Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling

Learning to Price Homogeneous Data

A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays

Provably Efficient Interactive-Grounded Learning with Personalized Reward

GACL: Exemplar-Free Generalized Analytic Continual Learning

Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting

Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets

Contextual Active Model Selection

A Continuous-time Stochastic Gradient Descent Method for Continuous Data

S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training

GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent

Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition

Low-Rank Optimal Transport through Factor Relaxation with Latent Coupling

Pretrained Optimization Model for Zero-Shot Black Box Optimization

Geometry-aware training of factorized layers in tensor Tucker format

Learning Generalized Linear Programming Value Functions

Stochastic Newton Proximal Extragradient Method

Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization

LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning

SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning

Emergence of heavy tails in homogenized stochastic gradient descent

The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information

TorchOpt: An Efficient Library for Differentiable Optimization

Fully First-Order Methods for Linearly Constrained Bilevel Optimization

Non-asymptotic Global Convergence Analysis of BFGS with the Armijo-Wolfe Line Search

ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models

Slack-Free Spiking Neural Network Formulation for Hypergraph Minimum Vertex Cover

Practical $0.385$-Approximation for Submodular Maximization Subject to a Cardinality Constraint

Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences

Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks

On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization

Hierarchical Federated Learning with Multi-Timescale Gradient Correction

Auditing Privacy Mechanisms via Label Inference Attacks

Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning

Instance-Specific Asymmetric Sensitivity in Differential Privacy

Drago: Primal-Dual Coupled Variance Reduction for Faster Distributionally Robust Optimization

Lookback Prophet Inequalitites

Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions

Non-geodesically-convex optimization in the Wasserstein space

DistrictNet: Decision-aware learning for geographical districting

Performative Control for Linear Dynamical Systems

HyperPrism: An Adaptive Non-linear Aggregation Framework for Distributed Machine Learning over Non-IID Data and Time-varying Communication Links

Communication Efficient Distributed Training with Distributed Lion

Weight for Robustness: A Comprehensive Approach towards Optimal Fault-Tolerant Asynchronous ML

The Limits of Differential Privacy in Online Learning

Human-Readable Fingerprint for Large Language Models

Differentially Private Reinforcement Learning with Self-Play

Differentially Private Graph Diffusion with Applications in Personalized PageRanks

Faster Algorithms for User-Level Private Stochastic Convex Optimization

Dimension-free Private Mean Estimation for Anisotropic Distributions

OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning

Learning Versatile Skills with Curriculum Masking

Zero-Shot Reinforcement Learning from Low Quality Data

Simplifying Latent Dynamics with Softly State-Invariant World Models

AlphaMath Almost Zero: Process Supervision Without Process

Adversarial Environment Design via Regret-Guided Diffusion Models

Solving Minimum-Cost Reach Avoid using Reinforcement Learning

Solving Zero-Sum Markov Games with Continous State via Spectral Dynamic Embedding

Multi-Agent Imitation Learning: Value is Easy, Regret is Hard

Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning

Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance

Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training

Feint Behaviors and Strategies: Formalization, Implementation and Evaluation

The Dormant Neuron Phenomenon in Multi-Agent Reinforcement Learning Value Factorization

Aligning Individual and Collective Objectives in Multi-Agent Cooperation

AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making

Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs

Multimodal foundation world models for generalist embodied agents

What type of inference is planning?

Goal Reduction with Loop-Removal Accelerates RL and Models Human Brain Activity in Goal-Directed Learning

Identifying Latent State-Transition Processes for Individualized Reinforcement Learning

Seek Commonality but Preserve Differences: Dissected Dynamics Modeling for Multi-modal Visual RL

Variational Delayed Policy Optimization

On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and Games

Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation

REBEL: Reinforcement Learning via Regressing Relative Rewards

Nonparametric Regression for 3D Point Cloud Learning

Conformal Classification with Equalized Coverage for Adaptively Selected Groups

Verifiably Robust Conformal Prediction

Carrot and Stick: Eliciting Comparison Data and Beyond

Learning the Expected Core of Strictly Convex Stochastic Cooperative Games

Bayesian Strategic Classification

Swap Regret, Symmetry, and Nash Convergence in Games

Computational Aspects of Bayesian Persuasion under Approximate Best Response

LaSCal: Label-Shift Calibration without target labels

LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization

DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices

Generalized Tensor Decomposition for Understanding Multi-Output Regression under Combinatorial Shifts

Using Surrogates in Covariate-adjusted Response-adaptive Randomization Experiments with Delayed Outcomes

Attention boosted Individualized Regression

Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality

Symmetries in Overparametrized Neural Networks: A Mean Field View

Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm

Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation

Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff

Truncated Variance Reduced Value Iteration

Preference-based Pure Exploration

Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox

Online Control in Population Dynamics

Hybrid Reinforcement Learning Breaks Sample Size Barriers In Linear MDPs

Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning

DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception

There is No Silver Bullet: Benchmarking Methods in Predictive Combinatorial Optimization

STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases

A Novel Benchmark for Decision-Making in Uncertain and Competitive Games

NeuralPlane: An Efficiently Parallelizable Platform for Fixed-wing Aircraft Control with Reinforcement Learning

CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making

MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions

Transformer Efficiently Learns Low-dimensional Target Functions In-context

Axioms for AI Alignment from Human Feedback

Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers

Variance estimation for compound decisions

ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons

CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs

$E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset

Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games

When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL

Can LLMs Learn by Teaching? A Preliminary Study

Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling

BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models

A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embedding

ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses

FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling

TOPA: Extend Large Language Models for Video Understanding via Text-Only Pre-Alignment

Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation

OTTER: Effortless Label Distribution Adaptation of Zero-shot Models

Decomposable Transformer Point Processes

Enhancing LLM Reasoning via Vision-Augmented Prompting

From Text to Trajectory: Exploring Unified Complex Constraint Representation and Decomposition in Safe Reinforcement Learning

Injecting Undetectable Backdoors in Deep Learning and Language Models

SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation

FRHOzen: Loss-Based Data Selection for Targeted Language Model Pre-training

On the Parameter Identifiability of Partially Observed Linear Causal Models

Out-Of-Distribution Detection with Diversification (Provably)

When and How Does Synthetic Data Improve Reasoning Capabilities of Language Models?

MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution

Ensemble sampling for linear bandits: small ensembles suffice

What can Foundation Models’ Embeddings do?

Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement

Connectivity-Driven Pseudo-Labeling Makes Stronger Cross-Domain Segmenters

PageRank Bandits for Link Prediction

Energy-efficient Reinforcement Learning by Discovering Neural Pathways

ALPINE: Unveiling The Planning Capability of Autoregressive Learning in Language Models

Gliding over the Pareto Front with Uniform Designs

Gradient Rewiring for Editable Graph Neural Network Training

Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling

DeTrack: In-model Latent Denoising Learning for Visual Object Tracking

Toward a Theory of Tokenization in LLMs

DFBA: Data Free Backdoor Attacks

Shuffling Gradient-Based Methods for Nonconvex-Concave Minimax Optimization

QUEST: Quadruple Multimodal Contrastive Learning with Constraints and Self-Penalization

Parameter Competition Balancing for Model Merging

Acceleration Exists! Optimization Problems When Oracle Can Only Compare Objective Function Values

A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings

On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity

KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension

MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes

Unlock the Intermittent Control Ability of Model Free Reinforcement Learning

Conservative Fine-Tuning of Diffusion Models from Offline Data

Neural Gaffer: Relighting Any Object via Diffusion

Cooperative Hardware-Prompt Learning for Snapshot Compressive Imaging

(ends 7:30 PM)

Poster Session 6 East [4:30-7:30]

Posters 4:30-7:30

Textual Training for the Hassle-Free Removal of Unwanted Visual Data

Idiographic Personality Gaussian Process for Psychological Assessment

A versatile informative diffusion model for single-cell ATAC-seq data generation and analysis

PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation

PowerPM: Foundation Model for Power Systems

PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation

AutoSurvey: Large Language Models Can Automatically Write Surveys

MDAgents: An Adaptive Collaboration of LLMs for Medical Decision Making

Implicit Precursor Extraction with Expert Retriever for Inorganic Retrosynthesis

Scalable and Effective Arithmetic Tree Generation for RL-Driven Adder and Multiplier Designs

$\nabla^2$DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials

Proving Olympiad Algebraic Inequalities without Human Demonstrations

Never Miss A Beat: An Efficient Recipe for Context Window Extension of Large Language Models with Consistent “Middle” Enhancement

Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models

Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records

DMNet: Self-comparison Driven Model for Subject-independent Seizure Detection

NanoBaseLib: A Multi-Task Benchmark Dataset for Nanopore Sequencing

A SARS-CoV-2 Interaction Dataset and VHH Sequence Corpus for Antibody Language Models

Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA

Transferable Boltzmann Generators

Revisiting K-mer Profile for Effective and Scalable Genome Representation Learning

Mixture of neural fields for heterogeneous reconstruction in cryo-EM

Protein-Nucleic Acid Complex Modeling with Frame Averaging Transformer

CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy

EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding

QUEEN: QUantized Efficient ENcoding for Streaming Free-viewpoint Videos

Human 3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models

VFIMamba: Video Frame Interpolation with State Space Models

ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Driving

On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection

Improving the Learning Capability of Small-size Image Restoration Network by Deep Fourier Shifting Operator over Resource-limited Scene

4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization

A General Protocol to Probe Large Vision Models for 3D Physical Understanding

Voxel Proposal Network via Multi-Frame Knowledge Distillation for Semantic Scene Completion

Human-level shape inferences: A benchmark for evaluating the 3D understanding of vision models

Contrastive losses as generalized models of global epistasis

Segment Any Change

A Siamese Transformer with Hierarchical Refinement for Lane Detection

Vision Foundation Model Enables Generalizable Object Pose Estimation

DoGaussian: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus

DiffuBox: Refining 3D Object Detection with Point Diffusion

Beyond Accuracy: Tracking more like Human via Visual Search

Breaking Semantic Artifacts for Generalized AI-generated Image Detection

RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-Identification

UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections

TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scene

Historical Test-time Prompt Tuning for Vision Foundation Models

FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Differential Aggregation

Future Motion Estimation via Event Sequence Diffusion

Referencing Where to Focus: Improving Visual Grounding with Referential Query

Masked Pre-training Enables Universal Zero-shot Denoiser

MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction

ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction

Pedestrian-Centric 3D Pre-collision Pose and Shape Estimation from Dashcam Perspective

DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos

Generalizable Person Re-identification via Balancing Alignment and Uniformity

NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction

Don't Just String Tokens, Stack Them! Improving Multimodal Transformers with Layer Stack

Adaptive Important Region Selection with Reinforced Hierarchical Search for Dense Object Detection

Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement

Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set

Towards Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling

TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration

AlterMOMA: Fusion Redundancy Pruning for Camera-LiDAR Fusion Models with Alternative Modality Masking

GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields

Dynamic 3D Gaussian Fields for Urban Areas

$SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation

Towards Flexible 3D Perception: Object-Centric Occupancy Completion Augments 3D Object Detection in Long Sequence

Overcoming Common Flaws in the Evaluation of Selective Classification Systems

Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery

Hypergraph-Based Fuzzy Assembled Representation for Open-Set 3D Object Retrieval

Scala: Scalable Representation Learning for Vision Transformer

UltraPixel: Advancing Ultra High-Resolution Image Synthesis to New Peaks

Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis

FouRA: Fourier Low-Rank Adaptation

Return of Unconditional Generation: A Self-supervised Representation Generation Method

ParallelEdits: Efficient Multi-Aspect Text-Driven Image Editing with Attention Grouping

FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference Images

Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)

Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts

Novel Object Synthesis via Adaptive Text-Image Harmony

Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function

AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion Models

OneActor: Consistent Subject Generation via Cluster-Conditioned Guidance

SA3DIP: Segment Any 3D Instance with Potential 3D Priors

MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning

Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation

Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation

Zero-Shot Image Segmentation via Recursive Normalized Cut on Diffusion Features

HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting

Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis

Multi-scale Consistency for Robust 3D Registration via Hierarchical Sinkhorn Tree

A Cat Is A Cat (Not A Dog!): Unraveling Information Mix-ups in Text-to-Image Encoders through Causal Analysis and Embedding Optimization

TPC: Test-time Procrustes Calibration for Diffusion-based Human Image Animation

LVD-2M: A Long-take Video Dataset with Temporally Dense Captions

MTGS: A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze Prediction

Understanding Bias in Visual Datasets

SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models

MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs

Predicting Label Distribution from Ternary Labels

Visual Data Diagnosis and Debiasing with Concept Graphs

SAND: Smooth imputation of sparse and noisy functional data with Transformer networks

MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer

DINTR: Tracking via Diffusion-based Interpolation

CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos

ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation

Slot State Space Models

UQE: A Query Engine for Unstructured Databases

Bayesian-Guided Label Mapping for Visual Reprogramming

You Only Cache Once: Decoder-Decoder Architectures for Language Models

Why Go Full? Elevating Federated Learning Through Partial Network Updates

Visual Prompt Tuning in Null Space for Continual Learning

Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate

Towards Understanding Evolving Patterns in Sequential Data

MoEUT: Mixture-of-Experts Universal Transformers

DARNet: Dual Attention Refinement Network with Spatiotemporal Construction for Auditory Attention Detection

RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space

A Walsh Hadamard Derived Linear Vector Symbolic Architecture

TinyLUT: Tiny Look-Up Table for Efficient Image Restoration at the Edge

LinNet: Linear Network for Efficient Point Cloud Representation Learning

Nuclear Norm Regularization for Deep Learning

When is an Embedding Model More Promising than Another?

Random Representations Outperform Online Continually Learned Representations

Navigating Extremes: Dynamic Sparsity in Large Output Spaces

Learning Group Actions on Latent Representations

Position Coupling: Leveraging Task Structure for Improved Length Generalization of Transformers

Towards Understanding Extrapolation: a Causal Lens

CosAE: Learnable Fourier Series for Image Restoration

Parallelizing Linear Transformers with the Delta Rule over Sequence Length

FactorizePhys: Effective Spatial-Temporal Attention in Remote Photo-plethysmography through Factorization of Voxel Embeddings

NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention

Road Network Representation Learning with the Third Law of Geography

$C^2M^3$: Cycle-Consistent Multi-Model Merging

Non-Euclidean Mixture Model for Social Network Embedding

The Mamba in the Llama: Distilling and Accelerating Hybrid Models

WeiPer: OOD Detection using Weight Perturbations of Class Projections

Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation

Towards Combating Frequency Simplicity-biased Learning for Domain Generalization

TAIA: Large Language Models are Out-of-Distribution Data Learners

MALT Powers Up Adversarial Attacks

Many-shot Jailbreaking

Understanding the Role of Equivariance in Self-supervised Learning

Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels

Are Multiple Instance Learning Algorithms Learnable for Instances?

SGD vs GD: Rank Deficiency in Linear Networks

Scalable Optimization in the Modular Norm

Bayes-optimal learning of an extensive-width neural network from quadratically many samples

Scaling Laws in Linear Regression: Compute, Parameters, and Data

Predicting Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data

Explicit Eigenvalue Reguralization Improves Sharpness-Aware Minimization

A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression

A simplicity bias in the learning dynamics of transformers

Improved Particle Approximation Error for Mean Field Neural Networks

Relating Hopfield Networks to Episodic Control

Neural collapse vs. low-rank bias: Is deep neural collapse really optimal?

Theoretical Characterisation of the Gauss Newton Conditioning in Neural Networks

Generalizablity of Memorization Neural Network

The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks

G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models

Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion

Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks

HORSE: Hierarchical Representation for Large-Scale Neural Subset Selection

Preference Alignment with Flow Matching

Activation Map Compression through Tensor Decomposition for Deep Learning

FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations

Amortized Planning with Large-Scale Transformers: A Case Study on Chess

Why Do We Need Weight Decay in Modern Deep Learning?

Compositional 3D-aware Video Generation with LLM Director

MInference: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

Fine-grained Control of Generative Data Augmentation in IoT Sensing

MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map

Hamiltonian Score Matching and Generative Flows

MVGamba: Unify 3D Content Generation as State Space Sequence Modeling

Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models

Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer

Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching

FlowLLM: Flow Matching for Material Generation with Learned Base Distributions

Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration

Watermarking Makes Language Models Radioactive

Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based Discrimination

Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective

Fully Transparent Self-Alignment for Code Generation

BitsFusion: 1.99 bits Weight Quantization of Diffusion Model

Schrodinger Bridge Flow for Unpaired Data Translation

Rethinking Score Distillation as a Bridge Between Image Distributions

Score-based generative models are provably robust: an uncertainty quantification perspective

Provable Posterior Sampling with Denoising Oracles Through Tilted Transport

ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restoration

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques

GrounDiT: Grounding Diffusion Transformers via Noisy Image Patch Transplantation

SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout

Improved off-policy training of diffusion samplers

SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data

DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization

BiDM: Pushing the Limit of Quantization for Diffusion Models

Diffusion Models With Learned Adaptive Noise

ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models

COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation

Lumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiT

ProgressEditor: Simple Progression is All You Need for High-Quality 3D Scene Editing

Image Copy Detection for Diffusion Models

Graph Diffusion Transformer for Multi-Conditional Molecular Generation

StepbaQ: Stepping backward as Correction for Quantized Diffusion Models

DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning

Many-Shot In-Context Learning

Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts

Estimating the Hallucination Rate of Generative AI

Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models

Grammar-Aligned Decoding

Human-AI Alignment in Chess with Skill-Aware Attention

LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single Image

One-Shot Safety Alignment for Large Language Models via Optimal Dualization

Trace is the New AutoDiff: Unlocking Efficient Optimization of Computational Workflows

Mars: Situated Inductive Reasoning in an Open-World Environment

Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset

A Topology-aware Graph Coarsening Framework for Continual Graph Learning

FUG: Feature-Universal Graph Contrastive Pre-training for Graphs with Diverse Node Features

Towards Principled Graph Transformers

Training GNNs in Balance by Dynamic Rescaling

TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs

JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models

Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision

Enhancing Large Language Models via Additional Pre-Training on Principled Synthetic Logic Corpus

Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models

EAI: Emotional Decision-Making of LLMs in Strategic Games and Ethical Dilemmas

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data

Chain-of-Thought Reasoning Without Prompting

Similarity-Navigated Conformal Prediction for Graph Neural Networks

GOUDA: A General Graph Contrastive Learning Framework via Augmentation Unification

UGC: Universal Graph Coarsening

What Matters in Graph Class Incremental Learning? An Information Preservation Perspective

Graph Edit Distance with General Costs Using Neural Set Divergence

A Taxonomy of Challenges to Curating Fair Datasets

MambaTalk: Co-Speech Gesture Generation with Selective State Space Models

Harmonizing Stochasticity and Determinism: Scene-responsive Diverse Human Motion Prediction

Shared Autonomy with IDA: Interventional Diffusion Assistance

Towards Explainable Evaluation Metrics for Machine Translation

Benchmarking the Attribution Quality of Vision Models

Truth is Universal: Robust Detection of Lies in LLMs

Measuring Goal-Directedness

Stochastic Concept Bottleneck Models

Towards the Dynamics of a DNN Learning Symbolic Interactions

Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization

Zipper: Addressing Degeneracy in Algorithm-Agnostic Inference

FastSurvival: Hidden Computational Blessings in Training Cox Proportional Hazards Models

Interpretable Mesomorphic Networks for Tabular Data

How Do Transformers Fill in the Blanks? A Case Study on Matrix Completion

Improving Decision Sparsity

Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects

Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning

Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)

Optimal ablation for model internals

Rule Based Rewards for Fine-Grained Safety Behavior in LLMs

A Full-duplex Speech Dialogue Scheme Based On Large Language Model

OneBit: Towards Extremely Low-bit Large Language Models

DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning

Fractal Patterns May Illuminate the Success of Next-Token Prediction

Achieving Efficient Alignment through Learned Correction

Multi-LLM Debate: Framework, Principals, and Interventions

Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing

xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token

MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models

Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models

Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation

A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative Missingness

Persistent Homology for High-dimensional Data Based on Spectral Methods

Approximating the Top Eigenvector in Random Order Streams

Aligner Encoders: Self-Attention Transformers Can Be Self-Transducers

TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation

SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words

Co-occurrence is not Factual Association in Language Models

I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token

Counterfactual PPO Enhanced Shared Reflector for LLM-based Multi-agent Collaboration

Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting

Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation

Dissect Black Box: Interpreting for Rule-Based Explanations in Unsupervised Anomaly Detection

A Kernel Perspective on Distillation-based Collaborative Learning

Statistical and Geometrical properties of the Kernel Kullback-Leibler divergence

Metric Space Magnitude for Evaluating the Diversity of Latent Representations

Identifiable Shared Component Analysis of Unpaired Multimodal Mixtures

Large Language Models Must Be Taught to Know What They Don’t Know

Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective

One-shot Federated Learning via Synthetic Distiller-Distillate Communication

Understanding the Transferability of Representations via Task-Relatedness

QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation

Scaling laws for learning with real and surrogate data

Unsupervised Anomaly Detection in The Presence of Missing Values

CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts

Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models

SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors

Extending Multi-modal Contrastive Representations

Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text Prompts

What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction

Needle In A Multimodal Haystack

Revisiting Few-Shot Object Detection with Vision-Language Models

Enhancing Semi-Supervised Learning via Representative and Diverse Sample Selection

Geometric Analysis of Nonlinear Manifold Clustering

Capturing the denoising effect of PCA via compression ratio

Localizing Memorization in SSL Vision Encoders

Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE

Homology Consistency Constrained Efficient Tuning for Vision-Language Models

Learning Spatially-Aware Language and Audio Embeddings

AV-Cloud: Spatial Audio Rendering Through Audio-Visual Cloud Splatting

Brain Treebank: Large-scale intracranial recordings from naturalistic language stimuli

ActSort: An active-learning accelerated cell sorting algorithm for large-scale calcium imaging datasets

Disentangling the Roles of Distinct Cell Classes with Cell-Type Dynamical Systems

Spiking Neural Network as Adaptive Event Stream Slicer

Pretraining with Random Noise for Fast and Robust Learning without Weight Transport

EEG2Video: Towards Decoding Dynamic Visual Perception from EEG Signals

Not so griddy: Internal representations of RNNs path integrating more than one agent

Population Predictive Coding: a structured Bayesian inference algorithm

Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations

What is my quantum computer good for? Quantum capability learning with physics-aware neural networks

Advection Augmented Convolutional Neural Networks

Latent Neural Operator for Solving Forward and Inverse PDE Problems

RandNet-Parareal: a time-parallel PDE solver using Random Neural Networks

Decoupling Semantic Similarity from Spatial Alignment for Neural Networks.

NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping

Geodesic Optimization for Predictive Shift Adaptation on EEG data

Shaping the distribution of neural responses with interneurons in a recurrent circuit model

Discovering plasticity rules that organize and maintain neural circuits

Improving optimal control and estimation methods adapted to the noise characteristics of the sensorimotor system

Time Makes Space: Emergence of Place Fields in Networks Encoding Temporally Continuous Sensory Experiences

Neural Fluidic System Design and Control with Differentiable Simulation

Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal Consistency

Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Loss

Physics-Informed Regularization for Domain-Agnostic Dynamical System Modeling

Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs

Learning 3D Garment Animation from Trajectories of A Piece of Cloth

Generalization of Hamiltonian algorithms

On Divergence Measures for Training GFlowNets

A Fast Convoluted Story: Scaling Probabilistic Inference for Integer Arithmetics

Learning to be Smooth: An End-to-End Differentiable Particle Smoother

A Generative Model of Symmetry Transformations

Deep Learning for Computing Convergence Rates of Markov Chains

Functional Gradient Flows for Constrained Sampling

A Compositional Atlas for Algebraic Circuits

Scaling Continuous Latent Variable Models as Probabilistic Integral Circuits

A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers

Scalable Bayesian Optimization via Focalized Sparse Gaussian Processes

Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees

Quasi-Bayes meets Vines

General bounds on the quality of Bayesian coresets

Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information

Nonparametric Copula Models for Multivariate, Mixed, and Missing Data

On the Expressive Power of Tree-Structured Probabilistic Circuits

An Information Theoretic Perspective on Conformal Prediction

EigenVI: score-based variational inference with orthogonal function expansions

Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies

Motion Forecasting in Continuous Driving

SCaR: Refining Skill Chaining for Long-Horizon Robotic Manipulation via Dual Regularization

VidMan: Exploiting Intrinsic Dynamics from Video Diffusion Model for Effective Robot Manipulation

DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States

FactorSim: Generative Simulation via Factorized Representation

CulturePark: Boosting Cross-cultural Understanding in Large Language Models

An engine not a camera: Measuring performative power of online search

The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection Benchmark

Time-MMD: A New Multi-Domain Multimodal Dataset for Time Series Analysis

Are Language Models Actually Useful for Time Series Forecasting?

Distributionally Robust Performative Prediction

Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters

Optimal Classification under Performative Distribution Shift

Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection

A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks

CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence

T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models

FilterNet: Harnessing Frequency Filters for Time Series Forecasting

Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective

Structured Matrix Basis for Multivariate Time Series Forecasting with Interpretable Dynamics

CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns

Federated Transformer: Scalable Vertical Federated Learning on Practical Fuzzily Linked Data

Improving Alignment and Robustness with Short Circuiting

Perplexity-aware Correction for Robust Alignment with Noisy Preferences

Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning

Non-Asymptotic Uncertainty Quantification in High-Dimensional Learning

Diffusion Unlearning Optimization for Robust and Safe Text-to-Image Models

AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning

Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature

Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments

Soft-Label Integration for Robust Toxicity Classification

Robust Conformal Prediction Using Privileged Information

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

CALVIN: Improved Contextual Video Captioning via Instruction Tuning

LCGen: Mining in Low-Certainty Generation for View-consistent Text-to-3D

A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise

DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning

Generative Retrieval Meets Multi-Graded Relevance

Reliable Learning of Halfspaces under Gaussian Marginals

JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images

MedJourney: Benchmark and Evaluation of Large Language Models over Patient Clinical Journey

MOTI$\mathcal{V}\mathcal{E}$: A Drug-Target Interaction Graph For Inductive Link Prediction

Scalable Early Childhood Reading Performance Prediction

Boosting the Transferability of Adversarial Attack on Vision Transformer with Adaptive Token Tuning

FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge

GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes

Real-time Stereo-based 3D Object Detection for Streaming Perception

Unravelling in Collaborative Learning

Multi-Object Hallucination in Vision Language Models

LG-CAV: Train Any Concept Activation Vector with Language Guidance

Smoothed Online Classification can be Harder than Batch Classification

Reinforcement Learning with Euclidean Data Augmentation for State-Based Continuous Control

Towards Stable Representations for Protein Interface Prediction

Iteratively Refined Behavior Regularization for Offline Reinforcement Learning

Gradient-variation Online Learning under Generalized Smoothness

Robust Fine-tuning of Zero-shot Models via Variance Reduction

Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control

MAmmoTH2: Scaling Instructions from the Web

Trading off Consistency and Dimensionality of Convex Surrogates for Multiclass Classification

An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness

Attention Temperature Matters in ViT-Based Cross-Domain Few-Shot Learning

Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner

EGODE: An Event-attended Graph ODE Framework for Modeling Rigid Dynamics

AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario

UNIT: Unifying Image and Text Recognition in One Vision Encoder

(ends 7:30 PM)

7 p.m.

Town Hall:

Town Hall / Business Meeting

(ends 8:00 PM)

8 p.m.

Closing Reception:

Closing Reception

(ends 9:30 PM)

SAT 14 DEC

7:30 a.m.

Registration (East)

(ends 12:00 PM)

Registration (West)

(ends 4:00 PM)

Break:

Coffee Break

(ends 8:00 AM)

8:15 a.m.

Workshop:

UniReps: Unifying Representations in Neural Models

(ends 5:30 PM)

Workshop:

5th Workshop on Self-Supervised Learning: Theory and Practice

(ends 5:30 PM)

Workshop:

Attributing Model Behavior at Scale (ATTRIB)

(ends 5:30 PM)

Workshop:

Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation

(ends 5:30 PM)

Workshop:

3rd Workshop on New Frontiers in Adversarial Machine Learning (AdvML-Frontiers)

(ends 5:30 PM)

Workshop:

Statistical Frontiers in LLMs and Foundation Models

(ends 5:30 PM)

Workshop:

Workshop on Behavioral Machine Learning

(ends 5:30 PM)

Workshop:

Causality and Large Models

(ends 5:30 PM)

Workshop:

AIM-FM: Advancements In Medical Foundation Models: Explainability, Robustness, Security, and Beyond

(ends 5:30 PM)

Workshop:

Workshop on Scalable Continual Learning for Lifelong Foundation Models

(ends 5:30 PM)

Workshop:

Algorithmic Fairness through the lens of Metrics and Evaluation

(ends 5:30 PM)

Workshop:

MATH-AI: The 4th Workshop on Mathematical Reasoning and AI

(ends 5:30 PM)

Workshop:

NeuroAI: Fusing Neuroscience and AI for Intelligent Solutions

(ends 5:30 PM)

Workshop:

Language Gamification

(ends 5:30 PM)

Workshop:

GenAI for Health: Potential, Trust and Policy Compliance

(ends 5:30 PM)

Workshop:

Symmetry and Geometry in Neural Representations

(ends 5:30 PM)

Workshop:

Mathematics of Modern Machine Learning (M3L)

(ends 5:30 PM)

Workshop:

Generative AI and Creativity: A dialogue between machine learning researchers and creative professionals

(ends 5:30 PM)

Workshop:

The Fourth Workshop on Efficient Natural Language and Speech Processing (ENLSP-IV): Highlighting New Architectures for Future Foundation Models

(ends 5:30 PM)

Workshop:

Workshop on Video-Language Models

(ends 5:30 PM)

Workshop:

Pluralistic Alignment Workshop

(ends 5:30 PM)

Workshop:

Table Representation Learning Workshop (TRL)

(ends 5:30 PM)

Workshop:

Workshop on Responsibly Building Next Generation of Multimodal Foundation Models

(ends 5:30 PM)

Workshop:

Fine-Tuning in Modern Machine Learning: Principles and Scalability

(ends 5:30 PM)

Workshop:

Socially Responsible Language Modelling Research (SoLaR)

(ends 5:30 PM)

Workshop:

Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning

(ends 5:30 PM)

Workshop:

Bayesian Decision-making and Uncertainty: from probabilistic and spatiotemporal modeling to sequential experiment design

(ends 5:30 PM)

Workshop:

AI4Mat-2024: NeurIPS 2024 Workshop on AI for Accelerated Materials Design

(ends 5:30 PM)

9 a.m.

Competition:

HAC: The Hacker-Cup AI Competition

(ends 12:00 PM)

Competition:

FAIR Universe – the challenge of handling uncertainties in fundamental science

(ends 12:00 PM)

Competition:

MyoChallenge 2024: Physiological Dexterity and Agility in Bionic Humans

(ends 12:00 PM)

Competition:

Ariel Data Challenge 2024: Extracting exoplanetary signals from the Ariel Space Telescope

(ends 12:00 PM)

Break:

Coffee Break

(ends 10:00 AM)

noon

Break:

Lunch Break

(ends 1:30 PM)

1:30 p.m.

Competition:

Workshop for URGENT 2024 Challenge

(ends 4:30 PM)

Competition:

Auto-Bidding in Large-Scale Auctions: Learning Decision-Making in Uncertain and Competitive Games

(ends 4:30 PM)

Competition:

Lux AI Season 3: Multi-Agent Meta Learning at Scale

(ends 4:30 PM)

Competition:

NeurIPS 2024 ML4CFD Competition: Harnessing Machine Learning for Computational Fluid Dynamics in Airfoil Design

(ends 4:30 PM)

3 p.m.

Break:

Coffee Break

(ends 3:30 PM)

SUN 15 DEC

7:30 a.m.

Registration (West)

(ends 12:00 PM)

Break:

Coffee Break

(ends 8:00 AM)

8:15 a.m.

Workshop:

Machine Learning for Systems

(ends 5:30 PM)

Workshop:

ML with New Compute Paradigms

(ends 5:30 PM)

Workshop:

Machine Learning in Structural Biology

(ends 5:30 PM)

Workshop:

Safe Generative AI

(ends 5:30 PM)

Workshop:

Time Series in the Age of Large Models

(ends 5:30 PM)

Workshop:

Multimodal Algorithmic Reasoning Workshop

(ends 5:30 PM)

Workshop:

Foundation Models for Science: Progress, Opportunities, and Challenges

(ends 5:30 PM)

Workshop:

Tackling Climate Change with Machine Learning

(ends 5:30 PM)

Workshop:

NeurIPS 2024 Workshop: Machine Learning and the Physical Sciences

(ends 5:30 PM)

Workshop:

D3S3: Data-driven and Differentiable Simulations, Surrogates, and Solvers

(ends 5:30 PM)

Workshop:

Foundation Model Interventions

(ends 5:30 PM)

Workshop:

Intrinsically Motivated Open-ended Learning (IMOL)

(ends 5:30 PM)

Workshop:

AI for New Drug Modalities

(ends 5:30 PM)

Workshop:

Workshop on Open-World Agents: Synnergizing Reasoning and Decision-Making in Open-World Environments (OWA-2024)

(ends 5:30 PM)

Workshop:

Optimization for ML Workshop

(ends 5:30 PM)

Workshop:

Interpretable AI: Past, Present and Future

(ends 5:30 PM)

Workshop:

Evaluating Evaluations: Examining Best Practices for Measuring Broader Impacts of Generative AI

(ends 5:30 PM)

Workshop:

Regulatable ML: Towards Bridging the Gaps between Machine Learning Research and Regulations

(ends 5:30 PM)

Workshop:

International Workshop on Federated Foundation Models in Conjunction with NeurIPS 2024 (FL@FM-NeurIPS'24)

(ends 5:30 PM)

Workshop:

Scientific Methods for Understanding Neural Networks: Discovering, Validating, and Falsifying Theories of Deep Learning with Experiments

(ends 5:30 PM)

Workshop:

The First Workshop on Large Foundation Models for Educational Assessment

(ends 5:30 PM)

Workshop:

Compositional Learning: Perspectives, Methods, and Paths Forward

(ends 5:30 PM)

Workshop:

NeurIPS'24 Workshop on Causal Representation Learning

(ends 5:30 PM)

Workshop:

Towards Safe & Trustworthy Agents

(ends 5:30 PM)

Workshop:

System-2 Reasoning at Scale

(ends 5:30 PM)

Workshop:

2nd Workshop on Touch Processing: From Data to Knowledge

(ends 5:30 PM)

Workshop:

Workshop on Machine Learning and Compression

(ends 5:30 PM)

Workshop:

Red Teaming GenAI: What Can We Learn from Adversaries?

(ends 5:30 PM)

9 a.m.

Competition:

The Concordia Contest: Advancing the Cooperative Intelligence of Language Agents

(ends 12:00 PM)

Competition:

LLM Merging: Building LLMs Efficiently through Merging

(ends 12:00 PM)

Competition:

Multi-task Challenges for Rain Movie Prediction on the Road to Hi-Res Foundation Models

(ends 12:00 PM)

Competition:

The NeurIPS 2024 LLM Privacy Challenge

(ends 12:00 PM)

Break:

Coffee Break

(ends 10:00 AM)

noon

Break:

Lunch Break

(ends 1:30 PM)

1:30 p.m.

Competition:

BELKA: The Big Encoded Library for Chemical Assessment

(ends 4:30 PM)

Competition:

Edge-LLMs: Edge-Device Large Language Model Competition

(ends 4:30 PM)

Competition:

Erasing the Invisible: A Stress-Test Challenge for Image Watermarks

(ends 4:30 PM)

Competition:

CLAS 2024: The Competition for LLM and Agent Safety

(ends 4:30 PM)

3 p.m.

Break:

Coffee Break

(ends 3:30 PM)