Skip to yearly menu bar
Skip to main content
Main Navigation
NeurIPS
Help/FAQ
Contact NeurIPS
Code of Ethics
Code of Conduct
Create Profile
Journal To Conference Track
Diversity & Inclusion
Proceedings
Future Meetings
Press
Exhibitor Information
Privacy Policy
Downloads
My Stuff
Login
Select Year: (2024)
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
2012
2011
2010
2009
2008
2007
2006
Past Conferences
Start Here
Schedule
Tutorials
Main Conference
Invited Talks
Orals
Spotlights
Papers
Paper Visualization
Competitions
Datasets & Benchmarks
Journal Track
Creative AI Track
Outstanding Paper Awards
Affinity Workshops
Community
Affinity Events
Bridging the Future
Socials
Careers
Workshops
Exhibitors
Help
FAQ
Helpdesk in RocketChat
Organizers
Browse
mini
compact
topic
detail
Showing papers for
.
×
×
title
author
topic
session
shuffle
by
serendipity
bookmarked first
visited first
not visited first
bookmarked but not visited
Enable Javascript in your browser to see the papers page.
IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
Is Programming by Example Solved by LLMs?
Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models
Back to the Continuous Attractor
SkipPredict: When to Invest in Predictions for Scheduling
A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
On the Expressive Power of Tree-Structured Probabilistic Circuits
Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation
Score-based 3D molecule generation with neural fields
Instance-Optimal Private Density Estimation in the Wasserstein Distance
Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
Intervention and Conditioning in Causal Bayesian Networks
SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead
A Structure-Aware Framework for Learning Device Placements on Computation Graphs
Model Fusion through Bayesian Optimization in Language Model Fine-Tuning
Online Estimation via Offline Estimation: An Information-Theoretic Framework
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
Scaling transformer neural networks for skillful and reliable medium-range weather forecasting
Toward Efficient Inference for Mixture of Experts
Learning Formal Mathematics From Intrinsic Motivation
PRODuctive bandits: Importance Weighting No More
Random Function Descent
Toward Approaches to Scalability in 3D Human Pose Estimation
Fully Distributed, Flexible Compositional Visual Representations via Soft Tensor Products
Private Attribute Inference from Images with Vision-Language Models
Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization
Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
Graph Neural Networks and Arithmetic Circuits
xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology
QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation
Constant Acceleration Flow
Contracting with a Learning Agent
Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy
Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
HEPrune: Fast Private Training of Deep Neural Networks With Encrypted Data Pruning
On the Reproducibility of: "Learning Perturbations to Explain Time Series Predictions"
AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields
Robust Sparse Regression with Non-Isotropic Designs
HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion
Agent Planning with World Knowledge Model
Latent Intrinsics Emerge from Training to Relight
Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information
Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks
QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation
Geometric Analysis of Nonlinear Manifold Clustering
Generating Highly Designable Proteins with Geometric Algebra Flow Matching
Conditional Synthesis of 3D Molecules with Time Correction Sampler
A General Protocol to Probe Large Vision Models for 3D Physical Understanding
Improving Deep Learning Optimization through Constrained Parameter Regularization
HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models
Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts
Equivariant Neural Diffusion for Molecule Generation
Transformers need glasses! Information over-squashing in language tasks
Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions
Learning on Large Graphs using Intersecting Communities
Graph Edit Distance with General Costs Using Neural Set Divergence
fMRI predictors based on language models of increasing complexity recover brain left lateralization
Private Online Learning via Lazy Algorithms
Autonomous Agents for Collaborative Task under Information Asymmetry
HHD-GP: Incorporating Helmholtz-Hodge Decomposition into Gaussian Processes for Learning Dynamical Systems
Estimating the Hallucination Rate of Generative AI
Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
DAGER: Exact Gradient Inversion for Large Language Models
A Theoretical Perspective for Speculative Decoding Algorithm
Generative Modeling of Molecular Dynamics Trajectories
Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
CoBo: Collaborative Learning via Bilevel Optimization
Controlling Continuous Relaxation for Combinatorial Optimization
Graph Coarsening with Message-Passing Guarantees
[Re] Reproducibility Study of “Explaining Temporal Graph Models Through an Explorer-Navigator Framework"
Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing
EffiBench: Benchmarking the Efficiency of Automatically Generated Code
Solving Inverse Problems via Diffusion Optimal Control
EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization
ProTransformer: Robustify Transformers via Plug-and-Play Paradigm
Wasserstein Gradient Boosting: A Framework for Distribution-Valued Supervised Learning
Proportional Fairness in Non-Centroid Clustering
Fairness in Social Influence Maximization via Optimal Transport
Attack-Aware Noise Calibration for Differential Privacy
Accelerating ERM for data-driven algorithm design using output-sensitive techniques
Limits of Transformer Language Models on Learning to Compose Algorithms
MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning
4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models
Nimbus: Secure and Efficient Two-Party Inference for Transformers
Combining Observational Data and Language for Species Range Estimation
Reciprocal Learning
No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models
Entity Alignment with Noisy Annotations from Large Language Models
SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types
Regret Minimization in Stackelberg Games with Side Information
Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure
MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset
On Causal Discovery in the Presence of Deterministic Relations
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Models
Towards Universal Mesh Movement Networks
Expected Probabilistic Hierarchies
Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate
Codec Avatar Studio: Paired Human Captures for Complete, Driveable, and Generalizable Avatars
Beyond Aesthetics: Cultural Competence in Text-to-Image Models
Studying How to Efficiently and Effectively Guide Models with Explanations - A Reproducibility Study
FEEL-SNN: Robust Spiking Neural Networks with Frequency Encoding and Evolutionary Leak Factor
RealMAN: A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization
Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs
DRIP: Unleashing Diffusion Priors for Joint Foreground and Alpha Prediction in Image Matting
OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
MaskFactory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation
Road Network Representation Learning with the Third Law of Geography
EyeGraph: Modularity-aware Spatio Temporal Graph Clustering for Continuous Event-based Eye Tracking
Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs
PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs
Generic Unsupervised Optimization for a Latent Variable Model With Exponential Family Observables
PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques
Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models
Beware of Road Markings: A New Adversarial Patch Attack to Monocular Depth Estimation
Critically Assessing the State of the Art in Neural Network Verification
How to Solve Contextual Goal-Oriented Problems with Offline Datasets?
Mind the Gap Between Prototypes and Images in Cross-domain Finetuning
Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers
Reproducibility Study of "Robust Fair Clustering: A Novel Fairness Attack and Defense Framework"
TinyTTA: Efficient Test-time Adaptation via Early-exit Ensembles on Edge Devices
DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection
ARC: A Generalist Graph Anomaly Detector with In-Context Learning
RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models
Understanding the Transferability of Representations via Task-Relatedness
Safe Time-Varying Optimization based on Gaussian Processes with Spatio-Temporal Kernel
MutaPLM: Protein Language Modeling for Mutation Explanation and Engineering
Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models
QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion
Reproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentations
Reproducibility study of “LICO: Explainable Models with Language-Image Consistency"
Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information
Reproducibility study of "Robust Fair Clustering: A Novel Fairness Attack and Defense Framework"
Reproducibility Study of "ITI-GEN: Inclusive Text-to-Image Generation"
Explaining RL Decisions with Trajectories': A Reproducibility Study
[Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models
[Re] GNNInterpreter: A probabilistic generative model-level explanation for Graph Neural Networks
Metrizing Weak Convergence with Maximum Mean Discrepancies
Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression
Label Alignment Regularization for Distribution Shift
An Analysis of Robustness of Non-Lipschitz Networks
Topological Hidden Markov Models
Pre-trained Gaussian Processes for Bayesian Optimization
Causal Bandits for Linear Structural Equation Models
Causal-learn: Causal Discovery in Python
Optimization-based Causal Estimation from Heterogeneous Environments
Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment
Nonparametric Regression for 3D Point Cloud Learning
Inference on the Change Point under a High Dimensional Covariance Shift
Dense Associative Memory Through the Lens of Random Features
Multi-Label Learning with Stronger Consistency Guarantees
Piecewise-Stationary Bandits with Knapsacks
Structural Inference of Dynamical Systems with Conjoined State Space Models
Inexact Augmented Lagrangian Methods for Conic Optimization: Quadratic Growth and Linear Convergence
SF-V: Single Forward Video Generation Model
Generative Retrieval Meets Multi-Graded Relevance
ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generation
Exploring Low-Dimensional Subspace in Diffusion Models for Controllable Image Editing
Deep Learning for Computing Convergence Rates of Markov Chains
FUSE: Fast Unified Simulation and Estimation for PDEs
Counterfactual Fairness by Combining Factual and Counterfactual Predictions
FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation
Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning
ResAD: A Simple Framework for Class Generalizable Anomaly Detection
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
Non-Euclidean Mixture Model for Social Network Embedding
GenRL: Multimodal-foundation world models for generalization in embodied agents
Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network
Flatten Anything: Unsupervised Neural Surface Parameterization
Learning Low-Rank Feature for Thorax Disease Classification
Long-range Meta-path Search on Large-scale Heterogeneous Graphs
On the Saturation Effects of Spectral Algorithms in Large Dimensions
LibAMM: Empirical Insights into Approximate Computing for Accelerating Matrix Multiplication
Hierarchical Selective Classification
SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding
Fixed points of nonnegative neural networks
On $f$-Divergence Principled Domain Adaptation: An Improved Framework
3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors
Implicit Optimization Bias of Next-token Prediction in Linear Models
Co-occurrence is not Factual Association in Language Models
TorchOpt: An Efficient Library for Differentiable Optimization
Efficient Convex Algorithms for Universal Kernel Learning
Chain-of-Thought Unfaithfulness as Disguised Accuracy
Reproducibility study of FairAC
Unsupervised Anomaly Detection Algorithms on Real-world Data: How Many Do We Need?
BenchMARL: Benchmarking Multi-Agent Reinforcement Learning
Text to Blind Motion
Supra-Laplacian Encoding for Transformer on Dynamic Graphs
Combining Statistical Depth and Fermat Distance for Uncertainty Quantification
MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions
Diffusion-Inspired Truncated Sampler for Text-Video Retrieval
TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks
Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs
Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation
Curriculum Fine-tuning of Vision Foundation Model for Medical Image Classification Under Label Noise
SustainDC: Benchmarking for Sustainable Data Center Control
MeshXL: Neural Coordinate Field for Generative 3D Foundation Models
No-Regret M${}^{\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and NP-Hardness of Adversarial Full-Information Setting
3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
Unified Lexical Representation for Interpretable Visual-Language Alignment
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
Mercury: A Code Efficiency Benchmark for Code Large Language Models
DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
ANT: Adaptive Noise Schedule for Time Series Diffusion Models
Principled Bayesian Optimization in Collaboration with Human Experts
DataStealing: Steal Data from Diffusion Models in Federated Learning with Multiple Trojans
STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes
VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding
A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data
Transferable Adversarial Attacks on SAM and Its Downstream Models
PERIA: Perceive, Reason, Imagine, Act via Holistic Language and Vision Planning for Manipulation
HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid
Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow
AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
Intrinsic Self-Supervision for Data Quality Audits
Subsurface Scattering for Gaussian Splatting
DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA
DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models
RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions
WildGaussians: 3D Gaussian Splatting In the Wild
Dynamic 3D Gaussian Fields for Urban Areas
PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization
Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery
FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification
Interpretable Mesomorphic Networks for Tabular Data
Classification Done Right for Vision-Language Pre-Training
SplitNeRF: Split Sum Approximation Neural Field for Joint Geometry, Illumination, and Material Estimation
Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs
Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving
Empowering and Assessing the Utility of Large Language Models in Crop Science
LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation
Sparse maximal update parameterization: A holistic approach to sparse training dynamics
HEST-1k: A Dataset For Spatial Transcriptomics and Histology Image Analysis
Performative Control for Linear Dynamical Systems
Elucidating the Design Space of Dataset Condensation
ChatCam: Empowering Camera Control through Conversational AI
VideoGUI: A Benchmark for GUI Automation from Instructional Videos
Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting
How to Use Diffusion Priors under Sparse Views?
BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices
MAN TruckScenes: A multimodal dataset for autonomous trucking in diverse conditions
SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM
JaxMARL: Multi-Agent RL Environments and Algorithms in JAX
A Systematic Review of NeurIPS Dataset Management Practices
Flaws can be Applause: Unleashing Potential of Segmenting Ambiguous Objects in SAM
Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models
DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States
RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from Scripts
NN4SysBench: Characterizing Neural Network Verification for Computer Systems
TaskBench: Benchmarking Large Language Models for Task Automation
Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis
MMM-RS: A Multi-modal, Multi-GSD, Multi-scene Remote Sensing Dataset and Benchmark for Text-to-Image Generation
The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection
Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective
A Cross-Domain Benchmark for Active Learning
HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection
DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion
MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations
Federated Model Heterogeneous Matryoshka Representation Learning
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
Mini-Sequence Transformers: Optimizing Intermediate Memory for Long Sequences Training
WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control
DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain
StreamBench: Towards Benchmarking Continuous Improvement of Language Agents
RobIR: Robust Inverse Rendering for High-Illumination Scenes
WikiDBs: A Large-Scale Corpus Of Relational Databases From Wikidata
Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction
ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model
Mars: Situated Inductive Reasoning in an Open-World Environment
Efficient Sketches for Training Data Attribution and Studying the Loss Landscape
FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection
Vision-Language Navigation with Energy-Based Policy
Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing
DisC-GS: Discontinuity-aware Gaussian Splatting
Benchmarking Structural Inference Methods for Interacting Dynamical Systems with Synthetic Data
Towards Visual Text Design Transfer Across Languages
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles
Paloma: A Benchmark for Evaluating Language Model Fit
SeeA*: Efficient Exploration-Enhanced A* Search by Selective Sampling
WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors
FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling
$\texttt{pfl-research}$: simulation framework for accelerating research in Private Federated Learning
Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency
Historical Test-time Prompt Tuning for Vision Foundation Models
Instruction Tuning Large Language Models to Understand Electronic Health Records
Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited Modalities
Structured Matrix Basis for Multivariate Time Series Forecasting with Interpretable Dynamics
ODRL: A Benchmark for Off-Dynamics Reinforcement Learning
Sharing Key Semantics in Transformer Makes Efficient Image Restoration
Localizing Memorization in SSL Vision Encoders
A StrongREJECT for Empty Jailbreaks
Marginal Causal Flows for Validation and Inference
Nuclear Fusion Diamond Polishing Dataset
SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
DINTR: Tracking via Diffusion-based Interpolation
FLAME : Factuality-Aware Alignment for Large Language Models
GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring
Tetrahedron Splatting for 3D Generation
Integrating Suboptimal Human Knowledge with Hierarchical Reinforcement Learning for Large-Scale Multiagent Systems
MultiOrg: A Multi-rater Organoid-detection Dataset
Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments
VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
MEQA: A Benchmark for Multi-hop Event-centric Question Answering with Explanations
A Generative Model of Symmetry Transformations
PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models
SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning
PROSPECT PTMs: Rich Labeled Tandem Mass Spectrometry Dataset of Modified Peptides for Machine Learning in Proteomics
Perceptual Fairness in Image Restoration
ABCFair: an Adaptable Benchmark approach for Comparing Fairness Methods
Biomedical Visual Instruction Tuning with Clinician Preference Alignment
DeepLag: Discovering Deep Lagrangian Dynamics for Intuitive Fluid Prediction
UrbanDataLayer: A Unified Data Pipeline for Urban Science
Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation
SuperVLAD: Compact and Robust Image Descriptors for Visual Place Recognition
Persistent Test-time Adaptation in Recurring Testing Scenarios
SurgicAI: A Hierarchical Platform for Fine-Grained Surgical Policy Learning and Benchmarking
Tell What You Hear From What You See - Video to Audio Generation Through Text
A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment
M3LEO: A Multi-Modal, Multi-Label Earth Observation Dataset Integrating Interferometric SAR and Multispectral Data
WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks
kGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution
Neural Gaffer: Relighting Any Object via Diffusion
A hierarchical decomposition for explaining ML performance discrepancies
ACFun: Abstract-Concrete Fusion Facial Stylization
PromptFix: You Prompt and We Fix the Photo
WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia
Understanding Bias in Large-Scale Visual Datasets
HAWK: Learning to Understand Open-World Video Anomalies
Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies
Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs
The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection Benchmark
The Art of Saying No: Contextual Noncompliance in Language Models
A Practitioner's Guide to Real-World Continual Multimodal Pretraining
GV-Rep: A Large-Scale Dataset for Genetic Variant Representation Learning
CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence
Goal Conditioned Reinforcement Learning for Photo Finishing Tuning
CARE: a Benchmark Suite for the Classification and Retrieval of Enzymes
Using Unity to Help Solve Reinforcement Learning
Off-Policy Selection for Initiating Human-Centric Experimental Design
Rethinking No-reference Image Exposure Assessment from Holism to Pixel: Models, Datasets and Benchmarks
EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records
GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps
End-to-end Learnable Clustering for Intent Learning in Recommendation
InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models
GLBench: A Comprehensive Benchmark for Graph with Large Language Models
T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition
Benchmarking Complex Instruction-Following with Multiple Constraints Composition
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark
Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry
Conjugate Bayesian Two-step Change Point Detection for Hawkes Process
Evaluating language models as risk scores
IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS
Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting
LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low Resource and Extinct Languages
Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD
Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal
Approaching Human-Level Forecasting with Language Models
BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models
Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity
Learning 3D Equivariant Implicit Function with Patch-Level Pose-Invariant Representation
Interactive Deep Clustering via Value Mining
UltraPixel: Advancing Ultra High-Resolution Image Synthesis to New Peaks
NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction
DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation
Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers
Addressing Bias in Online Selection with Limited Budget of Comparisons
Neural Isometries: Taming Transformations for Equivariant ML
Style Adaptation and Uncertainty Estimation for Multi-Source Blended-Target Domain Adaptation
Robust Fine-tuning of Zero-shot Models via Variance Reduction
Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy
Improved off-policy training of diffusion samplers
Noisy Dual Mirror Descent: A Near Optimal Algorithm for Jointly-DP Convex Resource Allocation
A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective
Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning
Large Scale Transfer Learning for Tabular Data via Language Modeling
Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers
Return of Unconditional Generation: A Self-supervised Representation Generation Method
Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge
Towards Flexible Visual Relationship Segmentation
Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models
Fourier Neural Operator with Learned Deformations for PDEs on General Geometries
Stepwise Alignment for Constrained Language Model Policy Optimization
Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis
Generate Universal Adversarial Perturbations for Few-Shot Learning
VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions
Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features
Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration
Stability and Generalizability in SDE Diffusion Models with Measure-Preserving Dynamics
R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction
TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scene
Amortizing intractable inference in diffusion models for vision, language, and control
GSDF: 3DGS Meets SDF for Improved Neural Rendering and Reconstruction
Multi-Agent Coordination via Multi-Level Communication
UQ-Guided Hyperparameter Optimization for Iterative Learners
ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images
Compositional PAC-Bayes: Generalization of GNNs with persistence and beyond
SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization
Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models
Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation
Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes
MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence
Optimal Algorithms for Online Convex Optimization with Adversarial Constraints
DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Rendering
Video Token Merging for Long Video Understanding
Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning
Gradient-based Discrete Sampling with Automatic Cyclical Scheduling
PLIP: Language-Image Pre-training for Person Representation Learning
Can Large Language Model Agents Simulate Human Trust Behavior?
Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution
Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Model
FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
Octopus: A Multi-modal LLM with Parallel Recognition and Sequential Understanding
Implicit Curriculum in Procgen Made Explicit
Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation
MambaTree: Tree Topology is All You Need in State Space Model
Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits
Boosting Graph Pooling with Persistent Homology
LG-CAV: Train Any Concept Activation Vector with Language Guidance
The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks
Instruction Tuning With Loss Over Instructions
NVRC: Neural Video Representation Compression
4+3 Phases of Compute-Optimal Neural Scaling Laws
Causal Temporal Representation Learning with Nonstationary Sparse Transition
Optimal deep learning of holomorphic operators between Banach spaces
A Globally Optimal Portfolio for m-Sparse Sharpe Ratio Maximization
Fine-grained Control of Generative Data Augmentation in IoT Sensing
BackTime: Backdoor Attacks on Multivariate Time Series Forecasting
On-Road Object Importance Estimation: A New Dataset and A Model with Multi-Fold Top-Down Guidance
Hierarchical Hybrid Sliced Wasserstein: A Scalable Metric for Heterogeneous Joint Distributions
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation
Hyper-opinion Evidential Deep Learning for Out-of-Distribution Detection
BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models
CigTime: Corrective Instruction Generation Through Inverse Motion Editing
Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting
Efficient LLM Scheduling by Learning to Rank
Dealing with Synthetic Data Contamination in Online Continual Learning
Towards Flexible 3D Perception: Object-Centric Occupancy Completion Augments 3D Object Detection
Not All Tokens Are What You Need for Pretraining
Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning
Opponent Modeling based on Subgoal Inference
Dual Cone Gradient Descent for Training Physics-Informed Neural Networks
OneActor: Consistent Subject Generation via Cluster-Conditioned Guidance
Fourier-enhanced Implicit Neural Fusion Network for Multispectral and Hyperspectral Image Fusion
Multi-times Monte Carlo Rendering for Inter-reflection Reconstruction
FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection
Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
QTIP: Quantization with Trellises and Incoherence Processing
The Space Complexity of Approximating Logistic Loss
The Mamba in the Llama: Distilling and Accelerating Hybrid Models
Towards Robust Multimodal Sentiment Analysis with Incomplete Data
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis
Neural Experts: Mixture of Experts for Implicit Neural Representations
Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models.
Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images
Infinite-Dimensional Feature Interaction
FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge
Trading off Consistency and Dimensionality of Convex Surrogates for Multiclass Classification
Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains
SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
Prospective Representation Learning for Non-Exemplar Class-Incremental Learning
Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding
$\textit{Bifr\"ost}$: 3D-Aware Image Compositing with Language Instructions
Domain Adaptation for Large-Vocabulary Object Detectors
Interpreting Learned Feedback Patterns in Large Language Models
First-Order Methods for Linearly Constrained Bilevel Optimization
Preferential Normalizing Flows
MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts
Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation
InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
Logical characterizations of recurrent graph neural networks with reals and floats
AGILE: A Novel Reinforcement Learning Framework of LLM Agents
SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet Knowledge
Resolving Discrepancies in Compute-Optimal Scaling of Language Models
CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense
SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams
Constrained Sampling with Primal-Dual Langevin Monte Carlo
Self-playing Adversarial Language Game Enhances LLM Reasoning
S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning
SDformer: Similarity-driven Discrete Transformer For Time Series Generation
Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learner
SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction
Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games
RL-GPT: Integrating Reinforcement Learning and Code-as-policy
MindMerger: Efficiently Boosting LLM Reasoning in non-English Languages
Rethinking Parity Check Enhanced Symmetry-Preserving Ansatz
Shaping the distribution of neural responses with interneurons in a recurrent circuit model
CLIP in Mirror: Disentangling text from visual images through reflection
Sample-Efficient Constrained Reinforcement Learning with General Parameterization
Improved Regret for Bandit Convex Optimization with Delayed Feedback
GRANOLA: Adaptive Normalization for Graph Neural Networks
Learning the Latent Causal Structure for Modeling Label Noise
Multimodal Large Language Models Make Text-to-Image Generative Models Align Better
SCaR: Refining Skill Chaining for Long-Horizon Robotic Manipulation via Dual Regularization
Streaming Bayes GFlowNets
Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulation
Breaking Semantic Artifacts for Generalized AI-generated Image Detection
Text-Infused Attention and Foreground-Aware Modeling for Zero-Shot Temporal Action Detection
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
Learning Cortico-Muscular Dependence through Orthonormal Decomposition of Density Ratios
Cascade of phase transitions in the training of energy-based models
Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
An Improved Empirical Fisher Approximation for Natural Gradient Descent
SelfCodeAlign: Self-Alignment for Code Generation
ColJailBreak: Collaborative Generation and Editing for Jailbreaking Text-to-Image Deep Generation
Certified Machine Unlearning via Noisy Stochastic Gradient Descent
A Concept-Based Explainability Framework for Large Multimodal Models
Distributional Reinforcement Learning with Regularized Wasserstein Loss
Fair Online Bilateral Trade
Pseudo-Private Data Guided Model Inversion Attacks
Binary Search with Distributional Predictions
Towards Explainable Evaluation Metrics for Machine Translation
Random Cycle Coding: Lossless Compression of Cluster Assignments via Bits-Back Coding
$\textit{NeuroPath}$: A Neural Pathway Transformer for Joining the Dots of Human Connectomes
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning
Identify Then Recommend: Towards Unsupervised Group Recommendation
Empowering Visible-Infrared Person Re-Identification with Large Foundation Models
Community Detection Guarantees using Embeddings Learned by Node2Vec
Decoupling Semantic Similarity from Spatial Alignment for Neural Networks.
Conditional Density Estimation with Histogram Trees
Rethinking LLM Memorization through the Lens of Adversarial Compression
Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits
Unveiling LoRA Intrinsic Ranks via Salience Analysis
Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing
LLMDFA: Analyzing Dataflow in Code with Large Language Models
Oracle-Efficient Differentially Private Learning with Public Data
On the Use of Anchoring for Training Vision Models
Probing Social Bias in Labor Market Text Generation by ChatGPT: A Masked Language Model Approach
Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding
Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs
Fisher Flow Matching for Generative Modeling over Discrete Data
Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently
Omnigrasp: Grasping Diverse Objects with Simulated Humanoids
Accelerating Augmentation Invariance Pretraining
Training Data Attribution via Approximate Unrolling
Transformers Can Do Arithmetic with the Right Embeddings
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks
Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales
ChatQA: Surpassing GPT-4 on Conversational QA and RAG
Not so griddy: Internal representations of RNNs path integrating more than one agent
The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
Instance-Specific Asymmetric Sensitivity in Differential Privacy
Approximation Rate of the Transformer Architecture for Sequence Modeling
In-Context Learning with Representations: Contextual Generalization of Trained Transformers
Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
Towards Exact Gradient-based Training on Analog In-memory Computing
Identifiability Analysis of Linear ODE Systems with Hidden Confounders
AHA: Human-Assisted Out-of-Distribution Generalization and Detection
Linear Causal Representation Learning from Unknown Multi-node Interventions
RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks
Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model
Fair Kernel K-Means: from Single Kernel to Multiple Kernel
An Autoencoder-Like Nonnegative Matrix Co-Factorization for Improved Student Cognitive Modeling
Active Perception for Grasp Detection via Neural Graspness Field
AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
Absorb & Escape: Overcoming Single Model Limitations in Generating Heterogeneous Genomic Sequences
Adaptive Visual Scene Understanding: Incremental Scene Graph Generation
DoFIT: Domain-aware Federated Instruction Tuning with Alleviated Catastrophic Forgetting
Robust Offline Active Learning on Graphs
Local Curvature Smoothing with Stein's Identity for Efficient Score Matching
Unveiling Encoder-Free Vision-Language Models
SlimGPT: Layer-wise Structured Pruning for Large Language Models
Decoding-Time Language Model Alignment with Multiple Objectives
Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNs
Make Your LLM Fully Utilize the Context
On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation
Temporal Graph Neural Tangent Kernel with Graphon-Guaranteed
Faster Local Solvers for Graph Diffusion Equations
Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance
Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization
Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series
StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs
MKGL: Mastery of a Three-Word Language
Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective
Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation
OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling
GenRec: Unifying Video Generation and Recognition with Diffusion Models
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow
Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning
B-ary Tree Push-Pull Method is Provably Efficient for Distributed Learning on Heterogeneous Data
SAND: Smooth imputation of sparse and noisy functional data with Transformer networks
How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective
GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes
ContactField: Implicit Field Representation for Multi-Person Interaction Geometry
Adaptive Domain Learning for Cross-domain Image Denoising
DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation
Pedestrian-Centric 3D Pre-collision Pose and Shape Estimation from Dashcam Perspective
Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks
Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models
Physics-Constrained Comprehensive Optical Neural Networks
Divide-and-Conquer Posterior Sampling for Denoising Diffusion priors
Unveiling The Matthew Effect Across Channels: Assessing Layer Width Sufficiency via Weight Norm Variance
Can Simple Averaging Defeat Modern Watermarks?
LaSe-E2V: Towards Language-guided Semantic-aware Event-to-Video Reconstruction
AdaPKC: PeakConv with Adaptive Peak Receptive Field for Radar Semantic Segmentation
On Sampling Strategies for Spectral Model Sharding
Aligning Individual and Collective Objectives in Multi-Agent Cooperation
PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition
One-Step Diffusion Distillation through Score Implicit Matching
Penalty-based Methods for Simple Bilevel Optimization under Hölderian Error Bounds
FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model
Private Edge Density Estimation for Random Graphs: Optimal, Efficient and Robust
Memory-Efficient LLM Training with Online Subspace Descent
Transformers are Minimax Optimal Nonparametric In-Context Learners
MOTE-NAS: Multi-Objective Training-based Estimate for Efficient Neural Architecture Search
ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate
The Implicit Bias of Gradient Descent toward Collaboration between Layers: A Dynamic Analysis of Multilayer Perceptions
Measuring Goal-Directedness
Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
Predicting Future Actions of Reinforcement Learning Agents
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
Suitable is the Best: Task-Oriented Knowledge Fusion in Vulnerability Detection
Towards Neuron Attributions in Multi-Modal Large Language Models
Analytically deriving Partial Information Decomposition for affine systems of stable and convolution-closed distributions
Stochastic Newton Proximal Extragradient Method
Neural Concept Binder
EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching
Parallel Backpropagation for Shared-Feature Visualization
Designs for Enabling Collaboration in Human-Machine Teaming via Interactive and Explainable Systems
The Secretary Problem with Predicted Additive Gap
Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models
Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks
Discrete Modeling via Boundary Conditional Diffusion Processes
LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch
Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs
Latent Neural Operator for Solving Forward and Inverse PDE Problems
Mechanism design augmented with output advice
HyperPrism: An Adaptive Non-linear Aggregation Framework for Distributed Machine Learning over Non-IID Data and Time-varying Communication Links
Thinking Forward: Memory-Efficient Federated Finetuning of Language Models
Towards Editing Time Series
Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual Structures
Reproducibility Study: Equal Improvability: A New Fairness Notion Considering the Long-Term Impact
Language Without Borders: A Dataset and Benchmark for Code-Switching Lip Reading
The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms
Smoothed Online Classification can be Harder than Batch Classification
AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making
Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model
APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments
[Re] CUDA: Curriculum of Data Augmentation for Long‐tailed Recognition
Better by default: Strong pre-tuned MLPs and boosted trees on tabular data
Learning Action and Reasoning-Centric Image Editing from Videos and Simulation
Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation
DAPE: Data-Adaptive Positional Encoding for Length Extrapolation
Scaling Sign Language Translation
Exploitation of a Latent Mechanism in Graph Contrastive Learning: Representation Scattering
UDON: Universal Dynamic Online distillatioN for generic image representations
Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features
EGSST: Event-based Graph Spatiotemporal Sensitive Transformer for Object Detection
Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models
MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
Multi-LLM Debate: Framework, Principals, and Interventions
Adaptive Sampling for Efficient Softmax Approximation
MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation
Demystify Mamba in Vision: A Linear Attention Perspective
Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
MVGamba: Unify 3D Content Generation as State Space Sequence Modeling
SciCode: A Research Coding Benchmark Curated by Scientists
Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers
A Simple Image Segmentation Framework via In-Context Examples
DOFEN: Deep Oblivious Forest ENsemble
Large Language Models' Expert-level Global History Knowledge Benchmark (HiST-LLM)
Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning
B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
Proving Olympiad Algebraic Inequalities without Human Demonstrations
On the Inductive Bias of Stacking Towards Improving Reasoning
Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
Data Acquisition via Experimental Design for Data Markets
QKFormer: Hierarchical Spiking Transformer using Q-K Attention
CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns
DisCEdit: Model Editing by Identifying Discriminative Components
A Continuous-time Stochastic Gradient Descent Method for Continuous Data
Statistical Inference for Fairness Auditing
Spectral Adapter: Fine-Tuning in Spectral Space
Derandomizing Multi-Distribution Learning
RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar
Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering
Unifying Homophily and Heterophily for Spectral Graph Neural Networks via Triple Filter Ensembles
ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer
A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health
An Adaptive Approach for Infinitely Many-armed Bandits under Generalized Rotting Constraints
Time-Reversal Provides Unsupervised Feedback to LLMs
Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
Where Do Large Learning Rates Lead Us?
Du-IN: Discrete units-guided mask modeling for decoding speech from Intracranial Neural signals
Distributed Sparse Regression via Penalization
A Unified Recipe for Deriving (Time-Uniform) PAC-Bayes Bounds
Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees
Optimal Clustering with Bandit Feedback
Transfer Learning with Informative Priors: Simple Baselines Better than Previously Reported
Towards Global Optimal Visual In-Context Learning Prompt Selection
Unified Generative and Discriminative Training for Multi-modal Large Language Models
CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition
SfPUEL: Shape from Polarization under Unknown Environment Light
LG-VQ: Language-Guided Codebook Learning
OccamLLM: Fast and Exact Language Model Arithmetic in a Single Step
Rethinking the Diffusion Models for Missing Data Imputation: A Gradient Flow Perspective
RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance
SegVol: Universal and Interactive Volumetric Medical Image Segmentation
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation
Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets
Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation
SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation
BertaQA: How Much Do Language Models Know About Local Culture?
Selective Explanations
Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection
Reinforcement Learning with Lookahead Information
Focus On What Matters: Separated Models For Visual-Based RL Generalization
IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation
Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning
Stochastic Optimal Control and Estimation with Multiplicative and Internal Noise
Understanding and Improving Training-free Loss-based Diffusion Guidance
VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages
HEMM: Holistic Evaluation of Multimodal Foundation Models
OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Construction
WhodunitBench: Evaluating Large Multimodal Agents via Murder Mystery Games
MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models
IaC-Eval: A Code Generation Benchmark for Cloud Infrastructure-as-Code Programs
UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training
LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation
ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty
Building Timeseries Dataset: Empowering Large-Scale Building Analytics
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
A Hitchhiker's Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning
ImageNet3D: Towards General-Purpose Object-Level 3D Understanding
Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving
Infusing Synthetic Data with Real-World Patterns for Zero-Shot Material State Segmentation
ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs
Sim2Real-Fire: A Multi-modal Simulation Dataset for Forecast and Backtracking of Real-world Forest Fire
GC-Bench: An Open and Unified Benchmark for Graph Condensation
LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment
CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs
AFBench: A Large-scale Benchmark for Airfoil Design
INQUIRE: A Natural World Text-to-Image Retrieval Benchmark
ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs
FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic Understanding
Streaming Detection of Queried Event Start
Test-time Adaptation in Non-stationary Environments via Adaptive Representation Alignment
A New Multi-Source Light Detection Benchmark and Semi-Supervised Focal Light Detection
BuckTales: A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes
Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?
MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations
Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning
DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model
FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models
UniMTS: Unified Pre-training for Motion Time Series
GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks
SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models
FindingEmo: An Image Dataset for Emotion Recognition in the Wild
ComBack: A Versatile Dataset for Enhancing Compiler Backend Development Efficiency
Is Your HD Map Constructor Reliable under Sensor Corruptions?
LucidAction: A Hierarchical and Multi-model Dataset for Comprehensive Action Quality Assessment
$\texttt{Model-GLUE}$: Democratized LLM Scaling for A Large Model Zoo in the Wild
BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays
BEACON: Benchmark for Comprehensive RNA Tasks and Language Models
FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models
The iNaturalist Sounds Dataset
A Synthetic Dataset for Personal Attribute Inference
Learning Superconductivity from Ordered and Disordered Material Structures
CoIN: A Benchmark of Continual Instruction Tuning for Multimodel Large Language Models
LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding
Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection
HourVideo: 1-Hour Video-Language Understanding
MARPLE: A Benchmark for Long-Horizon Inference
Scalable Early Childhood Reading Performance Prediction
Infer Induced Sentiment of Comment Response to Video: A New Task, Dataset and Baseline
IncomeSCM: From tabular data set to time-series simulator and causal estimation benchmark
LAVIB: A Large-scale Video Interpolation Benchmark
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs
DreamCatcher: A Wearer-aware Multi-modal Sleep Event Dataset Based on Earables in Non-restrictive Environments
NeuralPlane: An Efficiently Parallelizable Platform for Fixed-wing Aircraft Control with Reinforcement Learning
UltraMedical: Building Specialized Generalists in Biomedicine
Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization Regime
Task Me Anything
FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models
Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors
VastTrack: Vast Category Visual Object Tracking
GAIA: Rethinking Action Quality Assessment for AI-Generated Videos
Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models
WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences
Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions
Archaeoscape: Bringing Aerial Laser Scanning Archaeology to the Deep Learning Era
Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
SCRREAM : SCan, Register, REnder And Map: A Framework for Annotating Accurate and Dense 3D Indoor Scenes with a Benchmark
Muharaf: Manuscripts of Handwritten Arabic Dataset for Cursive Text Recognition
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos
Image Textualization: An Automatic Framework for Generating Rich and Detailed Image Descriptions
Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset
The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding
FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving
CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses
SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation
EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes
SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset
SeafloorAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey
Multi-modal Situated Reasoning in 3D Scenes
Benchmarking the Attribution Quality of Vision Models
4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on RDBs
GeoPlant: Spatial Plant Species Prediction Dataset
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
PEACE: A Dataset of Pharmaceutical Care for Cancer Pain Analgesia Evaluation and Medication Decision
Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox
Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models
WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark
NanoBaseLib: A Multi-Task Benchmark Dataset for Nanopore Sequencing
ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination
APEBench: A Benchmark for Autoregressive Neural Emulators of PDEs
A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era
On the Effects of Data Scale on UI Control Agents
TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning
GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shifts
Indoor Air Quality Dataset with Activities of Daily Living in Low to Middle-income Communities
EEVR: A Dataset of Paired Physiological Signals and Textual Descriptions for Joint Emotion Representation Learning
Calibrated Self-Rewarding Vision Language Models
LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models
Benchmarking Estimators for Natural Experiments: A Novel Dataset and a Doubly Robust Algorithm
Towards General Loop Invariant Generation: A Benchmark of Programs with Memory Manipulation
Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias
Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge
Terra: A Multimodal Spatio-Temporal Dataset Spanning the Earth
Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking
NovoBench: Benchmarking Deep Learning-based \emph{De Novo} Sequencing Methods in Proteomics
GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI
Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models
WONDERBREAD: A Benchmark for Evaluating Multimodal Foundation Models on Business Process Management Tasks
GenAI Arena: An Open Evaluation Platform for Generative Models
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation
Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics
NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models
Fast and Memory-Efficient Video Diffusion Using Streamlined Inference
PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads
A Benchmark Suite for Evaluating Neural Mutual Information Estimators on Unstructured Datasets
CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding
A Benchmark Dataset for Event-Guided Human Pose Estimation and Tracking in Extreme Conditions
HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
DF40: Toward Next-Generation Deepfake Detection
SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution
Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
WenMind: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Classical Literature and Language Arts
AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games
The Multimodal Universe: Enabling Large-Scale Machine Learning with 100 TB of Astronomical Scientific Data
VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark
DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks
Needle In A Multimodal Haystack
GTA: A Benchmark for General Tool Agents
Muscles in Time: Learning to Understand Human Motion In-Depth by Simulating Muscle Activations
Copycats: the many lives of a publicly available medical imaging dataset
LVD-2M: A Long-take Video Dataset with Temporally Dense Captions
ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction
T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming
BeanCounter: A low-toxicity, large-scale, and open dataset of business-oriented text
A Taxonomy of Challenges to Curating Fair Datasets
Revisiting Few-Shot Object Detection with Vision-Language Models
CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities
PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbations
DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios
FlexMol: A Flexible Toolkit for Benchmarking Molecular Relational Learning
A SARS-CoV-2 Interaction Dataset and VHH Sequence Corpus for Antibody Language Models
FinBen: A Holistic Financial Benchmark for Large Language Models
PURE: Prompt Evolution with Graph ODE for Out-of-distribution Fluid Dynamics Modeling
Brain Treebank: Large-scale intracranial recordings from naturalistic language stimuli
SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models
A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics
Einsum Benchmark: Enabling the Development of Next-Generation Tensor Execution Engines
Lean Workbook: A large-scale Lean problem set formalized from natural language math problems
ConceptFactory: Facilitate 3D Object Knowledge Annotation with Object Conceptualization
OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking
AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery
Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation
MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
Towards Next-Generation Logic Synthesis: A Scalable Neural Circuit Generation Framework
SHDocs: A dataset, benchmark, and method to efficiently generate high-quality, real-world specular highlight data with near-perfect alignment
II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models
Do Counterfactually Fair Image Classifiers Satisfy Group Fairness? -- A Theoretical and Empirical Study
The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning
Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and Toolbox
SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image Classification
The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning
JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images
Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model
BIGOS V2 Benchmark for Polish ASR: Curated Datasets and Tools for Reproducible Evaluation
Off to new Shores: A Dataset & Benchmark for (near-)coastal Flood Inundation Forecasting
ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition
STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics
The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset
Is Function Similarity Over-Engineered? Building a Benchmark
SolarCube: An Integrative Benchmark Dataset Harnessing Satellite and In-situ Observations for Large-scale Solar Energy Forecasting
MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling
USCILab3D: A Large-scale, Long-term, Semantically Annotated Outdoor Dataset
SubjECTive-QA: Measuring Subjectivity in Earnings Call Transcripts' QA Through Six-Dimensional Feature Analysis
Implicit Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes
RelBench: A Benchmark for Deep Learning on Relational Databases
Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets
emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation
NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security
ReactZyme: A Benchmark for Enzyme-Reaction Prediction
BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity
MOTIVE: A Drug-Target Interaction Graph For Inductive Link Prediction
IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization
Benchmark Data Repositories for Better Benchmarking
VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images
Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
Can LLMs Solve Molecule Puzzles? A Multimodal Benchmark for Molecular Structure Elucidation
Evaluating Copyright Takedown Methods for Language Models
Towards Comprehensive Detection of Chinese Harmful Memes
Assemblage: Automatic Binary Dataset Construction for Machine Learning
Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking
TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs
MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving
Instruction Embedding: Latent Representations of Instructions Towards Task Identification
SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagery
SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers
Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights
ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Ablation Capability for Large Vision-Language Models
A Careful Examination of Large Language Model Performance on Grade School Arithmetic
SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations
Vript: A Video Is Worth Thousands of Words
emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography
AudioMarkBench: Benchmarking Robustness of Audio Watermarking
UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-World Document Analysis
$E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset
ViLCo-Bench: VIdeo Language COntinual learning Benchmark
RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation
EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos
WildPPG: A Real-World PPG Dataset of Long Continuous Recordings
Benchmarking LLMs via Uncertainty Quantification
XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX
OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset
Are Large Language Models Good Statisticians?
MedJourney: Benchmark and Evaluation of Large Language Models over Patient Clinical Journey
TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools
PUZZLES: A Benchmark for Neural Algorithmic Reasoning
dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans
Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
$\nabla^2$DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials
AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries
BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval
Fit for our purpose, not yours: Benchmark for a low-resource, Indigenous language
Evaluating Multiview Object Consistency in Humans and Image Models
Advancing Video Anomaly Detection: A Concise Review and a New Dataset
A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences
EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries
A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data
CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence
NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates
Noisy Ostracods: A Fine-Grained, Imbalanced Real-World Dataset for Benchmarking Robust Machine Learning and Label Correction Methods
MathPile: A Billion-Token-Scale Pretraining Corpus for Math
Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation
Benchmarking Counterfactual Image Generation
CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making
WindsorML: High-Fidelity Computational Fluid Dynamics Dataset For Automotive Aerodynamics
PowerGraph: A power grid benchmark dataset for graph neural networks
ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models
TAPVid-3D: A Benchmark for Tracking Any Point in 3D
Newswire: A Large-Scale Structured Database of a Century of Historical News
Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
UniTox: Leveraging LLMs to Curate a Unified Dataset of Drug-Induced Toxicity from FDA Labels
EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity
FT-AED: Benchmark Dataset for Early Freeway Traffic Anomalous Event Detection
ProG: A Graph Prompt Learning Benchmark
$\texttt{dattri}$: A Library for Efficient Data Attribution
DECO-Bench: Unified Benchmark for Decoupled Task-Agnostic Synthetic Data Release
3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition
Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models
OAM-TCD: A globally diverse dataset of high-resolution tree cover maps
RedCode: Risky Code Execution and Generation Benchmark for Code Agents
BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity
What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction
cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Papers
RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation
Data curation via joint example selection further accelerates multimodal learning
StackEval: Benchmarking LLMs in Coding Assistance
Kuro Siwo: 33 billion $m^2$ under the water. A global multi-temporal satellite dataset for rapid flood mapping
ClashEval: Quantifying the tug-of-war between an LLM’s internal prior and external evidence
Enhancing vision-language models for medical imaging: bridging the 3D gap with innovative slice selection
SETLEXSEM CHALLENGE: Using Set Operations to Evaluate the Lexical and Semantic Robustness of Language Models
AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction
Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos
IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents
SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark
RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content
TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
shapiq: Shapley Interactions for Machine Learning
Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs
ReMI: A Dataset for Reasoning with Multiple Images
Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks
Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis
CALE: Continuous Arcade Learning Environment
Arctique: An artificial histopathological dataset unifying realism and controllability for uncertainty quantification
PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition
Consent in Crisis: The Rapid Decline of the AI Data Commons
Vocal Call Locator Benchmark (VCL) for localizing rodent vocalizations from multi-channel audio
DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
Weight decay induces low-rank attention layers
V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark
ClevrSkills: Compositional Language And Visual Reasoning in Robotics
Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking
DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents
RedPajama: an Open Dataset for Training Large Language Models
CiteME: Can Language Models Accurately Cite Scientific Claims?
Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex.
The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
Croissant: A Metadata Format for ML-Ready Datasets
Evaluating Numerical Reasoning in Text-to-Image Models
CryoBench: Diverse and challenging datasets for the heterogeneity problem in cryo-EM
Topic-Conversation Relevance (TCR) Dataset and Benchmarks
HelpSteer 2: Open-source dataset for training top-performing reward models
Image2Struct: Benchmarking Structure Extraction for Vision-Language Models
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
MassSpecGym: A benchmark for the discovery and identification of molecules
VHELM: A Holistic Evaluation of Vision Language Models
The State of Data Curation at NeurIPS: An Assessment of Dataset Development Practices in the Datasets and Benchmarks Track
Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
BLURD: Benchmarking and Learning using a Unified Rendering and Diffusion Model
MedCalc-Bench: Evaluating Large Language Models for Medical Calculations
A benchmark for prediction of transcriptomic responses to chemical perturbations across cell types
DevBench: A multimodal developmental benchmark for language learning
InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers
DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs
NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noise
Slice-100K: A Multimodal Dataset for Extrusion-based 3D Printing
Micro-Bench: A Microscopy Benchmark for Vision-Language Understanding
Melting Pot Contest: Charting the Future of Generalized Cooperative Intelligence
MmCows: A Multimodal Dataset for Dairy Cattle Monitoring
SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words
Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline
The Selective $G$-Bispectrum and its Inversion: Applications to $G$-Invariant Networks
Map It Anywhere: Empowering BEV Map Prediction using Large-scale Public Datasets
WikiDO: A New Benchmark Evaluating Cross-Modal Retrieval for Vision-Language Models
EMGBench: Benchmarking Out-of-Distribution Generalization and Adaptation for Electromyography
Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack
ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons
Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models
BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages
ProgressGym: Alignment with a Millennium of Moral Progress
Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Series
BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack
$\texttt{ConflictBank}$: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMs
Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
FairJob: A Real-World Dataset for Fairness in Online Systems
Multi-Chain Graphs of Graphs: A New Approach to Analyzing Blockchain Datasets
CRAG - Comprehensive RAG Benchmark
NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking
Learning Structure-Aware Representations of Dependent Types
What Rotary Position Embedding Can Tell Us: Identifying Query and Key Weights Corresponding to Basic Syntactic or High-level Semantic Information
Large Language Model Unlearning via Embedding-Corrupted Prompts
Attack-Resilient Image Watermarking Using Stable Diffusion
Unlock the Intermittent Control Ability of Model Free Reinforcement Learning
Adaptive Passive-Aggressive Framework for Online Regression with Side Information
Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Play
Transition Constrained Bayesian Optimization via Markov Decision Processes
Fairness-Aware Meta-Learning via Nash Bargaining
The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations
Transcendence: Generative Models Can Outperform The Experts That Train Them
RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health Interventions
FactorizePhys: Matrix Factorization for Multidimensional Attention in Remote Physiological Sensing
StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses
AutoPSV: Automated Process-Supervised Verifier
Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning
Frustratingly Easy Test-Time Adaptation of Vision-Language Models
Who's asking? User personas and the mechanics of latent misalignment
SpeAr: A Spectral Approach for Zero-Shot Node Classification
Navigating the Effect of Parametrization for Dimensionality Reduction
EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views
Confidence Calibration of Classifiers with Many Classes
Image-aware Evaluation of Generated Medical Reports
CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy
Nuclear Norm Regularization for Deep Learning
Adversarial Environment Design via Regret-Guided Diffusion Models
Multiple Physics Pretraining for Spatiotemporal Surrogate Models
TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
Infinite Limits of Multi-head Transformer Dynamics
Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models
Discovering Preference Optimization Algorithms with and for Large Language Models
Overcoming Brittleness in Pareto-Optimal Learning Augmented Algorithms
Neur2BiLO: Neural Bilevel Optimization
In-Context Symmetries: Self-Supervised Learning through Contextual World Models
Leveraging Drift to Improve Sample Complexity of Variance Exploding Diffusion Models
Foundation Inference Models for Markov Jump Processes
The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
Adaptive Important Region Selection with Reinforced Hierarchical Search for Dense Object Detection
A PID Controller Approach for Adaptive Probability-dependent Gradient Decay in Model Calibration
LaKD: Length-agnostic Knowledge Distillation for Trajectory Prediction with Any Length Observations
Metric Flow Matching for Smooth Interpolations on the Data Manifold
The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better
SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion
Compositional Generalization Across Distributional Shifts with Sparse Tree Operations
Mesa-Extrapolation: A Weave Position Encoding Method for Enhanced Extrapolation in LLMs
Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
Label Noise: Ignorance Is Bliss
TrajCLIP: Pedestrian trajectory prediction method using contrastive learning and idempotent networks
Pretrained Optimization Model for Zero-Shot Black Box Optimization
MatFormer: Nested Transformer for Elastic Inference
Approximating the Top Eigenvector in Random Order Streams
Graph Neural Networks Need Cluster-Normalize-Activate Modules
Exploiting Descriptive Completeness Prior for Cross Modal Hashing with Incomplete Labels
Efficient Leverage Score Sampling for Tensor Train Decomposition
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
Reconstruct and Match: Out-of-Distribution Robustness via Topological Homogeneity
Localized Adaptive Risk Control
Differentiable Modal Synthesis for Physical Modeling of Planar String Sound and Motion Simulation
SpikedAttention: Training-Free and Fully Spike-Driven Transformer-to-SNN Conversion with Winner-Oriented Spike Shift for Softmax Operation
Rethinking Imbalance in Image Super-Resolution for Efficient Inference
ReFT: Representation Finetuning for Language Models
SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection
Speculative Monte-Carlo Tree Search
GFlowNet Assisted Biological Sequence Editing
SPARKLE: A Unified Single-Loop Primal-Dual Framework for Decentralized Bilevel Optimization
CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models
Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis
An Information Theoretic Perspective on Conformal Prediction
Improving robustness to corruptions with multiplicative weight perturbations
Pandora's Box: Towards Building Universal Attackers against Real-World Large Vision-Language Models
Optimal Multi-Fidelity Best-Arm Identification
Panacea: Pareto Alignment via Preference Adaptation for LLMs
Understanding the Gains from Repeated Self-Distillation
Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splatting
Wormhole Loss for Partial Shape Matching
Alias-Free Mamba Neural Operator
Generalizable and Animatable Gaussian Head Avatar
Diffeomorphic interpolation for efficient persistence-based topological optimization
Quasi-Bayes meets Vines
In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment
Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity
Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources
Metric Space Magnitude for Evaluating the Diversity of Latent Representations
SARAD: Spatial Association-Aware Anomaly Detection and Diagnosis for Multivariate Time Series
Boosting Vision-Language Models with Transduction
In-Context Learning State Vector with Inner and Momentum Optimization
Unveiling the Tapestry of Consistency in Large Vision-Language Models
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Diversify, Contextualize, and Adapt: Efficient Entropy Modeling for Neural Image Codec
Image Copy Detection for Diffusion Models
End-To-End Causal Effect Estimation from Unstructured Natural Language Data
Weak-eval-Strong: Evaluating and Eliciting Lateral Thinking of LLMs with Situation Puzzles
Loss Landscape Characterization of Neural Networks without Over-Parametrization
Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts
Provable Benefits of Complex Parameterizations for Structured State Space Models
Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model
InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD
PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
TPC: Test-time Procrustes Calibration for Diffusion-based Human Image Animation
Continuous Partitioning for Graph-Based Semi-Supervised Learning
YOLOv10: Real-Time End-to-End Object Detection
Fixed Confidence Best Arm Identification in the Bayesian Setting
SimGen: Simulator-conditioned Driving Scene Generation
Low-Rank Optimal Transport through Factor Relaxation with Latent Coupling
Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms
An engine not a camera: Measuring performative power of online search
Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning
CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization
Is O(log N) practical? Near-Equivalence Between Delay Robustness and Bounded Regret in Bandits and RL
How Does Message Passing Improve Collaborative Filtering?
DRACO: A Denoising-Reconstruction Autoencoder for Cryo-EM
Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithm
Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning
Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery
Mixture of Experts Meets Prompt-Based Continual Learning
BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling
Vision-Language Models are Strong Noisy Label Detectors
Policy-shaped prediction: avoiding distractions in model-based reinforcement learning
Inverse M-Kernels for Linear Universal Approximators of Non-Negative Functions
Interpretable Image Classification with Adaptive Prototype-based Vision Transformers
HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
Convergence of $\text{log}(1/\epsilon)$ for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis
RGFN: Synthesizable Molecular Generation Using GFlowNets
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
Set-based Neural Network Encoding Without Weight Tying
Pre-trained Large Language Models Use Fourier Features to Compute Addition
Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
Learning to Predict Structural Vibrations
Causal language modeling can elicit search and reasoning capabilities on logic puzzles
Interpretable Lightweight Transformer via Unrolling of Learned Graph Smoothness Priors
SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions
HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation
S-SOS: Stochastic Sum-Of-Squares for Parametric Polynomial Optimization
$C^2M^3$: Cycle-Consistent Multi-Model Merging
ReFIR: Grounding Large Restoration Models with Retrieval Augmentation
Improved Algorithms for Contextual Dynamic Pricing
Are Self-Attentions Effective for Time Series Forecasting?
Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis
Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch
SubgDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning
Stochastic Concept Bottleneck Models
Physics-Informed Regularization for Domain-Agnostic Dynamical System Modeling
Theoretical guarantees in KL for Diffusion Flow Matching
DeepDRK: Deep Dependency Regularized Knockoff for Feature Selection
Variational Distillation of Diffusion Policies into Mixture of Experts
Only Strict Saddles in the Energy Landscape of Predictive Coding Networks?
COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation
Reinforcement Learning with LTL and $\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards
Accurate and Steady Inertial Pose Estimation through Sequence Structure Learning and Modulation
Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD
MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Images
Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention
Generalization Bound and Learning Methods for Data-Driven Projections in Linear Programming
Sparsity-Agnostic Linear Bandits with Adaptive Adversaries
Autoregressive Image Diffusion: Generation of Image Sequence and Application in MRI
Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model
Exploring Behavior-Relevant and Disentangled Neural Dynamics with Generative Diffusion Models
One Sample Fits All: Approximating All Probabilistic Values Simultaneously and Efficiently
Nonstationary Sparse Spectral Permanental Process
Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
DARNet: Dual Attention Refinement Network with Spatiotemporal Construction for Auditory Attention Detection
Statistical Multicriteria Benchmarking via the GSD-Front
Data-faithful Feature Attribution: Mitigating Unobservable Confounders via Instrumental Variables
Small coresets via negative dependence: DPPs, linear statistics, and concentration
Advection Augmented Convolutional Neural Networks
Efficient Temporal Action Segmentation via Boundary-aware Query Voting
Towards Croppable Implicit Neural Representations
EGODE: An Event-attended Graph ODE Framework for Modeling Rigid Dynamics
RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models
RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation
Solving Minimum-Cost Reach Avoid using Reinforcement Learning
Multi-Label Open Set Recognition
Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
Unveiling the Potential of Robustness in Selecting Conditional Average Treatment Effect Estimators
Beyond Optimism: Exploration With Partially Observable Rewards
Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
Diffusion-Reward Adversarial Imitation Learning
Large Language Models Play StarCraft II:Benchmarks and A Chain of Summarization Approach
On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models
An Analysis of Elo Rating Systems via Markov Chains
Fairness and Efficiency in Online Class Matching
This Too Shall Pass: Removing Stale Observations in Dynamic Bayesian Optimization
Chain of Thoughtlessness? An Analysis of CoT in Planning
Solving Sparse \& High-Dimensional-Output Regression via Compression
Dimension-free Private Mean Estimation for Anisotropic Distributions
Data Attribution for Text-to-Image Models by Unlearning Synthesized Images
Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe
Multi-Winner Reconfiguration
Boosting the Transferability of Adversarial Attack on Vision Transformer with Adaptive Token Tuning
Operator World Models for Reinforcement Learning
A generalized neural tangent kernel for surrogate gradient learning
HydraViT: Stacking Heads for a Scalable ViT
Normal-GS: 3D Gaussian Splatting with Normal-Involved Rendering
Group-wise oracle-efficient algorithms for online multi-group learning
Functional Gradient Flows for Constrained Sampling
Optimal Flow Matching: Learning Straight Trajectories in Just One Step
BMRS: Bayesian Model Reduction for Structured Pruning
VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks
Acceleration Exists! Optimization Problems When Oracle Can Only Compare Objective Function Values
LP-3DGS: Learning to Prune 3D Gaussian Splatting
Diffusion Actor-Critic with Entropy Regulator
Practical $0.385$-Approximation for Submodular Maximization Subject to a Cardinality Constraint
Toward Conditional Distribution Calibration in Survival Prediction
RMLR: Extending Multinomial Logistic Regression into General Geometries
Replicable Uniformity Testing
Real-time Core-Periphery Guided ViT with Smart Data Layout Selection on Mobile Devices
Unitary Convolutions for Learning on Graphs and Groups
Thought of Search: Planning with Language Models Through The Lens of Efficiency
PaCE: Parsimonious Concept Engineering for Large Language Models
Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition
Accelerated Regularized Learning in Finite N-Person Games
From Chaos to Clarity: 3DGS in the Dark
Full-Distance Evasion of Pedestrian Detectors in the Physical World
Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond
Deep Learning in Medical Image Registration: Magic or Mirage?
Cascade Speculative Drafting for Even Faster LLM Inference
VISA: Variational Inference with Sequential Sample-Average Approximations
OPEL: Optimal Transport Guided ProcedurE Learning
Shuffling Gradient-Based Methods for Nonconvex-Concave Minimax Optimization
(FL)$^2$: Overcoming Few Labels in Federated Semi-Supervised Learning
UniGAD: Unifying Multi-level Graph Anomaly Detection
Clustering with Non-adaptive Subset Queries
Compressing Large Language Models using Low Rank and Low Precision Decomposition
Black-Box Forgetting
CODA: A Correlation-Oriented Disentanglement and Augmentation Modeling Scheme for Better Resisting Subpopulation Shifts
Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration
UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation
EEGPT: Pretrained Transformer for Universal and Reliable Representation of EEG Signals
MotionCraft: Physics-Based Zero-Shot Video Generation
Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound
Search for Efficient Large Language Models
Predictive Attractor Models
Do LLMs Build World Representations? Probing Through the Lens of State Abstraction
Should We Really Edit Language Models? On the Evaluation of Edited Language Models
GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent
Generalization Error Bounds for Two-stage Recommender Systems with Tree Structure
Practical Bayesian Algorithm Execution via Posterior Sampling
Fetch and Forge: Efficient Dataset Condensation for Object Detection
START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
Long-tailed Object Detection Pretraining: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction
MaNo: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKA
Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization
Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare
Quality-Improved and Property-Preserved Polarimetric Imaging via Complementarily Fusing
A Simple yet Scalable Granger Causal Structural Learning Approach for Topological Event Sequences
Improving the Training of Rectified Flows
DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering
BrainBits: How Much of the Brain are Generative Reconstruction Methods Using?
Once Read is Enough: Domain-specific Pretraining-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain Knowledge
Learning Cooperative Trajectory Representations for Motion Forecasting
RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space
Semantics and Spatiality of Emergent Communication
Learning-Augmented Approximation Algorithms for Maximum Cut and Related Problems
Non-asymptotic Global Convergence Analysis of BFGS with the Armijo-Wolfe Line Search
FreeSplat: Generalizable 3D Gaussian Splatting Towards Free View Synthesis of Indoor Scenes
Learning De-Biased Representations for Remote-Sensing Imagery
A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference
Task-oriented Time Series Imputation Evaluation via Generalized Representers
Evidential Mixture Machines: Deciphering Multi-Label Correlations for Active Learning Sensitivity
Optimal Design for Human Preference Elicitation
Recurrent Reinforcement Learning with Memoroids
Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models
UniTS: A Unified Multi-Task Time Series Model
Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
FineCLIP: Self-distilled Region-based CLIP for Better Fine-grained Understanding
TinyLUT: Tiny Look-Up Table for Efficient Image Restoration at the Edge
DiffSF: Diffusion Models for Scene Flow Estimation
Shared Autonomy with IDA: Interventional Diffusion Assistance
To Err Like Human: Affective Bias-Inspired Measures for Visual Emotion Recognition Evaluation
UGC: Universal Graph Coarsening
Fight Back Against Jailbreaking via Prompt Adversarial Tuning
Toward Real Ultra Image Segmentation: Leveraging Surrounding Context to Cultivate General Segmentation Model
SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functions
Graph Neural Networks Do Not Always Oversmooth
Gradient-free Decoder Inversion in Latent Diffusion Models
A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models
HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
DistrictNet: Decision-aware learning for geographical districting
Visual Fourier Prompt Tuning
NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes
Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression
Constrained Binary Decision Making
Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks
VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks
3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction
If You Want to Be Robust, Be Wary of Initialization
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate
NeuralSteiner: Learning Steiner Tree for Overflow-avoiding Global Routing in Chip Design
Masked Pre-training Enables Universal Zero-shot Denoiser
Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
Posture-Informed Muscular Force Learning for Robust Hand Pressure Estimation
Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
Adversarially Robust Dense-Sparse Tradeoffs via Heavy-Hitters
BiDM: Pushing the Limit of Quantization for Diffusion Models
Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions
Boosting the Potential of Large Language Models with an Intelligent Information Assistant
Generalization Bounds via Conditional $f$-Information
Recovering Complete Actions for Cross-dataset Skeleton Action Recognition
Carrot and Stick: Eliciting Comparison Data and Beyond
RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness
CSPG: Crossing Sparse Proximity Graphs for Approximate Nearest Neighbor Search
Efficient Discrepancy Testing for Learning with Distribution Shift
Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality
Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning
Optimal ablation for interpretability
Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment
Compositional 3D-aware Video Generation with LLM Director
CALANet: Cheap All-Layer Aggregation for Human Activity Recognition
Exploration by Learning Diverse Skills through Successor State Representations
Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization
Particle Semi-Implicit Variational Inference
A Walsh Hadamard Derived Linear Vector Symbolic Architecture
Learning to Solve Quadratic Unconstrained Binary Optimization in a Classification Way
From Dictionary to Tensor: A Scalable Multi-View Subspace Clustering Framework with Triple Information Enhancement
Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models
Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought
Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning
Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints
Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs
Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models
Deep Submodular Peripteral Networks
Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration
Refusal in Language Models Is Mediated by a Single Direction
Scalable Constrained Policy Optimization for Safe Multi-agent Reinforcement Learning
The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure
Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning
Unleashing Multispectral Video's Potential in Semantic Segmentation: A Semi-supervised Viewpoint and New UAV-View Benchmark
What Variables Affect Out-of-Distribution Generalization in Pretrained Models?
MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training
E-Motion: Future Motion Simulation via Event Sequence Diffusion
ReMoDetect: Reward Models Recognize Aligned LLM's Generations
Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Generation
Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection
Near-Optimal Distributed Minimax Optimization under the Second-Order Similarity
Wasserstein Distributionally Robust Optimization through the Lens of Structural Causal Models and Individual Fairness
Algorithmic Capabilities of Random Transformers
SuperDeepFool: a new fast and accurate minimal adversarial attack
CAT: Coordinating Anatomical-Textual Prompts for Multi-Organ and Tumor Segmentation
Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching
Spectral Editing of Activations for Large Language Model Alignment
Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers
Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines
Efficient Combinatorial Optimization via Heat Diffusion
Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process
Abstracted Shapes as Tokens - A Generalizable and Interpretable Model for Time-series Classification
Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning
Apathetic or Empathetic? Evaluating LLMs' Emotional Alignments with Humans
Enhancing LLM’s Cognition via Structurization
N-agent Ad Hoc Teamwork
Stealth edits to large language models
Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates
Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework
Dynamic Neural Regeneration: Enhancing Deep Learning Generalization on Small Datasets
Differentially Private Equivalence Testing for Continuous Distributions and Applications
HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
Persistence Homology Distillation for Semi-supervised Continual Learning
Recognize Any Regions
4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities
Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning
Geodesic Optimization for Predictive Shift Adaptation on EEG data
Expert-level protocol translation for self-driving labs
Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling
The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach
IODA: Instance-Guided One-shot Domain Adaptation for Super-Resolution
MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
SocraticLM: Exploring Socratic Personalized Teaching with Large Language Models
Symmetry Discovery Beyond Affine Transformations
Variational Multi-scale Representation for Estimating Uncertainty in 3D Gaussian Splatting
Bridging OOD Detection and Generalization: A Graph-Theoretic View
How Control Information Influences Multilingual Text Image Generation and Editing?
From Causal to Concept-Based Representation Learning
Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model
DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
Neural Persistence Dynamics
CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models
Learning Successor Features the Simple Way
Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval
No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
Debiasing Synthetic Data Generated by Deep Generative Models
Activating Self-Attention for Multi-Scene Absolute Pose Regression
Interaction-Force Transport Gradient Flows
Learning from Highly Sparse Spatio-temporal Data
Multi-turn Reinforcement Learning with Preference Human Feedback
Everyday Object Meets Vision-and-Language Navigation Agent via Backdoor
3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability
DeBaRA: Denoising-Based 3D Room Arrangement Generation
Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context
MIDGArD: Modular Interpretable Diffusion over Graphs for Articulated Designs
Distributed Least Squares in Small Space via Sketching and Bias Reduction
Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator
FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets
Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting
OTTER: Effortless Label Distribution Adaptation of Zero-shot Models
T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback
Symbolic Regression with a Learned Concept Library
Generative Modelling of Structurally Constrained Graphs
Conformalized Credal Set Predictors
A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization
Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning
Order-Independence Without Fine Tuning
Expressive Gaussian Human Avatars from Monocular RGB Video
AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation
OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations
Learning Versatile Skills with Curriculum Masking
TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes
A probability contrastive learning framework for 3D molecular representation learning
RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-Identification
Time Makes Space: Emergence of Place Fields in Networks Encoding Temporally Continuous Sensory Experiences
Achieving Constant Regret in Linear Markov Decision Processes
MMSite: A Multi-modal Framework for the Identification of Active Sites in Proteins
Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models
realSEUDO for real-time calcium imaging analysis
Online Non-convex Learning in Dynamic Environments
Questioning the Survey Responses of Large Language Models
GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling
Differentially Private Set Representations
Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following
How do Large Language Models Handle Multilingualism?
Color-Oriented Redundancy Reduction in Dataset Distillation
Selective Attention: Enhancing Transformer through Principled Context Control
Trade-Offs of Diagonal Fisher Information Matrix Estimators
CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions
OccFusion: Rendering Occluded Humans with Generative Diffusion Priors
Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators
Barely Random Algorithms and Collective Metrical Task Systems
Bias Amplification in Language Model Evolution: An Iterated Learning Perspective
SSA-Seg: Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentation
Even Sparser Graph Transformers
Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
Improved Sample Complexity for Multiclass PAC Learning
Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators
SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models
Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization
Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR
Conditioning non-linear and infinite-dimensional diffusion processes
Long-form factuality in large language models
Scale Equivariant Graph Metanetworks
Shape analysis for time series
Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks
GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs
SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion
Breaking the curse of dimensionality in structured density estimation
Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation
An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding
Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens
Protein-Nucleic Acid Complex Modeling with Frame Averaging Transformer
Contrastive dimension reduction: when and how?
Large Pre-trained time series models for cross-domain Time series analysis tasks
FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
Improved Particle Approximation Error for Mean Field Neural Networks
Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance
SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning
LLMs Can Evolve Continually on Modality for $\mathbb{X}$-Modal Reasoning
Deep Homomorphism Networks
Bridge-IF: Learning Inverse Protein Folding with Markov Bridges
Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift
Rejection via Learning Density Ratios
Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting
Similarity-Navigated Conformal Prediction for Graph Neural Networks
Treeffuser: probabilistic prediction via conditional diffusions with gradient-boosted trees
Discrete Flow Matching
On the Power of Decision Trees in Auto-Regressive Language Modeling
ReVideo: Remake a Video with Motion and Content Control
Navigating Chemical Space with Latent Flows
Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection
Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
Towards Learning Group-Equivariant Features for Domain Adaptive 3D Detection
Parameter Competition Balancing for Model Merging
Gorilla: Large Language Model Connected with Massive APIs
A Simple yet Universal Framework for Depth Completion
Learnability of high-dimensional targets by two-parameter models and gradient flow
Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis
Active Sequential Posterior Estimation for Sample-Efficient Simulation-Based Inference
KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization
The surprising efficiency of temporal difference learning for rare event prediction
Interpret Your Decision: Logical Reasoning Regularization for Generalization in Visual Classification
Human Expertise in Algorithmic Prediction
Self-Play Fine-tuning of Diffusion Models for Text-to-image Generation
Are nuclear masks all you need for improved out-of-domain generalisation? A closer look at cancer classification in histopathology
Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension
NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory
SparseLLM: Towards Global Pruning of Pre-trained Language Models
Smoothie: Label Free Language Model Routing
Finding Transformer Circuits With Edge Pruning
Learning Better Representations From Less Data For Propositional Satisfiability
Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting
Semidefinite Relaxations of the Gromov-Wasserstein Distance
Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation
Bigger, Regularized, Optimistic: scaling for compute and sample efficient continuous control
ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restoration
Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
Asymptotics of Alpha-Divergence Variational Inference Algorithms with Exponential Families
Probabilistic Conformal Distillation for Enhancing Missing Modality Robustness
Model Based Inference of Synaptic Plasticity Rules
Data Augmentation with Diffusion for Open-Set Semi-Supervised Learning
Most Influential Subset Selection: Challenges, Promises, and Beyond
Score Distillation via Reparametrized DDIM
Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
FouRA: Fourier Low-Rank Adaptation
The Fairness-Quality Tradeoff in Clustering
Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference
AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario
MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making
Data-Efficient Learning with Neural Programs
Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems
Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generation
Language Model as Visual Explainer
No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO
REBEL: Reinforcement Learning via Regressing Relative Rewards
Synthesize, Partition, then Adapt: Eliciting Diverse Samples from Foundation Models
Efficient multi-prompt evaluation of LLMs
Neural Network Reparametrization for Accelerated Optimization in Molecular Simulations
Decision-Focused Learning with Directional Gradients
Graph Diffusion Policy Optimization
Learning to compute Gröbner bases
Partial Transportability for Domain Generalization
Robust Mixture Learning when Outliers Overwhelm Small Groups
How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers
Improving self-training under distribution shifts via anchored confidence with theoretical guarantees
Do Finetti: On Causal Effects for Exchangeable Data
DEPrune: Depth-wise Separable Convolution Pruning for Maximizing GPU Parallelism
Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations
DiffPO: A causal diffusion model for learning distributions of potential outcomes
Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization
Aligning LLM Agents by Learning Latent Preference from User Edits
Provably Efficient Interactive-Grounded Learning with Personalized Reward
Structured Unrestricted-Rank Matrices for Parameter Efficient Finetuning
The Prevalence of Neural Collapse in Neural Multivariate Regression
In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization
GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules
S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training
Slot State Space Models
Online Consistency of the Nearest Neighbor Rule
Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
Fully Explicit Dynamic Gaussian Splatting
Interpretable Generalized Additive Models for Datasets with Missing Values
Continual Learning with Global Alignment
MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers
Time-Constrained Robust MDPs
Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces
Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Space
Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
Diffusion Models are Certifiably Robust Classifiers
Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention
Causal Imitation for Markov Decision Processes: a Partial Identification Approach
Noisy Label Learning with Instance-Dependent Outliers: Identifiability via Crowd Wisdom
Symmetries in Overparametrized Neural Networks: A Mean Field View
Identifying Causal Effects Under Functional Dependencies
MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems
Unlocking the Potential of Global Human Expertise
Adaptive Exploration for Data-Efficient General Value Function Evaluations
Recursive Introspection: Teaching Language Model Agents How to Self-Improve
Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL
Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight
Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?
Bayesian Adaptive Calibration and Optimal Design
Contrastive losses as generalized models of global epistasis
Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity
Consistency of Neural Causal Partial Identification
Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models
Revisiting Ensembling in One-Shot Federated Learning
Foundations of Multivariate Distributional Reinforcement Learning
Generative Fractional Diffusion Models
Reward Machines for Deep RL in Noisy and Uncertain Environments
Linear Time Approximation Algorithm for Column Subset Selection with Local Search
Activation Map Compression through Tensor Decomposition for Deep Learning
Poisson Variational Autoencoder
SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model
Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codes
To Learn or Not to Learn, That is the Question — A Feature-Task Dual Learning Model of Perceptual Learning
Discovering Creative Behaviors through DUPLEX: Diverse Universal Features for Policy Exploration
Universal Sample Coding
Watermarking Makes Language Models Radioactive
MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
Learnability Matters: Active Learning for Video Captioning
AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks
Self-Guiding Exploration for Combinatorial Problems
First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs
Policy Learning from Tutorial Books via Understanding, Rehearsing and Introspecting
Testing Calibration in Nearly-Linear Time
Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf
Learning the Expected Core of Strictly Convex Stochastic Cooperative Games
ChronoEpilogi: Scalable Time Series Selection with Multiple Solutions
Learning Goal-Conditioned Representations for Language Reward Models
Linear Transformers are Versatile In-Context Learners
Efficient Multi-task Reinforcement Learning with Cross-Task Policy Guidance
Are Language Models Actually Useful for Time Series Forecasting?
Stress-Testing Capability Elicitation With Password-Locked Models
Cell ontology guided transcriptome foundation model
Distributionally Robust Performative Prediction
Optimal Multiclass U-Calibration Error and Beyond
Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations
The Implicit Bias of Gradient Descent on Separable Multiclass Data
TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation
Robust Gaussian Processes via Relevance Pursuit
Understanding and Minimising Outlier Features in Transformer Training
Near-Optimal Distributionally Robust Reinforcement Learning with General $L_p$ Norms
COLD: Causal reasOning in cLosed Daily activities
Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms
Online Budgeted Matching with General Bids
Loki: Low-rank Keys for Efficient Sparse Attention
A Metalearned Neural Circuit for Nonparametric Bayesian Inference
Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters
Unelicitable Backdoors via Cryptographic Transformer Circuits
Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
Computerized Adaptive Testing via Collaborative Ranking
LESS: Label-Efficient and Single-Stage Referring 3D Segmentation
Mixture of Nested Experts: Adaptive Processing of Visual Tokens
Skinned Motion Retargeting with Dense Geometric Interaction Perception
Handling Learnwares from Heterogeneous Feature Spaces with Explicit Label Exploitation
Sample Complexity of Interventional Causal Representation Learning
Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios
Categorical Flow Matching on Statistical Manifolds
Queueing Matching Bandits with Preference Feedback
Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space
Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering
DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge
Towards Calibrated Robust Fine-Tuning of Vision-Language Models
SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout
DarkSAM: Fooling Segment Anything Model to Segment Nothing
Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signals
Schrodinger Bridge Flow for Unpaired Data Translation
SimPO: Simple Preference Optimization with a Reference-Free Reward
Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
The Representation Landscape of Few-Shot Learning and Fine-Tuning in Large Language Models
Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification
Learning Diffusion Priors from Observations by Expectation Maximization
Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox
Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)
On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection
On the Efficiency of ERM in Feature Learning
Policy Aggregation
Face2QR: A Unified Framework for Aesthetic, Face-Preserving, and Scannable QR Code Generation
Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking
Diffusion for World Modeling: Visual Details Matter in Atari
WeiPer: OOD Detection using Weight Perturbations of Class Projections
Facilitating Multimodal Classification via Dynamically Learning Modality Gap
Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration
Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators
AlterMOMA: Fusion Redundancy Pruning for Camera-LiDAR Fusion Models with Alternative Modality Masking
CountGD: Multi-Modal Open-World Counting
The Dormant Neuron Phenomenon in Multi-Agent Reinforcement Learning Value Factorization
When is an Embedding Model More Promising than Another?
Reinforcing LLM Agents via Policy Optimization with Action Decomposition
UDC: A Unified Neural Divide-and-Conquer Framework for Large-Scale Combinatorial Optimization Problems
Extending Video Masked Autoencoders to 128 frames
Spectral Learning of Shared Dynamics Between Generalized-Linear Processes
Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction
xLSTM: Extended Long Short-Term Memory
An Analytical Study of Utility Functions in Multi-Objective Reinforcement Learning
Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation
Towards Efficient and Optimal Covariance-Adaptive Algorithms for Combinatorial Semi-Bandits
Kermut: Composite kernel regression for protein variant effects
Factorized Diffusion Architectures for Unsupervised Image Generation and Segmentation
$SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation
On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice
P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics
Accuracy is Not All You Need
CoSW: Conditional Sample Weighting for Smoke Segmentation with Label Noise
SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
Exploiting LLM Quantization
Are Graph Neural Networks Optimal Approximation Algorithms?
Hierarchical Programmatic Option Framework
Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks
Gradient Methods for Online DR-Submodular Maximization with Stochastic Long-Term Constraints
SGD vs GD: Rank Deficiency in Linear Networks
Physics-Informed Variational State-Space Gaussian Processes
Coherent 3D Scene Diffusion From a Single RGB Image
Multi-Agent Domain Calibration with a Handful of Offline Data
Probabilistic size-and-shape functional mixed models
Soft Superpixel Neighborhood Attention
FINALLY: fast and universal speech enhancement with studio-like quality
Active preference learning for ordering items in- and out-of-sample
You Don’t Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning
Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors
Constrained Diffusion Models via Dual Training
The Many Faces of Optimal Weak-to-Strong Learning
Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing
Diffusion of Thought: Chain-of-Thought Reasoning in Diffusion Language Models
HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data
Harnessing Multiple Correlated Networks for Exact Community Recovery
HYDRA: Model Factorization Framework for Black-Box LLM Personalization
Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics
MTGS: A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze Prediction
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
MetaCURL: Non-stationary Concave Utility Reinforcement Learning
YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals
Amortized Eigendecomposition for Neural Networks
What do Graph Neural Networks learn? Insights from Tropical Geometry
Diffusion Twigs with Loop Guidance for Conditional Graph Generation
Moving Off-the-Grid: Scene-Grounded Video Representations
Be Confident in What You Know: Bayesian Parameter Efficient Fine-Tuning of Vision Foundation Models
Certified Adversarial Robustness via Randomized $\alpha$-Smoothing for Regression Models
Interventional Causal Discovery in a Mixture of DAGs
Virtual Scanning: Unsupervised Non-line-of-sight Imaging from Irregularly Undersampled Transients
On the Limitations of Fractal Dimension as a Measure of Generalization
Memorize What Matters: Emergent Scene Decomposition from Multitraverse
Unified Covariate Adjustment for Causal Inference
Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation
Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba
Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit
Designing Cell-Type-Specific Promoter Sequences Using Conservative Model-Based Optimization
Flexible task abstractions emerge in linear networks with fast and bounded units
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
Efficient Policy Evaluation Across Multiple Different Experimental Datasets
Complete Graphical Criterion for Sequential Covariate Adjustment in Causal Inference
On the Adversarial Robustness of Benjamini Hochberg
Optimal Parallelization of Boosting
From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization
Global Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers
Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes
Graphcode: Learning from multiparameter persistent homology using graph neural networks
Sample-efficient Bayesian Optimisation Using Known Invariances
ProtGO: Function-Guided Protein Modeling for Unified Representation Learning
SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning
Attention Temperature Matters in ViT-Based Cross-Domain Few-Shot Learning
Improved Regret of Linear Ensemble Sampling
Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series
TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives
DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data
Validating Climate Models with Spherical Convolutional Wasserstein Distance
Unifying Generation and Prediction on Graphs with Latent Graph Diffusion
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
Transformers on Markov data: Constant depth suffices
Simulation-Free Training of Neural ODEs on Paired Data
PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
Disentangling the Roles of Distinct Cell Classes with Cell-Type Dynamical Systems
Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient
SceneCraft: Layout-Guided 3D Scene Generation
NeuralFluid: Nueral Fluidic System Design and Control with Differentiable Simulation
AutoMix: Automatically Mixing Language Models
MeMo: Meaningful, Modular Controllers via Noise Injection
BAKU: An Efficient Transformer for Multi-Task Policy Learning
I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token
FasMe: Fast and Sample-efficient Meta Estimator for Precision Matrix Learning in Small Sample Settings
Plant-and-Steal: Truthful Fair Allocations via Predictions
Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities
Elliptical Attention
Wide Two-Layer Networks can Learn from Adversarial Perturbations
ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Driving
EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models
Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time
SPEAR: Exact Gradient Inversion of Batches in Federated Learning
Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning
PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyond
Why Transformers Need Adam: A Hessian Perspective
Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees
Neural Model Checking
SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
Temporal Sentence Grounding with Relevance Feedback in Videos
Localized Zeroth-Order Prompt Optimization
UV-free Texture Generation with Denoising and Geodesic Heat Diffusion
Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication
Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Scary
How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?
Learning Transferable Features for Implicit Neural Representations
DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning
MotionTTT: 2D Test-Time-Training Motion Estimation for 3D Motion Corrected MRI
Monoculture in Matching Markets
Improving Environment Novelty Quantification for Effective Unsupervised Environment Design
TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight
Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness
BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
Euclidean distance compression via deep random features
Tight Bounds for Learning RUMs from Small Slates
Abductive Reasoning in Logical Credal Networks
Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)
DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment
Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
Exploring the Precise Dynamics of Single-Layer GAN Models: Leveraging Multi-Feature Discriminators for High-Dimensional Subspace Learning
Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inference
Structured flexibility in recurrent neural networks via neuromodulation
Scalable DP-SGD: Shuffling vs. Poisson Subsampling
Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments
End-to-End Ontology Learning with Large Language Models
Large Language Models Must Be Taught to Know What They Don’t Know
Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling
Aligning Diffusion Models by Optimizing Human Utility
SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models
Distributional Successor Features Enable Zero-Shot Policy Optimization
Sample-Efficient Private Learning of Mixtures of Gaussians
Referring Human Pose and Mask Estimation In the Wild
Unraveling the Gradient Descent Dynamics of Transformers
Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn
Simplifying Constraint Inference with Inverse Reinforcement Learning
GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats
Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment
MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting
Nonparametric Evaluation of Noisy ICA Solutions
Transfer Learning for Latent Variable Network Models
On Differentially Private U Statistics
Your contrastive learning problem is secretly a distribution alignment problem
DiffuBox: Refining 3D Object Detection with Point Diffusion
GOMAA-Geo: GOal Modality Agnostic Active Geo-localization
MILP-StuDio: MILP Instance Generation via Block Structure Decomposition
Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions
No Free Lunch Theorem and Black-Box Complexity Analysis for Adversarial Optimisation
Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priors
A Simple Framework for Generalization in Visual RL under Dynamic Scene Perturbations
xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
Federated Ensemble-Directed Offline Reinforcement Learning
OSLO: One-Shot Label-Only Membership Inference Attacks
Optimal Top-Two Method for Best Arm Identification and Fluid Analysis
MVSDet: Multi-View Indoor 3D Object Detection via Efficient Plane Sweeps
X-Ray: A Sequential 3D Representation For Generation
Learning to Decouple the Lights for 3D Face Texture Modeling
Learning Group Actions on Latent Representations
Few-Shot Task Learning through Inverse Generative Modeling
Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
Physically Compatible 3D Object Modeling from a Single Image
Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space
Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers
Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms
Learning to Cooperate with Humans using Generative Agents
LLM-Check: Investigating Detection of Hallucinations in Large Language Models
Constrained Synthesis with Projected Diffusion Models
Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data Coverage
KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge
Divergences between Language Models and Human Brains
ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
Gradient Rewiring for Editable Graph Neural Network Training
Alignment for Honesty
Dissect Black Box: Interpreting for Rule-Based Explanations in Unsupervised Anomaly Detection
MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures
$\textit{Read-ME}$: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
Optimization Can Learn Johnson Lindenstrauss Embeddings
Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties
No Free Delivery Service: Epistemic limits of passive data collection in complex social systems
Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos
Retrieval & Fine-Tuning for In-Context Tabular Models
Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale
CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming
Disentangled Representation Learning in Non-Markovian Causal Systems
Capturing the denoising effect of PCA via compression ratio
Novel Object Synthesis via Adaptive Text-Image Harmony
Maia-2: A Unified Model for Human-AI Alignment in Chess
FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training
Identifying Selections for Unsupervised Subtask Discovery
SAMPa: Sharpness-aware Minimization Parallelized
Normalization and effective learning rates in reinforcement learning
LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling
Scale-invariant Optimal Sampling for Rare-events Data and Sparse Models
Gradient-Variation Online Learning under Generalized Smoothness
Off-policy estimation with adaptively collected data: the power of online learning
TrAct: Making First-layer Pre-Activations Trainable
Convolutional Differentiable Logic Gate Networks
PointMamba: A Simple State Space Model for Point Cloud Analysis
Light Unbalanced Optimal Transport
Scaling Law for Time Series Forecasting
DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ
Splatter a Video: Video Gaussian Representation for Versatile Processing
Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
Selective Generation for Controllable Language Models
Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games
Adaptive Depth Networks with Skippable Sub-Paths
Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations
Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability, Reproducibility, and Practicality
Promoting Fairness Among Dynamic Agents in Online-Matching Markets under Known Stationary Arrival Distributions
Quantum algorithm for large-scale market equilibrium computation
On conditional diffusion models for PDE simulations
PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation
When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL
Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
GFT: Graph Foundation Model with Transferable Tree Vocabulary
IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors
Adversarial Moment-Matching Distillation of Large Language Models
Provable Tempered Overfitting of Minimal Nets and Typical Nets
ScaleKD: Strong Vision Transformers Could Be Excellent Teachers
Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
Non-parametric classification via expand-and-sparsify representation
Sourcerer: Sample-based Maximum Entropy Source Distribution Estimation
Learning Complete Protein Representation by Dynamically Coupling of Sequence and Structure
Neural collapse vs. low-rank bias: Is deep neural collapse really optimal?
ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models
Accelerating Non-Maximum Suppression: A Graph Theory Perspective
Crafting Interpretable Embeddings for Language Neuroscience by Asking LLMs Questions
Latent Diffusion for Neural Spiking Data
Private and Personalized Frequency Estimation in a Federated Setting
Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling
Confidence Regulation Neurons in Language Models
Accelerating Matroid Optimization through Fast Imprecise Oracles
Score-Optimal Diffusion Schedules
3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration
TSDS: Data Selection for Task-Specific Model Finetuning
Maximizing utility in multi-agent environments by anticipating the behavior of other learners
Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random
On the Stability and Generalization of Meta-Learning
Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
AdaNovo: Towards Robust \emph{De Novo} Peptide Sequencing in Proteomics against Data Biases
Adversarially Robust Multi-task Representation Learning
Offline Multitask Representation Learning for Reinforcement Learning
No-Regret Learning for Fair Multi-Agent Social Welfare Optimization
Risk-Averse Fine-tuning of Large Language Models
Geometry-aware training of factorized layers in tensor Tucker format
Polynomial-Time Computation of Exact $\Phi$-Equilibria in Polyhedral Games
Unleashing Region Understanding in Intermediate Layers for MLLM-based Referring Expression Generation
A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images
Uncertainty-aware Fine-tuning of Segmentation Foundation Models
MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Step
Episodic Future Thinking Mechanism for Multi-agent Reinforcement Learning
TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control
Continual Learning in the Frequency Domain
Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control
GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration
Metric Transforms and Low Rank Representations of Kernels for Fast Attention
Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity
Are Multiple Instance Learning Algorithms Learnable for Instances?
FactorSim: Generative Simulation via Factorized Representation
Autoregressive Image Generation without Vector Quantization
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
Data Free Backdoor Attacks
ConStat: Performance-Based Contamination Detection in Large Language Models
Graph Convolutions Enrich the Self-Attention in Transformers!
PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics
Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
LT-Defense: Searching-free Backdoor Defense via Exploiting the Long-tailed Effect
A Theoretical Understanding of Self-Correction through In-context Alignment
Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data
Stratified Prediction-Powered Inference for Effective Hybrid Evaluation of Language Models
A Neural Network Approach for Efficiently Answering Most Probable Explanation Queries in Probabilistic Models
Proving Theorems Recursively
No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery
Probing the Decision Boundaries of In-context Learning in Large Language Models
2D-OOB: Attributing Data Contribution Through Joint Valuation Framework
Provably Safe Neural Network Controllers via Differential Dynamic Logic
DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction
Unsupervised Discovery of Formulas for Mathematical Constants
Towards the Dynamics of a DNN Learning Symbolic Interactions
A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention
Coded Computing for Resilient Distributed Computing: A Learning-Theoretic Framework
Fast Channel Simulation via Error-Correcting Codes
Alignment at Pre-training! Towards Native Alignment for Arabic LLMs
Few-Shot Diffusion Models Escape the Curse of Dimensionality
The ALCHEmist: Automated Labeling 500x CHEaper than LLM Data Annotators
AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers
Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases
DMesh: A Differentiable Mesh Representation
SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training
FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making
Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction
Compact Proofs of Model Performance via Mechanistic Interpretability
Continual learning with the neural tangent ensemble
Do causal predictors generalize better to new domains?
Revisiting Score Propagation in Graph Out-of-Distribution Detection
Unrolled denoising networks provably learn to perform optimal Bayesian inference
DeNetDM: Debiasing by Network Depth Modulation
Ad Auctions for LLMs via Retrieval Augmented Generation
Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models
User-Creator Feature Polarization in Recommender Systems with Dual Influence
Pard: Permutation-Invariant Autoregressive Diffusion for Graph Generation
KALM: Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts
High-Resolution Image Harmonization with Adaptive-Interval Color Transformation
Generating Origin-Destination Matrices in Neural Spatial Interaction Models
Contextual Active Model Selection
On the Identifiability of Poisson Branching Structural Causal Model Using Probability Generating Function
FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning
InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint
QGFN: Controllable Greediness with Action Values
Learning Structured Representations with Hyperbolic Embeddings
Cost-aware Bayesian Optimization via the Pandora's Box Gittins Index
Generalization Analysis for Label-Specific Representation Learning
Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
Probabilistic Graph Rewiring via Virtual Nodes
A Bayesian Approach to Data Point Selection
Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured training
Slight Corruption in Pre-training Data Makes Better Diffusion Models
Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
Enhancing Large Vision Language Models with Self-Training on Image Comprehension
A scalable generative model for dynamical system reconstruction from neuroimaging data
UniDSeg: Unified Cross-Domain 3D Semantic Segmentation via Visual Foundation Models Prior
AdjointDEIS: Efficient Gradients for Diffusion Models
MonkeySee: Space-time-resolved reconstructions of natural images from macaque multi-unit activity
Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data
Understanding Transformers via N-Gram Statistics
BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO
Truth is Universal: Robust Detection of Lies in LLMs
How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad
A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embedding
Analysing the Generalisation and Reliability of Steering Vectors
Trajectory Diffusion for ObjectGoal Navigation
Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin Walk
Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
Mixture of Tokens: Continuous MoE through Cross-Example Aggregation
Parametric model reduction of mean-field and stochastic systems via higher-order action matching
Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective
Induced Model Matching: Restricted Models Help Train Full-Featured Models
Fast Best-of-N Decoding via Speculative Rejection
Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance
CultureLLM: Incorporating Cultural Differences into Large Language Models
CulturePark: Boosting Cross-cultural Understanding in Large Language Models
No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests
Multi-Object Hallucination in Vision Language Models
Bridge the Points: Graph-based Few-shot Segment Anything Semantically
Learning from Snapshots of Discrete and Continuous Data Streams
Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis
Tangent Space Causal Inference: Leveraging Vector Fields for Causal Discovery in Dynamical Systems
The Impact of Geometric Complexity on Neural Collapse in Transfer Learning
Polyhedral Complex Derivation from Piecewise Trilinear Networks
The Road Less Scheduled
Directional Smoothness and Gradient Methods: Convergence and Adaptivity
Learning to be Smooth: An End-to-End Differentiable Particle Smoother
Multi-view Masked Contrastive Representation Learning for Endoscopic Video Analysis
CryoSPIN: Improving Ab-Initio Cryo-EM Reconstruction with Semi-Amortized Pose Inference
Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification
Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input
ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier
A Polar coordinate system represents syntax in large language models
FedNE: Surrogate-Assisted Federated Neighbor Embedding for Dimensionality Reduction
DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation
Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems
Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model
L-TTA: Lightweight Test-Time Adaptation Using a Versatile Stem Layer
Motif-oriented influence maximization for viral marketing in large-scale social networks
Out-Of-Distribution Detection with Diversification (Provably)
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning
An Efficient High-dimensional Gradient Estimator for Stochastic Differential Equations
SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection
SongCreator: Lyrics-based Universal Song Generation
Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling
The Star Geometry of Critic-Based Regularizer Learning
A Recipe for Charge Density Prediction
Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation
Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents
Unified Guidance for Geometry-Conditioned Molecular Generation
Federated Learning over Connected Modes
Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain
B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory
How does PDE order affect the convergence of PINNs?
A Unifying Normative Framework of Decision Confidence
Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning
ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models
DisenGCD: A Meta Multigraph-assisted Disentangled Graph Learning Framework for Cognitive Diagnosis
Sequential Harmful Shift Detection Without Labels
RashomonGB: Analyzing the Rashomon Effect and Mitigating Predictive Multiplicity in Gradient Boosting
CoSy: Evaluating Textual Explanations of Neurons
$\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning
Efficient Large Multi-modal Models via Visual Context Compression
Mutual Information Estimation via Normalizing Flows
LLM-based Skill Diffusion for Zero-shot Policy Adaptation
A Universal Growth Rate for Learning with Smooth Surrogate Losses
Cardinality-Aware Set Prediction and Top-$k$ Classification
RTify: Aligning Deep Neural Networks with Human Behavioral Decisions
A Simple and Optimal Approach for Universal Online Learning with Gradient Variations
Universal Online Convex Optimization with $1$ Projection per Round
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
Exploring Molecular Pretraining Model at Scale
The Limits of Differential Privacy in Online Learning
Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
Empowering Active Learning for 3D Molecular Graphs with Geometric Graph Isomorphism
Harnessing small projectors and multiple views for efficient vision pretraining
On the Noise Robustness of In-Context Learning for Text Generation
ALPINE: Unveiling The Planning Capability of Autoregressive Learning in Language Models
AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning
Rethinking Optimal Transport in Offline Reinforcement Learning
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
Improving Temporal Link Prediction via Temporal Walk Matrix Projection
Bootstrapping Top-down Information for Self-modulating Slot Attention
Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies
Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data
Worst-Case Offline Reinforcement Learning with Arbitrary Data Support
SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data
Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization
Optimal Hypothesis Selection in (Almost) Linear Time
Strategic Linear Contextual Bandits
Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
Mitigating Biases in Blackbox Feature Extractors for Image Classification Tasks
Self-Distilled Depth Refinement with Noisy Poisson Fusion
Tackling Uncertain Correspondences for Multi-Modal Entity Alignment
Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs
Single Image Reflection Separation via Dual-Stream Interactive Transformers
Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models
GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation
Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity
Causal vs. Anticausal merging of predictors
Model Collapse Demystified: The Case of Regression
4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization
Text-Aware Diffusion for Policy Learning
Multi-scale Consistency for Robust 3D Registration via Hierarchical Sinkhorn Tree
Motion Graph Unleashed: A Novel Approach to Video Prediction
On the Role of Attention Masks and LayerNorm in Transformers
Simplified and Generalized Masked Diffusion for Discrete Data
Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents
StepbaQ: Stepping backward as Correction for Quantized Diffusion Models
Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms
NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
Communication Efficient Distributed Training with Distributed Lion
ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction
MiSO: Optimizing brain stimulation to create neural activity states
Integrating GNN and Neural ODEs for Estimating Non-Reciprocal Two-Body Interactions in Mixed-Species Collective Motion
Lookback Prophet Inequalities
From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $\alpha$-NeuS
Learning-Augmented Priority Queues
Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training
Unconditional stability of a recurrent neural circuit implementing divisive normalization
MotionBooth: Motion-Aware Customized Text-to-Video Generation
Credal Deep Ensembles for Uncertainty Quantification
Embedding Dimension of Contrastive Learning and $k$-Nearest Neighbors
Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective
IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering
GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping
FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
Learning predictable and robust neural representations by straightening image sequences
SafeWorld: Geo-Diverse Safety Alignment
Taming the Long Tail in Human Mobility Prediction
Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
Disentangling Interpretable Factors with Supervised Independent Subspace Principal Component Analysis
Fair Wasserstein Coresets
Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model
UNIT: Unifying Image and Text Recognition in One Vision Encoder
VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation
Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective
Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training
BitDelta: Your Fine-Tune May Only Be Worth One Bit
Microstructures and Accuracy of Graph Recall by Large Language Models
Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
Sample-Efficient Agnostic Boosting
Vision Mamba Mender
Ask, Attend, Attack: An Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models
Adaptive Proximal Gradient Method for Convex Optimization
EnsIR: An Ensemble Algorithm for Image Restoration via Gaussian Mixture Models
Nesterov acceleration despite very noisy gradients
Graph Structure Inference with BAM: Neural Dependency Processing via Bilinear Attention
Can Transformers Smell Like Humans?
Contrastive-Equivariant Self-Supervised Learning Improves Alignment with Primate Visual Area IT
Adaptive Labeling for Efficient Out-of-distribution Model Evaluation
Training for Stable Explanation for Free
DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging
Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation
Data Distribution Valuation
FastDrag: Manipulate Anything in One Step
Online Posterior Sampling with a Diffusion Prior
DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut
$\text{ID}^3$: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition
Quadratic Quantum Variational Monte Carlo
AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies
Scalable and Effective Arithmetic Tree Generation for Adder and Multiplier Designs
LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
Improving Equivariant Model Training via Constraint Relaxation
Evidential Stochastic Differential Equations for Time-Aware Sequential Recommendation
Enhancing Protein Mutation Effect Prediction through a Retrieval-Augmented Framework
Amortized Fourier Neural Operators
Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
Advancing Spiking Neural Networks for Sequential Modeling with Central Pattern Generators
Predicting Ground State Properties: Constant Sample Complexity and Deep Learning Algorithms
LRM-Zero: Training Large Reconstruction Models with Synthesized Data
PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference
Leveraging Tumor Heterogeneity: Heterogeneous Graph Representation Learning for Cancer Survival Prediction in Whole Slide Images
Causal Effect Identification in a Sub-Population with Latent Variables
Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery
Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference
Inversion-based Latent Bayesian Optimization
EigenVI: score-based variational inference with orthogonal function expansions
Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities
Truthfulness of Calibration Measures
FineStyle: Fine-grained Controllable Style Personalization for Text-to-image Models
OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learning
Achievable distributional robustness when the robust risk is only partially identified
Optimal Private and Communication Constraint Distributed Goodness-of-Fit Testing for Discrete Distributions in the Large Sample Regime
Bandits with Abstention under Expert Advice
Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting
The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
Computational Aspects of Bayesian Persuasion under Approximate Best Response
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
3D Gaussian Rendering Can Be Sparser: Efficient Rendering via Learned Fragment Pruning
Score-based generative models are provably robust: an uncertainty quantification perspective
AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment
A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation
Listenable Maps for Zero-Shot Audio Classifiers
BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
Online Iterative Reinforcement Learning from Human Feedback with General Preference Model
Dueling over Dessert, Mastering the Art of Repeated Cake Cutting
Provable Posterior Sampling with Denoising Oracles via Tilted Transport
NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention
A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation
Self-Supervised Adversarial Training via Diverse Augmented Queries and Self-Supervised Double Perturbation
Nonparametric Instrumental Variable Regression through Stochastic Approximate Gradients
Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand
Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits
Sample Efficient Bayesian Learning of Causal Graphs from Interventions
Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning
Efficient and Private Marginal Reconstruction with Local Non-Negativity
MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization
Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE
Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation
Learning Infinitesimal Generators of Continuous Symmetries from Data
CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics
Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks
Personalized Federated Learning with Mixture of Models for Adaptive Prediction and Model Fine-Tuning
On the Identifiability of Hybrid Deep Generative Models: Meta-Learning as a Solution
FairWire: Fair Graph Generation
Does Egalitarian Fairness Lead to Instability? The Fairness Bounds in Stable Federated Learning Under Altruistic Behaviors
Multi-model Ensemble Conformal Prediction in Dynamic Environments
SPO: Sequential Monte Carlo Policy Optimisation
Membership Inference Attacks against Large Vision-Language Models
Sample-Efficient Geometry Reconstruction from Euclidean Distances using Non-Convex Optimization
Causal Dependence Plots
LoCo: Learning 3D Location-Consistent Image Features with a Memory-Efficient Ranking Loss
FlexCap: Describe Anything in Images in Controllable Detail
Sequoia: Scalable and Robust Speculative Decoding
Blind Image Restoration via Fast Diffusion Inversion
A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints
MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes
Diffusion Models With Learned Adaptive Noise
LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
Generalizing CNNs to graphs with learnable neighborhood quantization
Bayesian Online Natural Gradient (BONG)
Just Add $100 More: Augmenting Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem
Mixture of neural fields for heterogeneous reconstruction in cryo-EM
Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutions
Policy Mirror Descent with Lookahead
AV-Cloud: Spatial Audio Rendering Through Audio-Visual Cloud Splatting
Self-Calibrating Conformal Prediction
Dual Lagrangian Learning for Conic Optimization
ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence
Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks
Fair GLASSO: Estimating Fair Graphical Models with Unbiased Statistical Behavior
State-free Reinforcement Learning
CosAE: Learnable Fourier Series for Image Restoration
Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
Practical Shuffle Coding
Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithm
A Fast Convoluted Story: Scaling Probabilistic Inference for Integer Arithmetics
Evaluating the design space of diffusion-based generative models
Learn To be Efficient: Build Structured Sparsity in Large Language Models
On the Optimality of Dilated Entropy and Lower Bounds for Online Learning in Extensive-Form Games
Preference Learning of Latent Decision Utilities with a Human-like Model of Preferential Choice
Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization
Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
Diffusing Differentiable Representations
Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
Understanding Hallucinations in Diffusion Models through Mode Interpolation
Predicting the Performance of Foundation Models via Agreement-on-the-Line
Improving Alignment and Robustness with Circuit Breakers
DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation
Language-Driven Interactive Traffic Trajectory Generation
Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
Graph Classification via Reference Distribution Learning: Theory and Practice
HOPE: Shape Matching Via Aligning Different K-hop Neighbourhoods
Reparameterization invariance in approximate Bayesian inference
Drones Help Drones: A Collaborative Framework for Multi-Drone Object Trajectory Prediction and Beyond
G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models
You Only Cache Once: Decoder-Decoder Architectures for Language Models
Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights
Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos
Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection
Not Just Object, But State: Compositional Incremental Learning without Forgetting
Learning from Noisy Labels via Conditional Distributionally Robust Optimization
Globally Q-linear Gauss-Newton Method for Overparameterized Non-convex Matrix Sensing
DiffuserLite: Towards Real-time Diffusion Planning
Overcoming Common Flaws in the Evaluation of Selective Classification Systems
Dendritic Integration Inspired Artificial Neural Networks Capture Data Correlation
Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model
From Similarity to Superiority: Channel Clustering for Time Series Forecasting
When Is Inductive Inference Possible?
Weight Diffusion for Future: Learn to Generalize in Non-Stationary Environments
Active learning of neural population dynamics using two-photon holographic optogenetics
Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems
Quantitative Convergences of Lie Group Momentum Optimizers
Multi-language Diversity Benefits Autoformalization
DEL: Discrete Element Learner for Learning 3D Particle Dynamics with Neural Rendering
Externally Valid Policy Evaluation from Randomized Trials Using Additional Observational Data
Towards Understanding Extrapolation: a Causal Lens
Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning
Automated Efficient Estimation using Monte Carlo Efficient Influence Functions
Multidimensional Fractional Programming for Normalized Cuts
Instance-adaptive Zero-shot Chain-of-Thought Prompting
How Does Variance Shape the Regret in Contextual Bandits?
Aggregating Quantitative Relative Judgments: From Social Choice to Ranking Prediction
Towards Multi-dimensional Explanation Alignment for Medical Classification
On Tractable $\Phi$-Equilibria in Non-Concave Games
Enhancing Large Language Models through Adaptive Tokenizers
On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks
Stylus: Automatic Adapter Selection for Diffusion Models
Flexible Context-Driven Sensory Processing in Dynamical Vision Models
Generative Adversarial Model-Based Optimization via Source Critic Regularization
GS-Hider: Hiding Messages into 3D Gaussian Splatting
InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
Global Rewards in Restless Multi-Armed Bandits
EGonc : Energy-based Open-Set Node Classification with substitute Unknowns
Improving the Learning Capability of Small-size Image Restoration Network by Deep Fourier Shifting
SEA: State-Exchange Attention for High-Fidelity Physics Based Transformers
Topological obstruction to the training of shallow ReLU neural networks
Low Degree Hardness for Broadcasting on Trees
Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning
Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention
Fearless Stochasticity in Expectation Propagation
Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup
A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement Learning
SA3DIP: Segment Any 3D Instance with Potential 3D Priors
The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space
Higher-Order Causal Message Passing for Experimentation with Complex Interference
ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses
Expectile Regularization for Fast and Accurate Training of Neural Optimal Transport
Boundary Matters: A Bi-Level Active Finetuning Method
AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion Models
AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing
Slack-Free Spiking Neural Network Formulation for Hypergraph Minimum Vertex Cover
How Does Black-Box Impact the Learning Guarantee of Stochastic Compositional Optimization?
Towards Dynamic Message Passing on Graphs
Bias Detection via Signaling
Linear Regression using Heterogeneous Data Batches
Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classification
Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem
On the Complexity of Teaching a Family of Linear Behavior Cloning Learners
iVideoGPT: Interactive VideoGPTs are Scalable World Models
Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity
AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis
Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language Models
Real-Time Recurrent Learning using Trace Units in Reinforcement Learning
Dynamic Subgroup Identification in Covariate-adjusted Response-adaptive Randomization Experiments
Iterative Reasoning Preference Optimization
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
Chain-of-Thought Reasoning Without Prompting
A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise
AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation
What is my quantum computer good for? Quantum capability learning with physics-aware neural networks
Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers
DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning
MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning
Motion Forecasting in Continuous Driving
Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function
Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning
Seek Commonality but Preserve Differences: Dissected Dynamics Modeling for Multi-modal Visual RL
Verified Code Transpilation with LLMs
Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus
VFIMamba: Video Frame Interpolation with State Space Models
Regularized Q-Learning
DiTFastAttn: Attention Compression for Diffusion Transformer Models
Improving Context-Aware Preference Modeling for Language Models
Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution
TARSS-Net: Temporal-Aware Radar Semantic Segmentation Network
CausalStock: Deep End-to-end Causal Discovery for News-driven Multi-stock Movement Prediction
Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning
VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought
Minimizing UCB: a Better Local Search Strategy in Local Bayesian Optimization
Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
MG-Net: Learn to Customize QAOA with Circuit Depth Awareness
FIDE: Frequency-Inflated Conditional Diffusion Model for Extreme-Aware Time Series Generation
DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph
TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment
Efficient Centroid-Linkage Clustering
Deep Support Vectors
Toxicity Detection for Free
SIRIUS : Contexual Sparisty with Correction for Efficient LLMs
Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis
Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models
Verifiably Robust Conformal Prediction
Algorithmic progress in language models
Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication
One-shot Federated Learning via Synthetic Distiller-Distillate Communication
Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models
SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation
Locating What You Need: Towards Adapting Diffusion Models to OOD Concepts In-the-Wild
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks
Learning Discrete Latent Variable Structures with Tensor Rank Conditions
Open-Book Neural Algorithmic Reasoning
Separations in the Representational Capabilities of Transformers and Recurrent Architectures
S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity
ROIDICE: Offline Return on Investment Maximization for Efficient Decision Making
HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning
Why Go Full? Elevating Federated Learning Through Partial Network Updates
Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms
Robust Neural Contextual Bandit against Adversarial Corruptions
The Sample-Communication Complexity Trade-off in Federated Q-Learning
Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback
Graph neural networks and non-commuting operators
Diffusion Imitation from Observation
Universal Rates of Empirical Risk Minimization
Classifier Clustering and Feature Alignment for Federated Learning under Distributed Concept Drift
Transfer Learning for Diffusion Models
DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models
Sparse High Rank Adapters
Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach
Block Transformer: Global-to-Local Language Modeling for Fast Inference
Consensus Learning with Deep Sets for Essential Matrix Estimation
Learning symmetries via weight-sharing with doubly stochastic tensors
Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers
Fast Rates for Bandit PAC Multiclass Classification
Zero-Shot Reinforcement Learning from Low Quality Data
Is Your LiDAR Placement Optimized for 3D Scene Understanding?
Right this way: Can VLMs Guide Us to See More to Answer Questions?
Amortized Active Causal Induction with Deep Reinforcement Learning
Group and Shuffle: Efficient Structured Orthogonal Parametrization
Learning Place Cell Representations and Context-Dependent Remapping
Slot-VLM: Object-Event Slots for Video-Language Modeling
CALVIN: Improved Contextual Video Captioning via Instruction Tuning
Error Correction Output Codes for Robust Neural Networks against Weight-errors: A Neural Tangent Kernel Point of View
Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing
Learning Social Welfare Functions
Great Minds Think Alike: The Universal Convergence Trend of Input Salience
Meta-Learning Universal Priors Using Non-Injective Change of Variables
Doubly Mild Generalization for Offline Reinforcement Learning
Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality
Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes
Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning
Towards Harmless Rawlsian Fairness Regardless of Demographic Prior
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
Prediction-Powered Ranking of Large Language Models
Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models
Derivatives of Stochastic Gradient Descent in parametric optimization
Progressive Entropic Optimal Transport Solvers
Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms
Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration
Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels
Navigable Graphs for High-Dimensional Nearest Neighbor Search: Constructions and Limits
Invisible Image Watermarks Are Provably Removable Using Generative AI
Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformation
VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
DeltaDEQ: Exploiting Heterogeneous Convergence for Accelerating Deep Equilibrium Iterations
Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition
AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos
LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single Image
The Power of Resets in Online Reinforcement Learning
Flipping-based Policy for Chance-Constrained Markov Decision Processes
Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning
Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning
Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff
Spectral Graph Pruning Against Over-Squashing and Over-Smoothing
Approximately Pareto-optimal Solutions for Bi-Objective k-Clustering
Unified Insights: Harnessing Multi-modal Data for Phenotype Imputation via View Decoupling
Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization
Adjust Pearson's $r$ to Measure Arbitrary Monotone Dependence
On the Power of Small-size Graph Neural Networks for Linear Programming
Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning
Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level
Robust Reinforcement Learning with General Utility
Optimal and Approximate Adaptive Stochastic Quantization
NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing
Extensive-Form Game Solving via Blackwell Approachability on Treeplexes
EAI: Emotional Decision-Making of LLMs in Strategic Games and Ethical Dilemmas
Evaluating alignment between humans and neural network representations in image-based learning tasks
Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency
Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
Improving Neural Network Surface Processing with Principal Curvatures
Temporal-Difference Learning Using Distributed Error Signals
LLM Evaluators Recognize and Favor Their Own Generations
Conformalized Multiple Testing after Data-dependent Selection
Globally Convergent Variational Inference
Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs
Pearls from Pebbles: Improved Confidence Functions for Auto-labeling
Boosting Alignment for Post-Unlearning Text-to-Image Generative Models
RandNet-Parareal: a time-parallel PDE solver using Random Neural Networks
Noise-Aware Differentially Private Regression via Meta-Learning
Boosting Text-to-Video Generative Model with MLLMs Feedback
Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers
Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis
Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation
Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning
Optimization Algorithm Design via Electric Circuits
Aligning Model Properties via Conformal Risk Control
UMB: Understanding Model Behavior for Open-World Object Detection
Compact Language Models via Pruning and Knowledge Distillation
Context and Geometry Aware Voxel Transformer for Semantic Scene Completion
IPM-LSTM: A Learning-Based Interior Point Method for Solving Nonlinear Programs
Knowledge-Empowered Dynamic Graph Network for Irregularly Sampled Medical Time Series
Online Learning with Sublinear Best-Action Queries
Knowledge Circuits in Pretrained Transformers
Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory
UDPM: Upsampling Diffusion Probabilistic Models
Improving Subgroup Robustness via Data Selection
FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification
Attention boosted Individualized Regression
Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
Testing Semantic Importance via Betting
Optimal Transport-based Labor-free Text Prompt Modeling for Sketch Re-identification
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Label Delay in Online Continual Learning
Tensor-Based Synchronization and the Low-Rankness of the Block Trifocal Tensor
Vector Quantization Prompting for Continual Learning
TableRAG: Million-Token Table Understanding with Language Models
Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification
Feint Behaviors and Strategies: Formalization, Implementation and Evaluation
Credal Learning Theory
DEFT: Efficient Fine-tuning of Diffusion Models by Learning the Generalised $h$-transform
Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
Improving Neural ODE Training with Temporal Adaptive Batch Normalization
CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing
Optimal Batched Best Arm Identification
Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations
Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases
Causal Context Adjustment Loss for Learned Image Compression
Covariate Shift Corrected Conditional Randomization Test
Expanding Sparse Tuning for Low Memory Usage
SpelsNet: Surface Primitive Elements Segmentation by B-Rep Graph Structure Supervision
Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation
UQE: A Query Engine for Unstructured Databases
PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression
Learning Identifiable Factorized Causal Representations of Cellular Responses
Multi-Group Proportional Representation in Retrieval
Fair Secretaries with Unfair Predictions
Auditing Privacy Mechanisms via Label Inference Attacks
Robust and Faster Zeroth-Order Minimax Optimization: Complexity and Applications
Simple and Fast Distillation of Diffusion Models
Unsupervised Anomaly Detection in The Presence of Missing Values
Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss
NeuMA: Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics
Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate
DeformableTST: Transformer for Time Series Forecasting without Over-reliance on Patching
Matryoshka Query Transformer for Large Vision-Language Models
SLowcalSGD : Slow Query Points Improve Local-SGD for Stochastic Convex Optimization
Differentiable Structure Learning with Partial Orders
Towards Accurate and Fair Cognitive Diagnosis via Monotonic Data Augmentation
Genetic-guided GFlowNets for Sample Efficient Molecular Optimization
Optimizing the coalition gain in Online Auctions with Greedy Structured Bandits
Rethinking Fourier Transform from A Basis Functions Perspective for Long-term Time Series Forecasting
Toward Semantic Gaze Target Detection
BERTs are Generative In-Context Learners
Efficiently Learning Significant Fourier Feature Pairs for Statistical Independence Testing
Model-based Diffusion for Trajectory Optimization
Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling
Locally Private and Robust Multi-Armed Bandits
Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation
AdanCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer
InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction
Causal Inference in the Closed-Loop: Marginal Structural Models for Sequential Excursion Effects
Truncated Variance Reduced Value Iteration
Effective Exploration Based on the Structural Information Principles
QWO: Speeding Up Permutation-Based Causal Discovery in LiGAMs
Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem
Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand Avatars
Inferring stochastic low-rank recurrent neural networks from neural data
Unchosen Experts Can Contribute Too: Unleashing MoE Models’ Power by Self-Contrast
Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler
Diffusion Spectral Representation for Reinforcement Learning
Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization
Stabilizing Zero-Shot Prediction: A Novel Antidote to Forgetting in Continual Vision-Language Tasks
Multistep Distillation of Diffusion Models via Moment Matching
Towards Multi-Domain Learning for Generalizable Video Anomaly Detection
Convergence of No-Swap-Regret Dynamics in Self-Play
Cross-Scale Self-Supervised Blind Image Deblurring via Implicit Neural Representation
Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity
Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent Coding
Global Convergence in Training Large-Scale Transformers
Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in LLMs
Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks
Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces
Spiking Neural Network as Adaptive Event Stream Slicer
Universal Exact Compression of Differentially Private Mechanisms
Enhancing Robustness of Last Layer Two-Stage Fair Model Corrections
Fast Proxy Experiment Design for Causal Effect Identification
Coherence-free Entrywise Estimation of Eigenvectors in Low-rank Signal-plus-noise Matrix Models
From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings
Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning
Simplifying Latent Dynamics with Softly State-Invariant World Models
PAC-Bayes-Chernoff bounds for unbounded losses
Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences
LLM Dataset Inference: Did you train on my dataset?
Grokking of Implicit Reasoning in Transformers: A Mechanistic Journey to the Edge of Generalization
DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms
Learning Distinguishable Trajectory Representation with Contrastive Loss
Interpreting the Weight Space of Customized Diffusion Models
Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning
Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers
Identifying Spatio-Temporal Drivers of Extreme Events
HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting
Animal-Bench: Benchmarking Multimodal Video Models for Animal-centric Video Understanding
Contextual Decision-Making with Knapsacks Beyond the Worst Case
Is Knowledge Power? On the (Im)possibility of Learning from Strategic Interactions
Neural Combinatorial Optimization for Robust Routing Problem with Uncertain Travel Times
Make Continual Learning Stronger via C-Flat
Automatic Outlier Rectification via Optimal Transport
Exactly Minimax-Optimal Locally Differentially Private Sampling
On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
PuLID: Pure and Lightning ID Customization via Contrastive Alignment
A Theory of Optimistically Universal Online Learnability for General Concept Classes
Efficient Streaming Algorithms for Graphlet Sampling
Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions
Nearly Minimax Optimal Regret for Multinomial Logistic Bandit
FM-Delta: Lossless Compression for Storing Massive Fine-tuned Foundation Models
STONE: A Submodular Optimization Framework for Active 3D Object Detection
Data subsampling for Poisson regression with pth-root-link
Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective
Kernel PCA for Out-of-Distribution Detection
Matching the Statistical Query Lower Bound for $k$-Sparse Parity Problems with Sign Stochastic Gradient Descent
Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
Revisiting K-mer Profile for Effective and Scalable Genome Representation Learning
CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object Detection
Last-Iterate Convergence for Generalized Frank-Wolfe in Monotone Variational Inequalities
Multiview Scene Graph
Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers
3D Structure Prediction of Atomic Systems with Flow-based Direct Preference Optimization
Leveraging an ECG Beat Diffusion Model for Morphological Reconstruction from Indirect Signals
LLaNA: Large Language and NeRF Assistant
Predicting Label Distribution from Ternary Labels
Deep linear networks for regression are implicitly regularized towards flat minima
SAM-Guided Masked Token Prediction for 3D Scene Understanding
MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning
Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity
Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages
Consistency Diffusion Bridge Models
Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
ProxyFusion: Face Feature Aggregation Through Sparse Experts
Language Generation in the Limit
GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
Pruning neural network models for gene regulatory dynamics using data and domain knowledge
Space-Time Continuous PDE Forecasting using Equivariant Neural Fields
Policy Improvement using Language Feedback Models
The Challenges of the Nonlinear Regime for Physics-Informed Neural Networks
Edit Distance Robust Watermarks via Indexing Pseudorandom Codes
Artemis: Towards Referential Understanding in Complex Videos
When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search
TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Models
Federated Black-Box Adaptation for Semantic Segmentation
Structured Learning of Compositional Sequential Interventions
The Power of Extrapolation in Federated Learning
Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes
Learning Plaintext-Ciphertext Cryptographic Problems via ANF-based SAT Instance Representation
Linguistic Collapse: Neural Collapse in (Large) Language Models
Continuous Temporal Domain Generalization
Hybrid Generative AI for De Novo Design of Co-Crystals with Enhanced Tabletability
Relational Concept Bottleneck Models
Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model
Robust Conformal Prediction Using Privileged Information
Differentiable Quantum Computing for Large-scale Linear Control
Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization
Language Models as Hierarchy Encoders
On the Convergence of Loss and Uncertainty-based Active Learning Algorithms
Exponential Quantum Communication Advantage in Distributed Inference and Learning
BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction
Bridging Gaps: Federated Multi-View Clustering in Heterogeneous Hybrid Views
Sample Selection via Contrastive Fragmentation for Noisy Label Regression
Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
First-Order Minimax Bilevel Optimization
Latent Learning Progress Drives Autonomous Goal Selection in Human Reinforcement Learning
Neuronal Competition Groups with Supervised STDP for Spike-Based Classification
Continuous Heatmap Regression for Pose Estimation via Implicit Neural Representation
A distributional simplicity bias in the learning dynamics of transformers
Improving Decision Sparsity
HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness
PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
Active Set Ordering
Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
Sparse Bayesian Generative Modeling for Compressive Sensing
Dual Critic Reinforcement Learning under Partial Observability
Achievable Fairness on Your Data With Utility Guarantees
Skill-aware Mutual Information Optimisation for Zero-shot Generalisation in Reinforcement Learning
Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning
Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training
PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation
Preference-based Pure Exploration
Propensity Score Alignment of Unpaired Multimodal Data
Retrieval-Retro: Retrieval-based Inorganic Retrosynthesis with Expert Knowledge
ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users
Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
Physics-informed Neural Networks for Functional Differential Equations: Cylindrical Approximation and Its Convergence Guarantees
OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
Learning the Infinitesimal Generator of Stochastic Diffusion Processes
Achieving Linear Convergence with Parameter-Free Algorithms in Decentralized Optimization
ESPACE: Dimensionality Reduction of Activations for Model Compression
Animate3D: Animating Any 3D Model with Multi-view Video Diffusion
Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach
Learning Representations for Hierarchies with Minimal Support
Learning Image Priors Through Patch-Based Diffusion Models for Solving Inverse Problems
Generative Semi-supervised Graph Anomaly Detection
Approximating mutual information of high-dimensional variables using learned representations
Online Feature Updates Improve Online (Generalized) Label Shift Adaptation
A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration
Finding good policies in average-reward Markov Decision Processes without prior knowledge
Is Score Matching Suitable for Estimating Point Processes?
Initializing Services in Interactive ML Systems for Diverse Users
LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language
Local and Adaptive Mirror Descents in Extensive-Form Games
Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting
Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models
Hierarchical Object-Aware Dual-Level Contrastive Learning for Domain Generalized Stereo Matching
Decomposed Prompt Decision Transformer for Efficient Unseen Task Generalization
SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning
Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach
Transferring disentangled representations: bridging the gap between synthetic and real images
Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling
Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning
Neural Embeddings Rank: Aligning 3D latent dynamics with movements
Periodic agent-state based Q-learning for POMDPs
Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning
Mixture of Adversarial LoRAs: Boosting Robust Generalization in Meta-Tuning
FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation
Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network
Proportional Fairness in Clustering: A Social Choice Perspective
FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference
Full-Atom Peptide Design with Geometric Latent Diffusion
Learning via Surrogate PAC-Bayes
OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images
Consistency Models for Scalable and Fast Simulation-Based Inference
Doubly Hierarchical Geometric Representations for Strand-based Human Hairstyle Generation
Piecewise deterministic generative models
Inflationary Flows: Calibrated Bayesian Inference with Diffusion-Based Models
A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression
Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world Corruptions
Putting Gale & Shapley to Work: Guaranteeing Stability Through Learning
On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization
LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model
Dynamic Rescaling for Training GNNs
DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity
Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning
Smoke and Mirrors in Causal Downstream Tasks
Randomized Sparse Matrix Compression for Large-Scale Constrained Optimization in Cancer Radiotherapy
Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation
NeuralSolver: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks
SSDM: Scalable Speech Dysfluency Modeling
State Chrono Representation for Enhancing Generalization in Reinforcement Learning
WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
SpecExec: Massively Parallel Speculative Decoding For Interactive LLM Inference on Consumer Devices
Non-convolutional graph neural networks.
Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting
PowerPM: Foundation Model for Power Systems
Image Reconstruction Via Autoencoding Sequential Deep Image Prior
Hamiltonian Score Matching and Generative Flows
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
Visual Perception by Large Language Model’s Weights
Energy-Guided Continuous Entropic Barycenter Estimation for General Costs
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
Unravelling in Collaborative Learning
FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?
Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems
LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Control and Rendering
What Makes Partial-Label Learning Algorithms Effective?
Online Control with Adversarial Disturbance for Continuous-time Linear Systems
Semantic Routing via Autoregressive Modeling
Learning to Understand: Identifying Interactions via the Möbius Transform
Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling
REDUCR: Robust Data Downsampling using Class Priority Reweighting
ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field
SpaceByte: Towards Deleting Tokenization from Large Language Modeling
Oracle-Efficient Reinforcement Learning for Max Value Ensembles
RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis
Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass
Accelerating Blockwise Parallel Language Models with Draft Refinement
Banded Square Root Matrix Factorization for Differentially Private Model Training
Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control
DiffuPac: Contextual Mimicry in Adversarial Packets Generation via Diffusion Model
Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?
ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation
On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models
Information-theoretic Limits of Online Classification with Noisy Labels
Scaling Continuous Latent Variable Models as Probabilistic Integral Circuits
Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
Dual-Perspective Activation: Efficient Channel Denoising via Joint Forward-Backward Criterion for Artificial Neural Networks
Noise Contrastive Alignment of Language Models with Explicit Rewards
Why the Metric Backbone Preserves Community Structure
Bayesian Optimization of Functions over Node Subsets in Graphs
The Minimax Rate of HSIC Estimation for Translation-Invariant Kernels
Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models
CondTSF: One-line Plugin of Dataset Condensation for Time Series Forecasting
ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models
Adversarial Schrödinger Bridge Matching
Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning
Proximal Causal Inference With Text Data
Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression
LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning
Partial observation can induce mechanistic mismatches in data-constrained models of neural dynamics
A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays
Robot Policy Learning with Temporal Optimal Transport Reward
Non-geodesically-convex optimization in the Wasserstein space
Where's Waldo: Diffusion Features For Personalized Segmentation and Retrieval
On provable privacy vulnerabilities of graph representations
Seeing Beyond the Crop: Using Language Priors for Out-of-Bounding Box Keypoint Prediction
Association Pattern-aware Fusion for Biological Entity Relationship Prediction
Towards Principled Graph Transformers
Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Search
Cross-Modality Perturbation Synergy Attack for Person Re-identification
MAC Advice for facility location mechanism design
How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval
Neural decoding from stereotactic EEG: accounting for electrode variability across subjects
Towards Effective Planning Strategies for Dynamic Opinion Networks
A Kernel Perspective on Distillation-based Collaborative Learning
Beyond Accuracy: Tracking more like Human via Visual Search
Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts
Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering
ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models
MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models
eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling
Tolerant Algorithms for Learning with Arbitrary Covariate Shift
Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation
Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning
Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections
Learning 1D Causal Visual Representation with De-focus Attention Networks
The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning
Paths to Equilibrium in Games
PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning
Provable Partially Observable Reinforcement Learning with Privileged Information
Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?
Optimal Classification under Performative Distribution Shift
FedAvP: Augment Local Data via Shared Policy in Federated Learning
Identifiability Guarantees for Causal Disentanglement from Purely Observational Data
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling
Building a stable classifier with the inflated argmax
A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
A Single-Step, Sharpness-Aware Minimization is All You Need to Achieve Efficient and Accurate Sparse Training
How to Boost Any Loss Function
Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation
Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization
DePLM: Denoising Protein Language Models for Property Optimization
Reinforcement Learning with Adaptive Regularization for Safe Control of Critical Systems
Analysis of Corrected Graph Convolutions
Marrying Causal Representation Learning with Dynamical Systems for Science
ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization
Active Classification with Few Queries under Misspecification
BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
Online Composite Optimization Between Stochastic and Adversarial Environments
Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learning
Differential Privacy in Scalable General Kernel Learning via $K$-means Nystr{\"o}m Random Features
Robust group and simultaneous inferences for high-dimensional single index model
On the Worst Prompt Performance of Large Language Models
Implicit Regularization of Decentralized Gradient Descent for Sparse Regression
Scalable Kernel Inverse Optimization
CLIPCEIL: Domain Generalization through CLIP via Channel rEfinement and Image-text aLignment
Beyond Slow Signs in High-fidelity Model Extraction
A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning
Quantifying the Gain in Weak-to-Strong Generalization
Mirror and Preconditioned Gradient Descent in Wasserstein Space
Geometry of naturalistic object representations in recurrent neural network models of working memory
AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning
Natural Counterfactuals With Necessary Backtracking
Scaling laws for learning with real and surrogate data
The Power of Hard Attention Transformers on Data Sequences: A formal language theoretic perspective
DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection
Neural Residual Diffusion Models for Deep Scalable Vision Generation
Enhancing LLM Reasoning via Vision-Augmented Prompting
Discrete Dictionary-based Decomposition Layer for Structured Representation Learning
Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads
Parameter-Inverted Image Pyramid Networks
SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain
Understanding the Role of Equivariance in Self-supervised Learning
Decompose, Analyze and Rethink: Solving Intricate Problems with Human-like Reasoning Cycle
Robustly overfitting latents for flexible neural image compression
Harmonizing Stochasticity and Determinism: Scene-responsive Diverse Human Motion Prediction
DeTrack: In-model Latent Denoising Learning for Visual Object Tracking
Dual-Diffusion for Binocular 3D Human Pose Estimation
Meta-Diffu$B$: A Contextualized Sequence-to-Sequence Text Diffusion Model with Meta-Exploration
Why Warmup the Learning Rate? Underlying Mechanisms and Improvements
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
MeLLoC: Lossless Compression with High-order Mechanism Learning
AID: Attention Interpolation of Text-to-Image Diffusion
Taming Generative Diffusion Prior for Universal Blind Image Restoration
Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions
Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond
Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation
BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning
When does perceptual alignment benefit vision representations?
Safe and Sparse Newton Method for Entropic-Regularized Optimal Transport
Adaptive Experimentation When You Can't Experiment
Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
Reinforcement Learning with Euclidean Data Augmentation for State-Based Continuous Control
UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction
How Diffusion Models Learn to Factorize and Compose
On scalable oversight with weak LLMs judging strong LLMs
On the Comparison between Multi-modal and Single-modal Contrastive Learning
Pseudo-Siamese Blind-spot Transformers for Self-Supervised Real-World Denoising
Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes
Abrupt Learning in Transformers: A Case Study on Matrix Completion
Honor Among Bandits: No-Regret Learning for Online Fair Division
M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation
Scalable Bayesian Optimization via Focalized Sparse Gaussian Processes
Stochastic Extragradient with Flip-Flop Shuffling & Anchoring: Provable Improvements
DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning
Saliency-driven Experience Replay for Continual Learning
Ordering-Based Causal Discovery for Linear and Nonlinear Relations
CLUES: Collaborative Private-domain High-quality Data Selection for LLMs via Training Dynamics
Perplexity-aware Correction for Robust Alignment with Noisy Preferences
HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction
Can large language models explore in-context?
Geometric Trajectory Diffusion Models
Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer
Mitigating Spurious Correlations via Disagreement Probability
Zero-Shot Transfer of Neural ODEs
Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach
The GAN is dead; long live the GAN! A Modern GAN Baseline
Improved Guarantees for Fully Dynamic $k$-Center Clustering with Outliers in General Metric Spaces
HGDL: Heterogeneous Graph Label Distribution Learning
Improved Sample Complexity Bounds for Diffusion Model Training
When is Multicalibration Post-Processing Necessary?
DenoiseRep: Denoising Model for Representation Learning
QueST: Self-Supervised Skill Abstractions for Learning Continuous Control
GACL: Exemplar-Free Generalized Analytic Continual Learning
Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
Linear Causal Bandits: Unknown Graph and Soft Interventions
Scaling Laws in Linear Regression: Compute, Parameters, and Data
Gene-Gene Relationship Modeling Based on Genetic Evidence for Single-Cell RNA-Seq Data Imputation
Relationship Prompt Learning is Enough for Open-Vocabulary Semantic Segmentation
Accelerating Transformers with Spectrum-Preserving Token Merging
Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss
Group Robust Preference Optimization in Reward-free RLHF
No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations
Reinforcement Learning Guided Semi-Supervised Learning
Infusing Self-Consistency into Density Functional Theory Hamiltonian Prediction via Deep Equilibrium Models
Mutual Information Estimation via $f$-Divergence and Data Derangements
Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding
Continual Audio-Visual Sound Separation
Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition
Who’s Gaming the System? A Causally-Motivated Approach for Detecting Strategic Adaptation
Elo Uncovered: Robustness and Best Practices in Language Model Evaluation
Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers
DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices
ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis
LoQT: Low-Rank Adapters for Quantized Pretraining
Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuli
Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference
Gaussian Process Bandits for Top-k Recommendations
Second-order forward-mode optimization of recurrent neural networks for neuroscience
LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment
Fundamental Convergence Analysis of Sharpness-Aware Minimization
MADiff: Offline Multi-agent Learning with Diffusion Models
Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets
On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval
Near-Optimality of Contrastive Divergence Algorithms
Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training
FashionR2R: Texture-preserving Rendered-to-Real Image Translation with Diffusion Models
An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning
Iteration Head: A Mechanistic Study of Chain-of-Thought
Leveraging partial stragglers within gradient coding
Learning rigid-body simulators over implicit shapes for large-scale scenes and vision
Learning Optimal Tax Design in Nonatomic Congestion Games
Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective
DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
Imitating Language via Scalable Inverse Reinforcement Learning
Rule Based Rewards for Language Model Safety
A Gradient Accumulation Method for Dense Retriever under Memory Constraint
DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs
Safe Exploitative Play with Untrusted Type Beliefs
DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion
LIVE: Learnable In-Context Vector for Visual Question Answering
Wasserstein convergence of Cech persistence diagrams for samplings of submanifolds
Toward Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal Consistency
Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models
Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration Bonus
Cloud Object Detector Adaptation by Integrating Different Source Knowledge
PhyRecon: Physically Plausible Neural Scene Reconstruction
GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts
Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques
RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
Understanding Model Selection for Learning in Strategic Environments
Parallelizing Model-based Reinforcement Learning Over the Sequence Length
Bayes-optimal learning of an extensive-width neural network from quadratically many samples
Qualitative Mechanism Independence
Your Diffusion Model is Secretly a Noise Classifier and Benefits from Contrastive Training
Trading Place for Space: Increasing Location Resolution Reduces Contextual Capacity in Hippocampal Codes
What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration
FastSurvival: Hidden Computational Blessings in Training Cox Proportional Hazards Models
Gradients of Functions of Large Matrices
Coarse-to-Fine Concept Bottleneck Models
Image Understanding Makes for A Good Tokenizer for Image Generation
Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
Collaborative Refining for Learning from Inaccurate Labels
Bridging the Divide: Reconsidering Softmax and Linear Attention
DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor
HuRef: HUman-REadable Fingerprint for Large Language Models
Sample Complexity Reduction via Policy Difference Estimation in Tabular Reinforcement Learning
Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification
Iteratively Refined Behavior Regularization for Offline Reinforcement Learning
Scaling the Codebook Size of VQ-GAN to 100,000 with a Utilization Rate of 99%
Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation
EEG2Video: Towards Decoding Dynamic Visual Perception from EEG Signals
LACIE: Listener-Aware Finetuning for Calibration in Large Language Models
QVAE-Mole: The Quantum VAE with Spherical Latent Variable Learning for 3-D Molecule Generation
Exploring Adversarial Robustness of Deep State Space Models
Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise
ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
Zero-Shot Tokenizer Transfer
Intrinsic Robustness of Prophet Inequality to Strategic Reward Signaling
Statistical and Geometrical properties of the Kernel Kullback-Leibler divergence
Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion
Identification and Estimation of the Bi-Directional MR with Some Invalid Instruments
Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras
VeXKD: The Versatile Integration of Cross-Modal Fusion and Knowledge Distillation for 3D Perception
A versatile informative diffusion model for single-cell ATAC-seq data generation and analysis
Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers
AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data
General bounds on the quality of Bayesian coresets
Stepping on the Edge: Curvature Aware Learning Rate Tuners
4Diffusion: Multi-view Video Diffusion Model for 4D Generation
Parameter-free Clipped Gradient Descent Meets Polyak
ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling
Automatically Learning Hybrid Digital Twins of Dynamical Systems
U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis
Bayesian Strategic Classification
Information Re-Organization Improves Reasoning in Large Language Models
FUGAL: Feature-fortified Unrestricted Graph Alignment
Time-Varying LoRA: Towards Effective Cross-Domain Fine-Tuning of Diffusion Models
Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure
Dual Encoder GAN Inversion for High-Fidelity 3D Head Reconstruction from Single Images
Deep Bayesian Active Learning for Preference Modeling in Large Language Models
Unscrambling disease progression at scale: fast inference of event permutations with optimal transport
EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature
MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their Usability
Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections
Deep Equilibrium Algorithmic Reasoning
Detecting and Measuring Confounding Using Causal Mechanism Shifts
EM Distillation for One-step Diffusion Models
Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation
Differentially Private Reinforcement Learning with Self-Play
Universal Rates for Active Learning
Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
Monte Carlo Tree Search based Space Transfer for Black Box Optimization
OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators
Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibration
LaSCal: Label-Shift Calibration without target labels
Generated and Pseudo Content guided Prototype Refinement for Few-shot Point Cloud Segmentation
From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach
Confident Natural Policy Gradient for Local Planning in $q_\pi$-realizable Constrained MDPs
What type of inference is planning?
A two-scale Complexity Measure for Deep Learning Models
How Do Large Language Models Acquire Factual Knowledge During Pretraining?
Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection
MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models
DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation
Dynamic Service Fee Pricing under Strategic Behavior: Actions as Instruments and Phase Transition
DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers
High-dimensional (Group) Adversarial Training in Linear Regression
Randomized Truthful Auctions with Learning Agents
QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model
Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^\pi$-Realizability and Concentrability
Boosted Conformal Prediction Intervals
Idiographic Personality Gaussian Process for Psychological Assessment
UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections
Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation
Ordered Momentum for Asynchronous SGD
Targeted Sequential Indirect Experiment Design
An eye for an ear: zero-shot audio description leveraging an image captioner with audio-visual token distribution matching
Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms
MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
Federated Graph Learning for Cross-Domain Recommendation
Benign overfitting in leaky ReLU networks with moderate input dimension
Exploring the trade-off between deep-learning and explainable models for brain-machine interfaces
Frequency-aware Generative Models for Multivariate Time Series Imputation
RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models
Distribution-Aware Data Expansion with Diffusion Models
Exocentric-to-Egocentric Video Generation
Rapid Plug-in Defenders
Improved learning rates in multi-unit uniform price auctions
Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
The Value of Reward Lookahead in Reinforcement Learning
Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization
Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images
Toward a Well-Calibrated Discrimination via Survival Outcome-Aware Contrastive Learning
Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization
A Tractable Inference Perspective of Offline RL
State Space Models on Temporal Graphs: A First-Principles Study
Variational Flow Matching for Graph Generation
AverNet: All-in-one Video Restoration for Time-varying Unknown Degradations
Hierarchical Uncertainty Exploration via Feedforward Posterior Trees
Direct Unlearning Optimization for Robust and Safe Text-to-Image Models
PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
DreamSteerer: Enhancing Source Image Conditioned Editability using Personalized Diffusion Models
Faster Repeated Evasion Attacks in Tree Ensembles
Cross-modal Representation Flattening for Multi-modal Domain Generalization
Auditing Local Explanations is Hard
Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning
Interventionally Consistent Surrogates for Complex Simulation Models
Regression under demographic parity constraints via unlabeled post-processing
Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels
Renovating Names in Open-Vocabulary Segmentation Benchmarks
Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse
Uncovering Safety Risks of Large Language Models through Concept Activation Vector
Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models
DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach
EMVP: Embracing Visual Foundation Model for Visual Place Recognition with Centroid-Free Probing
Outlier-Robust Distributionally Robust Optimization via Unbalanced Optimal Transport
FUG: Feature-Universal Graph Contrastive Pre-training for Graphs with Diverse Node Features
StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
Learning Where to Edit Vision Transformers
Connectivity-Driven Pseudo-Labeling Makes Stronger Cross-Domain Segmenters
BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning
Spiking Graph Neural Network on Riemannian Manifolds
CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations
Weak Supervision Performance Evaluation via Partial Identification
PrivCirNet: Efficient Private Inference via Block Circulant Transformation
A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning
PageRank Bandits for Link Prediction
Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis
Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learner
Reproducibility of predictive networks for mouse visual cortex
Balancing Context Length and Mixing Times for Reinforcement Learning at Scale
LoRA-GA: Low-Rank Adaptation with Gradient Approximation
Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion models
Grounded Answers for Multi-agent Decision-making Problem through Generative World Model
TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering
Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
Nearly Minimax Optimal Submodular Maximization with Bandit Feedback
Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach
A Topology-aware Graph Coarsening Framework for Continual Graph Learning
SGLang: Efficient Execution of Structured Language Model Programs
Pipeline Parallelism with Controllable Memory
Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm
Learning Generalized Linear Programming Value Functions
Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation
ContextGS : Compact 3D Gaussian Splatting with Anchor Level Context Model
Contextual Bilevel Reinforcement Learning for Incentive Alignment
Relational Verification Leaps Forward with RABBit
Derivative-enhanced Deep Operator Network
Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients
One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
Adversarially Robust Decision Transformer
Efficient Reinforcement Learning by Discovering Neural Pathways
Exploiting Representation Curvature for Boundary Detection in Time Series
Interpretable Concept-Based Memory Reasoning
Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers
IPO: Interpretable Prompt Optimization for Vision-Language Models
Estimating Epistemic and Aleatoric Uncertainty with a Single Model
Query-Efficient Correlation Clustering with Noisy Oracle
Safety through feedback in Constrained RL
Embedding-Aligned Language Models
Hybrid Reinforcement Learning Breaks Sample Size Barriers In Linear MDPs
Disentangling Linear Quadratic Control with Untrusted ML Predictions
Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning
Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control
CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition
Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning
Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis
Personalized Federated Learning via Feature Distribution Adaptation
Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference
Fairness-Aware Estimation of Graphical Models
PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications
Graph Learning for Numeric Planning
Generalized Protein Pocket Generation with Prior-Informed Flow Matching
Invariant subspaces and PCA in nearly matrix multiplication time
Functional Bilevel Optimization for Machine Learning
FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference Images
Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion
Mixture of Link Predictors on Graphs
MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encoding
Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning
Non-asymptotic Approximation Error Bounds of Parameterized Quantum Circuits
Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection
Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations
The Collusion of Memory and Nonlinearity in Stochastic Approximation With Constant Stepsize
High-probability complexity bounds for stochastic non-convex minimax optimization
Visual Data Diagnosis and Debiasing with Concept Graphs
Linear Uncertainty Quantification of Graphical Model Inference
Continuous Product Graph Neural Networks
Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL
Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts
How does Gradient Descent Learn Features --- A Local Analysis for Regularized Two-Layer Neural Networks
Semi-Random Matrix Completion via Flow-Based Adaptive Reweighting
Pure Message Passing Can Estimate Common Neighbor for Link Prediction
When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
What If the Input is Expanded in OOD Detection?
Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation
A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem
TAIA: Large Language Models are Out-of-Distribution Data Learners
Goal Reduction with Loop-Removal Accelerates RL and Models Human Brain Activity in Goal-Directed Learning
Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments
Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method
Conformal Inverse Optimization
SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification
MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
A Cat Is A Cat (Not A Dog!): Unraveling Information Mix-ups in Text-to-Image Encoders through Causal Analysis and Embedding Optimization
Acoustic Volume Rendering for Neural Impulse Response Fields
Synergistic Dual Spatial-aware Generation of Image-to-text and Text-to-image
Cross-model Control: Improving Multiple Large Language Models in One-time Training
SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors
A Full-duplex Speech Dialogue Scheme Based On Large Language Model
Can Learned Optimization Make Reinforcement Learning Less Difficult?
CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks
Physics-Regularized Multi-Modal Image Assimilation for Brain Tumor Localization
Linearly Decomposing and Recomposing Vision Transformers for Diverse-Scale Models
Preference Learning Algorithms Do Not Learn Preference Rankings
Discrete-state Continuous-time Diffusion for Graph Generation
TreeVI: Reparameterizable Tree-structured Variational Inference for Instance-level Correlation Capturing
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models
United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial Trajectories
DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models
The tree autoencoder model, with application to hierarchical data visualization
Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees
pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization
Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling
Unity by Diversity: Improved Representation Learning for Multimodal VAEs
Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery
SlimSAM: 0.1% Data Makes Segment Anything Slim
A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative Missingness
MemVLT: Vision-Language Tracking with Adaptive Memory-based Prompts
DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning
NeoRL: Efficient Exploration for Nonepisodic RL
Recurrent neural network dynamical systems for biological vision
ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models
Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution
CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos
Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models
How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach
CriticEval: Evaluating Large-scale Language Model as Critic
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance
Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
OneBit: Towards Extremely Low-bit Large Language Models
Learn more, but bother less: parameter efficient continual learning
OPUS: Occupancy Prediction Using a Sparse Set
Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models
Block Sparse Bayesian Learning: A Diversified Scheme
Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization
Images that Sound: Composing Images and Sounds on a Single Canvas
CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle Detectors
On the Sparsity of the Strong Lottery Ticket Hypothesis
Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient
Learning Mixtures of Unknown Causal Interventions
Diffusion PID: Interpreting Diffusion via Partial Information Decomposition
Hierarchical Federated Learning with Multi-Timescale Gradient Correction
Bandits with Ranking Feedback
TopoFR: A Closer Look at Topology Alignment on Face Recognition
On Differentially Private Subspace Estimation in a Distribution-Free Setting
An Accelerated Gradient Method for Convex Smooth Simple Bilevel Optimization
On Socially Fair Low-Rank Approximation and Column Subset Selection
Segment Anything without Supervision
Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading
Symmetric Linear Bandits with Hidden Symmetry
Trajectory Flow Matching with Applications to Clinical Time Series Modelling
Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
SureMap: Simultaneous mean estimation for single-task and multi-task disaggregated evaluation
Evaluating the World Model Implicit in a Generative Model
Discovering plasticity rules that organize and maintain neural circuits
Learning World Models for Unconstrained Goal Navigation
Learning Elastic Costs to Shape Monge Displacements
Symmetry-Informed Governing Equation Discovery
Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniques
Zipper: Addressing Degeneracy in Algorithm-Agnostic Inference
Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
Differentially Private Graph Diffusion with Applications in Personalized PageRanks
TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy
Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control
Is Multiple Object Tracking a Matter of Specialization?
Streaming Long Video Understanding with Large Language Models
VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction
Using Noise to Infer Aspects of Simplicity Without Learning
Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps
Don't Look Twice: Faster Video Transformers with Run-Length Tokenization
Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models
Learning Frequency-Adapted Vision Foundation Model for Domain Generalized Semantic Segmentation
MALT Powers Up Adversarial Attacks
VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
Fair Allocation in Dynamic Mechanism Design
Opponent Modeling with In-context Search
Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness
VisMin: Visual Minimal-Change Understanding
Causal Contrastive Learning for Counterfactual Regression Over Time
VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization
Robust Sleep Staging over Incomplete Multimodal Physiological Signals via Contrastive Imagination
Towards training digitally-tied analog blocks via hybrid gradient computation
On the Complexity of Identification in Linear Structural Causal Models
Learning Discrete Concepts in Latent Hierarchical Models
One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos
Fast yet Safe: Early-Exiting with Risk Control
Challenges of Generating Structurally Diverse Graphs
Guiding a Diffusion Model with a Bad Version of Itself
Multistable Shape from Shading Emerges from Patch Diffusion
OnlineTAS: An Online Baseline for Temporal Action Segmentation
Decoupled Kullback-Leibler Divergence Loss
Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Models
Fast Encoder-Based 3D from Casual Videos via Point Track Processing
Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception
Self-Labeling the Job Shop Scheduling Problem
Large Spatial Model: End-to-end Unposed Images to Semantic 3D
A Non-parametric Direct Learning Approach to Heterogeneous Treatment Effect Estimation under Unmeasured Confounding
Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy
Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data
Efficient $\Phi$-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games
Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptation
Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
ParallelEdits: Efficient Multi-Aspect Text-Driven Image Editing with Attention Grouping
Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods
Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation
OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning
Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming
No-Regret Bandit Exploration based on Soft Tree Ensemble Model
One-to-Multiple: A Progressive Style Transfer Unsupervised Domain-Adaptive Framework for Kidney Tumor Segmentation
Fine-Tuning is Fine, if Calibrated
Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
Private Geometric Median
Credit Attribution and Stable Compression
Generative Forests
Distributional regression: CRPS-error bounds for model fitting, model selection and convex aggregation
Learning Truncated Causal History Model for Video Restoration
Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders
Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation
Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference
DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning
Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation
Discretely beyond $1/e$: Guided Combinatorial Algortihms for Submodular Maximization
IF-Font: Ideographic Description Sequence-Following Font Generation
Learning Macroscopic Dynamics from Partial Microscopic Observations
Axioms for AI Alignment from Human Feedback
InversionView: A General-Purpose Method for Reading Information from Neural Activations
DeiSAM: Segment Anything with Deictic Prompting
Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
Customized Subgraph Selection and Encoding for Drug-drug Interaction Prediction
Online Weighted Paging with Unknown Weights
An exactly solvable model for emergence and scaling laws in the multitask sparse parity problem
Many-shot Jailbreaking
Can neural operators always be continuously discretized?
Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences
LeDex: Training LLMs to Better Self-Debug and Explain Code
EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models
Context-Aware Testing: A New Paradigm for Model Testing with Large Language Models
Classification Diffusion Models: Revitalizing Density Ratio Estimation
One-Shot Safety Alignment for Large Language Models via Optimal Dualization
Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens
DiGRAF: Diffeomorphic Graph-Adaptive Activation Function
UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models
MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models
Dissecting Query-Key Interaction in Vision Transformers
Constrained Diffusion with Trust Sampling
Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression
Retrieval-Augmented Diffusion Models for Time Series Forecasting
ReMAP: Neural Model Reprogramming with Network Inversion and Retrieval-Augmented Mapping for Adaptive Motion Forecasting
DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Docking
Molecule Design by Latent Prompt Transformer
Geometric Exploitation for Indoor Panoramic Semantic Segmentation
Hardness of Learning Neural Networks under the Manifold Hypothesis
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data
Dynamics of Supervised and Reinforcement Learning in the Non-Linear Perceptron
Noether's Razor: Learning Conserved Quantities
Approximately Equivariant Neural Processes
An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning
Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement
Nature-Inspired Local Propagation
What matters when building vision-language models?
Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach
Semi-supervised Knowledge Transfer Across Multi-omic Single-cell Data
Learning Human-like Representations to Enable Learning Human Values
C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory
SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models
Stochastic contextual bandits with graph feedback: from independence number to MAS number
Optimal Algorithms for Augmented Testing of Discrete Distributions
Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models
One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection
What Matters in Graph Class Incremental Learning? An Information Preservation Perspective
SILENCE: Protecting privacy in offloaded speech understanding on resource-constrained devices
Out-of-Distribution Detection with a Single Unconditional Diffusion Model
Reinforced Cross-Domain Knowledge Distillation on Time Series Data
Transductive Active Learning: Theory and Applications
Reimagining Mutual Information for Enhanced Defense against Data Leakage in Collaborative Inference
Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions
TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration
AirSketch: Generative Motion to Sketch
Revisiting the Integration of Convolution and Attention for Vision Backbone
Conditional Outcome Equivalence: A Quantile Alternative to CATE
RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness
Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers
Online Convex Optimisation: The Optimal Switching Regret for all Segmentations Simultaneously
Protecting Your LLMs with Information Bottleneck
On the Necessity of Collaboration for Online Model Selection with Decentralized Data
Training Compute-Optimal Protein Language Models
Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generation
Nonconvex Federated Learning on Compact Smooth Submanifolds With Heterogeneous Data
PACE: Pacing Operator Learning to Accurate Optical Field Simulation for Complicated Photonic Devices
Sample Complexity of Algorithm Selection Using Neural Networks and Its Applications to Branch-and-Cut
Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood
Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction
Convergence Analysis of Split Federated Learning on Heterogeneous Data
Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recovery
FIFO-Diffusion: Generating Infinite Videos from Text without Training
Drago: Primal-Dual Coupled Variance Reduction for Faster Distributionally Robust Optimization
The Fine-Grained Complexity of Gradient Computation for Training Large Language Models
Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations
Learning to Edit Visual Programs with Self-Supervision
Achieving Domain-Independent Certified Robustness via Knowledge Continuity
Weight for Robustness: A Comprehensive Approach towards Optimal Fault-Tolerant Asynchronous ML
GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields
CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework
Measuring Dejavu Memorization Efficiently
Learning from Uncertain Data: From Possible Worlds to Possible Models
Going Beyond Heuristics by Imposing Policy Improvement as a Constraint
Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication
Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient
DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control
Can We Leave Deepfake Data Behind in Training Deepfake Detector?
$\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise
Learning Segmentation from Point Trajectories
Average gradient outer product as a mechanism for deep neural collapse
Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation
High Rank Path Development: an approach to learning the filtration of stochastic processes
Can Language Models Learn to Skip Steps?
Discovery of the Hidden World with Large Language Models
Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
Energy-Based Modelling for Discrete and Mixed Data via Heat Equations on Structured Spaces
Learning Spatially-Aware Language and Audio Embeddings
Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling
Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering Playlists
S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule Search
CRAYM: Neural Field Optimization via Camera RAY Matching
Batched Energy-Entropy acquisition for Bayesian Optimization
Neural Collapse Inspired Feature Alignment for Out-of-Distribution Generalization
Iterative Methods via Locally Evolving Set Process
Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks
Reflective Multi-Agent Collaboration based on Large Language Models
A Sober Look at the Robustness of CLIPs to Spurious Features
Incentivizing Quality Text Generation via Statistical Contracts
RoPINN: Region Optimized Physics-Informed Neural Networks
Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective
Real-Time Selection Under General Constraints via Predictive Inference
MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders
Stochastic Optimal Control Matching
Implicit Bias of Mirror Flow on Separable Data
Scaling White-Box Transformers for Vision
Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation
Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification
The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks
On the Ability of Developers' Training Data Preservation of Learnware
A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness
Unsupervised Object Detection with Theoretical Guarantees
On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions
From Unstructured Data to In-Context Learning: Exploring What Tasks Can Be Learned and When
Med-Real2Sim: Non-Invasive Medical Digital Twins using Physics-Informed Self-Supervised Learning
Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies
Communication-Efficient Federated Group Distributionally Robust Optimization
The Implicit Bias of Adam on Separable Data
Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning
Feedback control guides credit assignment in recurrent neural networks
Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning
FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
Reasons and Solutions for the Decline in Model Performance after Editing
Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks
Scene Graph Generation with Role-Playing Large Language Models
Inverse Factorized Soft Q-Learning for Cooperative Multi-agent Imitation Learning
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation
Learning diffusion at lightspeed
Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving
Causal Discovery from Event Sequences by Local Cause-Effect Attribution
In Pursuit of Causal Label Correlations for Multi-label Image Recognition
Stepping Forward on the Last Mile
AUC Maximization under Positive Distribution Shift
Toward a Stable, Fair, and Comprehensive Evaluation of Object Hallucination in Large Vision-Language Models
Diffusion-based Curriculum Reinforcement Learning
Exogenous Matching: Learning Good Proposals for Tractable Counterfactual Estimation
Learning Bregman Divergences with Application to Robustness
Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking
Controlled maximal variability along with reliable performance in recurrent neural networks
Binarized Diffusion Model for Image Super-Resolution
Avoiding Undesired Future with Minimal Cost in Non-Stationary Environments
Optimal Algorithms for Learning Partitions with Faulty Oracles
Information-theoretic Generalization Analysis for Expected Calibration Error
ReGS: Reference-based Controllable Scene Stylization with Gaussian Splatting
PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecasting
GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations
ReLIZO: Sample Reusable Linear Interpolation-based Zeroth-order Optimization
XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation
Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame
Gated Inference Network: Inference and Learning State-Space Models
Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation
Learning diverse causally emergent representations from time series data
Amortized Bayesian Experimental Design for Decision-Making
A teacher-teacher framework for clinical language representation learning
Deep Correlated Prompting for Visual Recognition with Missing Modalities
Semantic Feature Learning for Universal Unsupervised Cross-Domain Retrieval
Inference of Neural Dynamics Using Switching Recurrent Neural Networks
Exploring Context Window of Large Language Models via Decomposed Positional Vectors
SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution
Enhancing Robustness of Graph Neural Networks on Social Media with Explainable Inverse Reinforcement Learning
TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning
Rethinking Deep Thinking: Stable Learning of Algorithms using Lipschitz Constraints
GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction
OxonFair: A Flexible Toolkit for Algorithmic Fairness
A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models
Learning Distributions on Manifolds with Free-Form Flows
Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
On the Expressivity and Sample Complexity of Node-Individualized Graph Neural Networks
Molecule Generation with Fragment Retrieval Augmentation
Persistent Homology for High-dimensional Data Based on Spectral Methods
Is Cross-validation the Gold Standard to Estimate Out-of-sample Model Performance?
Testably Learning Polynomial Threshold Functions
GAVEL: Generating Games via Evolution and Language Models
Linking In-context Learning in Transformers to Human Episodic Memory
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
Non-Asymptotic Uncertainty Quantification in High-Dimensional Learning
Contextual Multinomial Logit Bandits with General Value Functions
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
Transferable Boltzmann Generators
Quantum Deep Equilibrium Models
Navigating Extremes: Dynamic Sparsity in Large Output Spaces
Representation Noising: A Defence Mechanism Against Harmful Finetuning
Communication Bounds for the Distributed Experts Problem
Multi-Reward Best Policy Identification
Parseval Regularization for Continual Reinforcement Learning
Identifiable Shared Component Analysis of Unpaired Multimodal Mixtures
Code Repair with LLMs gives an Exploration-Exploitation Tradeoff
UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes
WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment
Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP
Zero-shot Image Editing with Reference Imitation
On Divergence Measures for Training GFlowNets
MambaLRP: Explaining Selective State Space Sequence Models
Large language model validity via enhanced conformal prediction methods
Depth Anything V2
Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
Semi-Open 3D Object Retrieval via Hierarchical Equilibrium on Hypergraph
Assembly Fuzzy Representation on Hypergraph for Open-Set 3D Object Retrieval
Warm-starting Push-Relabel
Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations
When are dynamical systems learned from time series data statistically accurate?
STL: Still Tricky Logic (for System Validation, Even When Showing Your Work)
FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation
Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization
Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularization
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
Autobidder's Dilemma: Why More Sophisticated Autobidders Lead to Worse Auction Efficiency
Efficiency of the First-Price Auction in the Autobidding World
DiffusionPDE: Generative PDE-Solving under Partial Observation
Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
Mitigating Covariate Shift in Behavioral Cloning via Robust Stationary Distribution Correction
Learning Cut Generating Functions for Integer Programming
GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching
Distributed-Order Fractional Graph Operating Network
Rad-NeRF: Ray-decoupled Training of Neural Radiance Field
Enhancing Semi-Supervised Learning via Representative and Diverse Sample Selection
On the Computational Landscape of Replicable Learning
Entrywise error bounds for low-rank approximations of kernel matrices
Cooperative Hardware-Prompt Learning for Snapshot Compressive Imaging
Neural Conditional Probability for Uncertainty Quantification
Learning the Optimal Policy for Balancing Short-Term and Long-Term Rewards
Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models
Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
MC-DiT: Contextual Enhancement via Clean-to-Clean Reconstruction for Masked Diffusion Models
Parallelizing Linear Transformers with the Delta Rule over Sequence Length
RCDN: Towards Robust Camera-Insensitivity Collaborative Perception via Dynamic Feature-based 3D Neural Modeling
Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization
KFNN: K-Free Nearest Neighbor For Crowdsourcing
Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting
GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting
LiT: Unifying LiDAR "Languages" with LiDAR Translator
Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
Homology Consistency Constrained Efficient Tuning for Vision-Language Models
Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis
AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models
Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models
BendVLM: Test-Time Debiasing of Vision-Language Embeddings
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent
Understanding Information Storage and Transfer in Multi-Modal Large Language Models
Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based Discrimination
Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
Prediction with Action: Visual Policy Learning via Joint Denoising Process
UPS: Unified Projection Sharing for Lightweight Single-Image Super-resolution and Beyond
Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
SyncVIS: Synchronized Video Instance Segmentation
An Image is Worth 32 Tokens for Reconstruction and Generation
DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization
Learning-Augmented Dynamic Submodular Maximization
DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model
Association of Objects May Engender Stereotypes: Mitigating Association-Engendered Stereotypes in Text-to-Image Generation
Generalizablity of Memorization Neural Network
Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set
Fast samplers for Inverse Problems in Iterative Refinement models
CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning
On Softmax Direct Preference Optimization for Recommendation
Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention
Tighter Convergence Bounds for Shuffled SGD via Primal-Dual Perspective
What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights
A Closer Look at the CLS Token for Cross-Domain Few-Shot Learning
FlexPlanner: Flexible 3D Floorplanning via Deep Reinforcement Learning in Hybrid Action Space with Multi-Modality Representation
Task-Agnostic Machine-Learning-Assisted Inference
End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning
OT4P: Unlocking Effective Orthogonal Group Path for Permutation Relaxation
Tight Rates for Bandit Control Beyond Quadratics
Direct Preference-Based Evolutionary Multi-Objective Optimization with Dueling Bandits
Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis
Referencing Where to Focus: Improving Visual Grounding with Referential Query
Is Value Learning Really the Main Bottleneck in Offline RL?
ActAnywhere: Subject-Aware Video Background Generation
Wings: Learning Multimodal LLMs without Text-only Forgetting
Dual-Personalizing Adapter for Federated Foundation Models
Goal-Conditioned On-Policy Reinforcement Learning
Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
Few-Shot Adversarial Prompt Learning on Vision-Language Models
MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction
DMNet: Self-comparison Driven Model for Subject-independent Seizure Detection
Latent Functional Maps: a spectral framework for representation alignment
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection
Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models
Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift
DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos
D2R2: Diffusion-based Representation with Random Distance Matching for Tabular Few-shot Learning
John Ellipsoids via Lazy Updates
QUEST: Quadruple Multimodal Contrastive Learning with Constraints and Self-Penalization
Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration
Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner
GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning
Multi-Scale Representation Learning for Protein Fitness Prediction
Synthetic Programming Elicitation for Text-to-Code in Very Low-Resource Programming and Formal Languages
Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
A Canonicalization Perspective on Invariant and Equivariant Learning
Identifying General Mechanism Shifts in Linear Causal Representations
An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations
Con4m: Context-aware Consistency Learning Framework for Segmented Time Series Classification
Query-Based Adversarial Prompt Generation
Instructor-inspired Machine Learning for Robust Molecular Property Prediction
Customizing Language Models with Instance-wise LoRA for Sequential Recommendation
Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimization
ProEdit: Simple Progression is All You Need for High-Quality 3D Scene Editing
PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
Flexible mapping of abstract domains by grid cells via self-supervised extraction and projection of generalized velocity signals
A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings
Optimizing Automatic Differentiation with Deep Reinforcement Learning
Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling
On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity
Online Learning of Delayed Choices
Detecting Bugs with Substantial Monetary Consequences by LLM and Rule-based Reasoning
A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs
The Price of Implicit Bias in Adversarially Robust Generalization
Least Squares Regression Can Exhibit Under-Parameterized Double Descent
KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension
Towards Unsupervised Model Selection for Domain Adaptive Object Detection
Fine-Grained Dynamic Framework for Bias-Variance Joint Optimization on Data Missing Not at Random
HyperLogic: Enhancing Diversity and Accuracy in Rule Learning with HyperNets
Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning
Long-range Brain Graph Transformer
DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs
Boundary Decomposition for Nadir Objective Vector Estimation
Active Learning of General Halfspaces: Label Queries vs Membership Queries
SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection
Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium
Multi-Head Mixture-of-Experts
Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
Knowledge Graph Completion by Intermediate Variables Regularization
Fractal Patterns May Illuminate the Success of Next-Token Prediction
Transformer Doctor: Diagnosing and Treating Vision Transformers
Gliding over the Pareto Front with Uniform Designs
Boosting Transferability and Discriminability for Time Series Domain Adaptation
A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch
FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Discrepancy-Aware Aggregation
Revisiting motion information for RGB-Event tracking with MOT philosophy
Long-Range Feedback Spiking Network Captures Dynamic and Static Representations of the Visual Cortex under Movie Stimuli
Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps
Optimistic Verifiable Training by Controlling Hardware Nondeterminism
Vivid-ZOO: Multi-View Video Generation with Diffusion Model
Identifying Equivalent Training Dynamics
MatrixNet: Learning over symmetry groups using learned group representations
Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows
Mind the Gap: A Causal Perspective on Bias Amplification in Prediction & Decision-Making
In-and-Out: Algorithmic Diffusion for Sampling Convex Bodies
IWBVT: Instance Weighting-based Bias-Variance Trade-off for Crowdsourcing
Video Diffusion Models are Training-free Motion Interpreter and Controller
TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation
Truthful High Dimensional Sparse Linear Regression
Generalizable Implicit Motion Modeling for Video Frame Interpolation
Typicalness-Aware Learning for Failure Detection
Implicit Regularization Paths of Weighted Neural Representations
$\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$
Zero-shot Generalizable Incremental Learning for Vision-Language Object Detection
Collaboration! Towards Robust Neural Methods for Routing Problems
Reprogramming Pretrained Target-Specific Diffusion Models for Dual-Target Drug Design
Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network
MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models
Data-Driven Discovery of Dynamical Systems in Pharmacology using Large Language Models
FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention
Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse Experts
Spiking Transformer with Experts Mixture
A Functional Extension of Semi-Structured Networks
Universal Neural Functionals
Satformer: Accurate and Robust Traffic Data Estimation for Satellite Networks
LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed Problems
A Motion-aware Spatio-temporal Graph for Video Salient Object Ranking
The Bayesian sampling in a canonical recurrent circuit with a diversity of inhibitory interneurons
Energy-based Hopfield Boosting for Out-of-Distribution Detection
Cost-efficient Knowledge-based Question Answering with Large Language Models
Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model
Cryptographic Hardness of Score Estimation
Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics
Neural Cover Selection for Image Steganography
Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings
FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations
Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning
One-Step Effective Diffusion Network for Real-World Image Super-Resolution
Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly
LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization
Stabilized Proximal-Point Methods for Federated Optimization
Mixtures of Experts for Audio-Visual Learning
Computing the Bias of Constant-step Stochastic Approximation with Markovian Noise
DDN: Dual-domain Dynamic Normalization for Non-stationary Time Series Forecasting
On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion
Improving Generalization of Dynamic Graph Learning via Environment Prompt
Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts
The motion planning neural circuit in goal-directed navigation as Lie group operator search
Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning
Faster Differentially Private Top-$k$ Selection: A Joint Exponential Mechanism with Pruning
Hybrid Mamba for Few-Shot Segmentation
Graph-based Uncertainty Metrics for Long-form Language Model Generations
Cross-video Identity Correlating for Person Re-identification Pre-training
Statistical-Computational Trade-offs for Density Estimation
Sharpness-Aware Minimization Activates the Interactive Teaching's Understanding and Optimization
KnowGPT: Knowledge Graph based Prompting for Large Language Models
The Reliability of OKRidge Method in Solving Sparse Ridge Regression Problems
Efficient Graph Matching for Correlated Stochastic Block Models
GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning
Accelerating Relative Entropy Coding with Space Partitioning
Diffusion Priors for Variational Likelihood Estimation and Image Denoising
On the Computational Complexity of Private High-dimensional Model Selection
Observational Scaling Laws and the Predictability of Langauge Model Performance
Decomposable Transformer Point Processes
ST$_k$: A Scalable Module for Solving Top-k Problems
Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models
Test-Time Dynamic Image Fusion
G2D: From Global to Dense Radiography Representation Learning via Vision-Language Pre-training
Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
A Local Method for Satisfying Interventional Fairness with Partially Known Causal Graphs
UniAudio 1.5: Large Language Model-Driven Audio Codec is A Few-Shot Audio Task Learner
TFG: Unified Training-Free Guidance for Diffusion Models
Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data
Boosting Weakly Supervised Referring Image Segmentation via Progressive Comprehension
You Only Look Around: Learning Illumination-Invariant Feature for Low-light Object Detection
On Sparse Canonical Correlation Analysis
SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining
Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual Information Minimization
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
RanDumb: Random Representations Outperform Online Continually Learned Representations
From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement Learning
Online Classification with Predictions
A Framework for Bilevel Optimization on Riemannian Manifolds
Multivariate Probabilistic Time Series Forecasting with Correlated Errors
Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models
Learning to Handle Complex Constraints for Vehicle Routing Problems
Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation
Learning to Price Homogeneous Data
Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learning
Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment
Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise
Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?
Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation
Transcoders find interpretable LLM feature circuits
Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization
Real-time Stereo-based 3D Object Detection for Streaming Perception
Soft ascent-descent as a stable and flexible alternative to flooding
Probablistic Emulation of a Global Climate Model with Spherical DYffusion
Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks
Rethinking Score Distillation as a Bridge Between Image Distributions
Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective
Variance estimation in compound decision theory under boundedness
Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting
SCOREQ: Speech Quality Assessment with Contrastive Regression
DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus
What Is Missing For Graph Homophily? Disentangling Graph Homophily For Graph Neural Networks
SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network
CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training
Pre-training Differentially Private Models with Limited Public Data
Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization
Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
A Critical Evaluation of AI Feedback for Aligning Large Language Models
StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences
AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
Using Surrogates in Covariate-adjusted Response-adaptive Randomization Experiments with Delayed Outcomes
AutoSurvey: Large Language Models Can Automatically Write Surveys
Dimension-free deterministic equivalents and scaling laws for random feature regression
ZeroMark: Towards Dataset Ownership Verification without Disclosing Watermark
Towards a Scalable Reference-Free Evaluation of Generative Models
Graph Diffusion Transformers for Multi-Conditional Molecular Generation
SE(3)-bi-equivariant Transformers for Point Cloud Assembly
Conformalized Time Series with Semantic Features
Addressing Spatial-Temporal Heterogeneity: General Mixed Time Series Analysis via Latent Continuity Recovery and Alignment
Emergence of heavy tails in homogenized stochastic gradient descent
The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing
Learning 3D Garment Animation from Trajectories of A Piece of Cloth
On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
Rethinking 3D Convolution in $\ell_p$-norm Space
A Siamese Transformer with Hierarchical Refinement for Lane Detection
HORSE: Hierarchical Representation for Large-Scale Neural Subset Selection
Pre-Trained Multi-Goal Transformers with Prompt Optimization for Efficient Online Adaptation
Segment Any Change
LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing
Spike-based Neuromorphic Model for Sound Source Localization
Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learning
Ex Uno Pluria: Insights on Ensembling in Low Precision Number Systems
Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processes
Fully Unconstrained Online Learning
Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding
SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures
Sample Complexity of Posted Pricing for a Single Item
Model Sensitivity Aware Continual Learning
GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell Genomics
Learning to Embed Distributions via Maximum Kernel Entropy
From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection
Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion
Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers
Evidence of Learned Look-Ahead in a Chess-Playing Neural Network
BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping
Provable Benefit of Cutout and CutMix for Feature Learning
MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials
Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Prediction
Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
HENASY: Learning to Assemble Scene-Entities for Interpretable Egocentric Video-Language Model
Dissecting the Failure of Invariant Learning on Graphs
Do's and Don'ts: Learning Desirable Skills with Instruction Videos
RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models
Uncovering the Redundancy in Graph Self-supervised Learning Models
A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers
Error Analysis of Spherically Constrained Least Squares Reformulation in Solving the Stackelberg Prediction Game
Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks
Diffusion Policies Creating a Trust Region for Offline Reinforcement Learning
DiffGS: Functional Gaussian Splatting Diffusion
Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars
Confusion-Resistant Federated Learning via Diffusion-Based Data Harmonization on Non-IID Data
IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation
Policy Optimization for Robust Average Reward MDPs
Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text Prompts
Hierarchical and Density-based Causal Clustering
Hypothesis Testing the Circuit Hypothesis in LLMs
Transfer Q-star : Principled Decoding for LLM Alignment
e-COP : Episodic Constrained Optimization of Policies
Relating Hopfield Networks to Episodic Control
LCGen: Mining in Low-Certainty Generation for View-consistent Text-to-3D
Alleviate Anchor-Shift: Explore Blind Spots with Cross-View Reconstruction for Incomplete Multi-View Clustering
Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective
WATT: Weight Average Test Time Adaptation of CLIP
OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning
Nearly Optimal Approximation of Matrix Functions by the Lanczos Method
Conformal Classification with Equalized Coverage for Adaptively Selected Groups
Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
Theoretical Foundations of Deep Selective State-Space Models
Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
LLM Circuit Analyses Are Consistent Across Training and Scale
LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings
Exploring Fixed Point in Image Editing: Theoretical Support and Convergence Optimization
SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction
Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning
Distributional Preference Alignment of LLMs via Optimal Transport
Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
Can Models Learn Skill Composition from Examples?
FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner
Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes
Multilingual Diversity Improves Vision-Language Representations
Diversity Is Not All You Need: Training A Robust Cooperative Agent Needs Specialist Partners
Enhancing Domain Adaptation through Prompt Gradient Alignment
Fourier Amplitude and Correlation Loss: Beyond Using L2 Loss for Skillful Precipitation Nowcasting
Reliable Learning of Halfspaces under Gaussian Marginals
Grounding Multimodal Large Language Models in Actions
Improved Analysis for Bandit Learning in Matching Markets
SyncTweedies: A General Generative Framework Based on Synchronized Diffusions
PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection
Unveiling the Bias Impact on Symmetric Moral Consistency of Large Language Models
Mixture of Demonstrations for In-Context Learning
Monomial Matrix Group Equivariant Neural Functional Networks
Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
Precipitation Downscaling with Spatiotemporal Video Diffusion
Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking
Scalable DBSCAN with Random Projections
Reconstruction of Manipulated Garment with Guided Deformation Prior
A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective
User-item fairness tradeoffs in recommendations
Transductive Learning is Compact
On the Scalability of Certified Adversarial Robustness with Generated Data
Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction
Learning and Transferring Sparse Contextual Bigrams with Linear Transformers
Resource-Aware Federated Self-Supervised Learning with Global Class Representations
Local to Global: Learning Dynamics and Effect of Initialization for Transformers
Risk-sensitive control as inference with Rényi divergence
GUIDE: Real-Time Human-Shaped Agents
An effective framework for estimating individualized treatment rules
SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models
Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers
2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
CLIPAway: Harmonizing focused embeddings for removing objects via diffusion models
Supervised Kernel Thinning
AED: Adaptable Error Detection for Few-shot Imitation Policy
Active, anytime-valid risk controlling prediction sets
ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
InstructG2I: Synthesizing Images from Multimodal Attributed Graphs
Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes
Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability
Towards Human-AI Complementarity with Prediction Sets
Evaluate then Cooperate: Shapley-based View Cooperation Enhancement for Multi-view Clustering
LOVA3: Learning to Visual Question Answering, Asking and Assessment
FilterNet: Harnessing Frequency Filters for Time Series Forecasting
Enriching Disentanglement: From Logical Definitions to Quantitative Metrics
Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks
UniFL: Improve Latent Diffusion Model via Unified Feedback Learning
Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games
Aligning to Thousands of Preferences via System Message Generalization
F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning
RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation
AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
Prune and Repaint: Content-Aware Image Retargeting for any Ratio
Hallo3D: Multi-Modal Hallucination Detection and Mitigation for Consistent 3D Content Generation
Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning
From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
WelQrate: Defining the Gold Standard in Small Molecule Drug Discovery Benchmarking
Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy
Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation
LocCa: Visual Pretraining with Location-aware Captioners
Soft-Label Integration for Robust Toxicity Classification
Sm: enhanced localization in Multiple Instance Learning for medical imaging classification
GraphVis: Boosting LLMs with Visual Knowledge Graph Integration
Faster Algorithms for User-Level Private Stochastic Convex Optimization
Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
Harmonizing Visual Text Comprehension and Generation
MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model
LinNet: Linear Network for Efficient Point Cloud Representation Learning
GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation
Exploring DCN-like architecture for fast image generation with arbitrary resolution
A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation
Oja's Algorithm for Streaming Sparse PCA
UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation
Can Graph Learning Improve Planning in LLM-based Agents?
Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation
VMamba: Visual State Space Model
Regularized Conditional Diffusion Model for Multi-Task Preference Alignment
SpeedLoader: An I/O efficient scheme for heterogeneous and distributed LLM operation
Amortized Planning with Large-Scale Transformers: A Case Study on Chess
Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention
Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics
MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing
LLaMo: Large Language Model-based Molecular Graph Assistant
Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection?
Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptative Residual Module
WizardArena: Post-training Large Language Models via Simulated Offline Chatbot Arena
MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging
A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
Open-Vocabulary Object Detection via Language Hierarchy
GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning
SpeechAlign: Aligning Speech Generation to Human Preferences
Swift Sampler: Efficient Learning of Sampler by 10 Parameters
Scalable Optimization in the Modular Norm
Déjà Vu Memorization in Vision–Language Models
Conditional Controllable Image Fusion
Grasp as You Say: Language-guided Dexterous Grasp Generation
Upping the Game: How 2D U-Net Skip Connections Flip 3D Segmentation
Generative Hierarchical Materials Search
Self-supervised Transformation Learning for Equivariant Representations
Leveraging Separated World Model for Exploration in Visually Distracted Environments
Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
Understanding Visual Feature Reliance through the Lens of Complexity
A Modular Conditional Diffusion Framework for Image Reconstruction
EfficientCAPER: An End-to-End Framework for Fast and Robust Category-Level Articulated Object Pose Estimation
Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives
Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization
GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance
Universal In-Context Approximation By Prompting Fully Recurrent Models
Physical Consistency Bridges Heterogeneous Data in Molecular Multi-Task Learning
Improving Gloss-free Sign Language Translation by Reducing Representation Density
On Affine Homotopy between Language Encoders
HonestLLM: Toward an Honest and Helpful Large Language Model
Generalized Linear Bandits with Limited Adaptivity
Segmenting Watermarked Texts From Language Models
Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning
FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion
TAPTRv2: Attention-based Position Update Improves Tracking Any Point
DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection
On improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
Understanding Transformer Reasoning Capabilities via Graph Algorithms
4-bit Shampoo for Memory-Efficient Network Training
$\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling
Efficient Lifelong Model Evaluation in an Era of Rapid Progress
CV-VAE: A Compatible Video VAE for Latent Generative Video Models
Improved Generation of Adversarial Examples Against Safety-aligned LLMs
Offline Behavior Distillation
Learning from Pattern Completion: Self-supervised Controllable Generation
DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models
ContextCite: Attributing Model Generation to Context
Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis
Robust Contrastive Multi-view Clustering against Dual Noisy Correspondence
VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time
ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction
E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection
A Swiss Army Knife for Heterogeneous Federated Learning: Flexible Coupling via Trace Norm
I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing
Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching
Learning to Shape In-distribution Feature Space for Out-of-distribution Detection
Voxel Proposal Network via Multi-Frame Knowledge Distillation for Semantic Scene Completion
Bridge the Modality and Capability Gaps in Vision-Language Model Selection
Multiclass Transductive Online Learning
On the cohesion and separability of average-link for hierarchical agglomerative clustering
BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning
Theoretical Analysis of Weak-to-Strong Generalization
A Foundation Model for Zero-shot Logical Query Reasoning
Generalized Fast Exact Conformalization
QBB: Quantization with Binary Bases for LLMs
WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off
Enhancing Chess Reinforcement Learning with Graph Representation
Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality
Towards Stable Representations for Protein Interface Prediction
Almost Surely Asymptotically Constant Graph Neural Networks
Pricing and Competition for Generative AI
Variational Delayed Policy Optimization
GREATS: Online Selection of High-Quality Data for LLM Training in Every Iteration
Neuro-Symbolic Data Generation for Math Reasoning
DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks
Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs
What does guidance do? A fine-grained analysis in a simple setting
RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs
Self-Guided Masked Autoencoder
Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models
On the Surprising Effectiveness of Attention Transfer for Vision Transformers
Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment
Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models
Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional Optimization
Improving Adaptivity via Over-Parameterization in Sequence Models
GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing
Recurrent neural networks: vanishing and exploding gradients are not the end of the story
Revisiting Differentially Private ReLU Regression
Post-Hoc Reversal: Are We Selecting Models Prematurely?
Stochastic Optimal Control for Diffusion Bridges in Function Spaces
Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning
Generalization of Hamiltonian algorithms
Online Bayesian Persuasion Without a Clue
Why Do We Need Weight Decay in Modern Deep Learning?
The Sample Complexity of Gradient Descent in Stochastic Convex Optimization
Online Control in Population Dynamics
Mutli-Armed Bandits with Network Interference
Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms
Disentangling and mitigating the impact of task similarity for continual learning
Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model
Instruction-Guided Visual Masking
Stopping Bayesian Optimization with Probabilistic Regret Bounds
Robust Reinforcement Learning from Corrupted Human Feedback
Can LLMs Implicitly Learn Numeric Parameter Constraints in Data Science APIs?
Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models
UniIF: Unified Molecule Inverse Folding
Easy Regional Contrastive Learning of Expressive Fashion Representations
On Weak Regret Analysis for Dueling Bandits
Statistical Efficiency of Distributional Temporal Difference Learning
How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression
Neural Collapse To Multiple Centers For Imbalanced Data
Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures
Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses
A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems
Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints
CoFie: Learning Compact Neural Surface Representations with Coordinate Fields
Gated Slot Attention for Efficient Linear-Time Sequence Modeling
Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer
Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Loss
Nonlinear dynamics of localization in neural receptive fields
Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records
Neglected Hessian component explains mysteries in sharpness regularization
AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
Where does In-context Learning Happen in Large Language Models?
Online Relational Inference for Evolving Multi-agent Interacting Systems
One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection
A theoretical design of concept sets: improving the predictability of concept bottleneck models
Measuring Per-Unit Interpretability at Scale Without Humans
Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models
Super Consistency of Neural Network Landscapes and Learning Rate Transfer
The Impact of Initialization on LoRA Finetuning Dynamics
Approximation-Aware Bayesian Optimization
Dynamic Conditional Optimal Transport through Simulation-Free Flows
Explaining Datasets in Words: Statistical Models with Natural Language Parameters
Adam with model exponential moving average is effective for nonconvex optimization
Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising
An Analysis of Tokenization: Transformers under Markov Data
Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient
MAmmoTH2: Scaling Instructions from the Web
Bridging Geometric States via Geometric Diffusion Bridge
Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models
CogVLM: Visual Expert for Pretrained Language Models
Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity
Efficiency for Free: Ideal Data Are Transportable Representations
Aligning Audio-Visual Joint Representations with an Agentic Workflow
On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and Games
Distribution Learning with Valid Outputs Beyond the Worst-Case
Any2Policy: Learning Visuomotor Policy with Any-Modality
Length Optimization in Conformal Prediction
Autonomous Driving with Spiking Neural Networks
Generalized Eigenvalue Problems with Generative Priors
The Intelligible and Effective Graph Neural Additive Network
Reranking Laws for Language Generation: A Communication-Theoretic Perspective
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
Optimal Scalarizations for Sublinear Hypervolume Regret
Theoretical Characterisation of the Gauss Newton Conditioning in Neural Networks
Hyperbolic Embeddings of Supervised Models
Bandits with Preference Feedback: A Stackelberg Game Perspective
Generalized Tensor Decomposition for Understanding Multi-Output Regression under Combinatorial Shifts
Clustering in Causal Attention Masking
MSA Generation with Seqs2Seqs Pretraining: Advancing Protein Structure Predictions
Large Language Model Unlearning
Fairness without Harm: An Influence-Guided Active Sampling Approach
Q-VLM: Post-training Quantization for Large Vision-Language Models
Revealing Distribution Discrepancy by Sampling Transfer in Unlabeled Data
Slicing Vision Transformer for Flexible Inference
Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation
Measuring Mutual Policy Divergence for Multi-Agent Sequential Exploration
Understanding Multi-Granularity for Open-Vocabulary Part Segmentation
Hybrid Top-Down Global Causal Discovery with Local Search for Linear and Nonlinear Additive Noise Models
Solving Zero-Sum Markov Games with Continuous State via Spectral Dynamic Embedding
Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective
Low Precision Local Training is Enough for Federated Learning
The Benefits of Balance: From Information Projections to Variance Reduction
An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
Calibrating Reasoning in Language Models with Internal Consistency
Verified Safe Reinforcement Learning for Neural Network Dynamic Models
SEL-BALD: Deep Bayesian Active Learning with Selective Labels
LoTLIP: Improving Language-Image Pre-training for Long Text Understanding
Learning Partitions from Context
Identification of Analytic Nonlinear Dynamical Systems with Non-asymptotic Guarantees
Explanations that reveal all through the definition of encoding
A Compositional Atlas for Algebraic Circuits
In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before an Ongoing Trajectory Terminates
How many classifiers do we need?
TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency Models
Aligner: Efficient Alignment by Learning to Correct
To Believe or Not to Believe Your LLM: Iterative Prompting for Estimating Epistemic Uncertainty
Generalizable Person Re-identification via Balancing Alignment and Uniformity
Spiking Token Mixer: An event-driven friendly Former structure for spiking neural networks
Belief-State Query Policies for User-Aligned POMDPs
DALD: Improving Logits-based Detector without Logits from Black-box LLMs
Towards Scalable and Stable Parallelization of Nonlinear RNNs
Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patching
Biologically Inspired Learning Model for Instructed Vision
Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation
Stochastic Optimization Schemes for Performative Prediction with Nonconvex Loss
Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL
Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
A Unified Framework for 3D Scene Understanding
Active Learning with LLMs for Partially Observed and Cost-Aware Scenarios
Entropy testing and its application to testing Bayesian networks
BAN: Detecting Backdoors Activated by Adversarial Neuron Noise
Enhancing Preference-based Linear Bandits via Human Response Time
Parameterized Approximation Schemes for Fair-Range Clustering
Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees
Randomized Strategic Facility Location with Predictions
Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy
The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domains
Prospective Learning: Learning for a Dynamic Future
General Articulated Objects Manipulation in Real Images via Part-Aware Diffusion Process
Provable and Efficient Dataset Distillation for Kernel Ridge Regression
Learning to Assist Humans without Inferring Rewards
NoiseGPT: Label Noise Detection and Rectification through Probability Curvature
Markov Equivalence and Consistency in Differentiable Structure Learning
Layer-Adaptive State Pruning for Deep State Space Models
Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement
Ensemble sampling for linear bandits: small ensembles suffice
Online Adaptation of Language Models with a Memory of Amortized Contexts
Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning
Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data
Algebraic Positional Encodings
Functionally Constrained Algorithm Solves Convex Simple Bilevel Problem
Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning
Universality in Transfer Learning for Linear Models
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
RETR: Multi-View Radar Detection Transformer for Indoor Perception
Visual Pinwheel Centers Act as Geometric Saliency Detectors
Model-Based Transfer Learning for Contextual Reinforcement Learning
VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning
Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective
Provable Editing of Deep Neural Networks using Parametric Linear Relaxation
Beyond Single Stationary Policies: Meta-Task Players as Naturally Superior Collaborators
Schur Nets: exploiting local structure for equivariance in higher order graph neural networks
Ultrafast classical phylogenetic method beats large protein language models on variant effect prediction
Bayesian Domain Adaptation with Gaussian Mixture Domain-Indexing
Rethinking the Capacity of Graph Neural Networks for Branching Strategy
Newton Informed Neural Operator for Solving Nonlinear Partial Differential Equations
Sketching for Distributed Deep Learning: A Sharper Analysis
Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure
BOLD: Boolean Logic Deep Learning
Pretraining with Random Noise for Fast and Robust Learning without Weight Transport
FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning
A New Neural Kernel Regime: The Inductive Bias of Multi-Task Learning
Visual Prompt Tuning in Null Space for Continual Learning
Asynchronous Perception Machine for Efficient Test Time Training
Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
Learning with Fitzpatrick Losses
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models
Addressing Hidden Confounding with Heterogeneous Observational Datasets for Recommendation
Disentangled Style Domain for Implicit $z$-Watermark Towards Copyright Protection
Understanding Emergent Abilities of Language Models from the Loss Perspective
Beyond task diversity: provable representation transfer for sequential multitask linear bandits
IR-CM: The Fast and General-purpose Image Restoration Method Based on Consistency Model
Continuous Spatiotemporal Events Decoupling through Spike-based Bayesian Computation
Temporally Consistent Atmospheric Turbulence Mitigation with Neural Representations
CIFD: Controlled Information Flow to Enhance Knowledge Distillation
DDK: Distilling Domain Knowledge for Efficient Large Language Models
pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning
Automated Multi-level Preference for MLLMs
Multi-modal Transfer Learning between Biological Foundation Models
MeshFormer : High-Quality Mesh Generation with 3D-Guided Reconstruction Model
Quantum Algorithms for Non-smooth Non-convex Optimization
Hamiltonian Monte Carlo Inference of Marginalized Linear Mixed-Effects Models
SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
MoVA: Adapting Mixture of Vision Experts to Multimodal Context
SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning
Towards Estimating Bounds on the Effect of Policies under Unobserved Confounding
Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization
Learning to Reason via Program Generation, Emulation, and Search
When to Act and When to Ask: Policy Learning With Deferral Under Hidden Confounding
EASI: Evolutionary Adversarial Simulator Identification for Sim-to-Real Transfer
Improved Distribution Matching Distillation for Fast Image Synthesis
Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss
Interpolating Item and User Fairness in Multi-Sided Recommendations
DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization
Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs
HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation
einspace: Searching for Neural Architectures from Fundamental Operations
SnapKV: LLM Knows What You are Looking for Before Generation
Multi-Stage Predict+Optimize for (Mixed Integer) Linear Programs
Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
Zipfian Whitening
Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data
OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries
Classifier-guided Gradient Modulation for Enhanced Multimodal Learning
A Label is Worth A Thousand Images in Dataset Distillation
SS1: Accelerating Inference with Fast and Expressive Sketch Structured Transform
A Layer-Wise Natural Gradient Optimizer for Training Deep Neural Networks
Towards a "Universal Translator" for Neural Dynamics at Single-Cell, Single-Spike Resolution
Phased Consistency Models
Yo'LLaVA: Your Personalized Language and Vision Assistant
Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification
AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
Deep Graph Mating
In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
ShowMaker: Creating High-Fidelity 2D Human Video via Fine-Grained Diffusion Modeling
EMR-Merging: Tuning-Free High-Performance Model Merging
Contextual Linear Optimization with Bandit Feedback
MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space
On the Scalability of GNNs for Molecular Graphs
CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation
General Detection-based Text Line Recognition
Identifying Latent State-Transition Processes for Individualized Reinforcement Learning
IllumiNeRF: 3D Relighting Without Inverse Rendering
Improved Bayes Regret Bounds for Multi-Task Hierarchical Bayesian Bandit Algorithms
Unified Graph Augmentations for Generalized Contrastive Learning on Graphs
AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback
INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling
Public-data Assisted Private Stochastic Optimization: Power and Limitations
Lumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiT
Scaling Retrieval-Based Language Models with a Trillion-Token Datastore
Happy: A Debiased Learning Framework for Continual Generalized Category Discovery
Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization
Autoregressive Policy Optimization for Constrained Allocation Tasks
An Equivalence Between Static and Dynamic Regret Minimization
Action Imitation in Common Action Space for Customized Action Image Synthesis
PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation
Are We on the Right Way for Evaluating Large Vision-Language Models?
Exploring Token Pruning in Vision State Space Models
The Expressive Capacity of State Space Models: A Formal Language Perspective
Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models
Robust Graph Neural Networks via Unbiased Aggregation
LoFiT: Localized Fine-tuning on LLM Representations
Neural Krylov Iteration for Accelerating Linear System Solving
Improving Generalization and Convergence by Enhancing Implicit Regularization
Causal discovery with endogenous context variables
On Feature Learning in Structured State Space Models
MoEUT: Mixture-of-Experts Universal Transformers
Voila-A: Aligning Vision-Language Models with User's Gaze Attention
DiffHammer: Rethinking the Robustness of Diffusion-Based Adversarial Purification
Cross-Device Collaborative Test-Time Adaptation
Minimum Entropy Coupling with Bottleneck
DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
Transformers Represent Belief State Geometry in their Residual Stream
MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank Experts
Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers
Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
Gradient Guidance for Diffusion Models: An Optimization Perspective
MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
AlphaMath Almost Zero: Process Supervision without Process
Learning from Offline Foundation Features with Tensor Augmentations
Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
Continual Counting with Gradual Privacy Expiration
Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction
A Closer Look at AUROC and AUPRC under Class Imbalance
D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models
3D Gaussian Splatting as Markov Chain Monte Carlo
Enhancing Graph Transformers with Hierarchical Distance Structural Encoding
Interfacing Foundation Models' Embeddings
Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning
CAT3D: Create Anything in 3D with Multi-View Diffusion Models
Frequency Adaptive Normalization For Non-stationary Time Series Forecasting
Achieving Tractable Minimax Optimal Regret in Average Reward MDPs
Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization
Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks using the Marginal Likelihood
SymILO: A Symmetry-Aware Learning Framework for Integer Linear Optimization
Optical Diffusion Models for Image Generation
VideoTetris: Towards Compositional Text-to-Video Generation
EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection
Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification
Density-based User Representation using Gaussian Process Regression for Multi-interest Personalized Retrieval
Extending Multi-modal Contrastive Representations
L4GM: Large 4D Gaussian Reconstruction Model
Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting
Multi-Instance Partial-Label Learning with Margin Adjustment
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
MO-DDN: A Coarse-to-Fine Attribute-based Exploration Agent for Multi-Object Demand-driven Navigation
Equivariant spatio-hemispherical networks for diffusion MRI deconvolution
Generating compositional scenes via Text-to-image RGBA Instance Generation
DiffPhyCon: A Generative Approach to Control Complex Physical Systems
Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials
Mind the Graph When Balancing Data for Fairness or Robustness
Pessimistic Backward Policy for GFlowNets
Simple and Effective Masked Diffusion Language Models
Binding in hippocampal-entorhinal circuits enables compositionality in cognitive maps
Progressive Exploration-Conformal Learning for Sparsely Annotated Object Detection in Aerial Images
D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models
Fine Tuning Out-of-Vocabulary Item Recommendation with User Sequence Imagination
RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation
Poseidon: Efficient Foundation Models for PDEs
HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors
Dense Connector for MLLMs
TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
Unveiling User Satisfaction and Creator Productivity Trade-Offs in Recommendation Platforms
Towards Understanding Evolving Patterns in Sequential Data
HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting
Efficient Multi-task LLM Quantization and Serving for Multiple LoRA Adapters
Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations
The Importance of Online Data: Understanding Preference Fine-tuning via Coverage
Humanoid Locomotion as Next Token Prediction
CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning
DeepITE: Designing Variational Graph Autoencoders for Intervention Target Estimation
Metric from Human: Zero-shot Monocular Metric Depth Estimation via Test-time Adaptation
Knowledge Composition using Task Vectors with Learned Anisotropic Scaling
UniAR: A Unified model for predicting human Attention and Responses on visual content
Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
Vision Foundation Model Enables Generalizable Object Pose Estimation
Efficient Prompt Optimization Through the Lens of Best Arm Identification
Base of RoPE Bounds Context Length
On the Parameter Identifiability of Partially Observed Linear Causal Models
Preference Alignment with Flow Matching
RAGraph: A General Retrieval-Augmented Graph Learning Framework
Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability
LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes
Spatio-Spectral Graph Neural Networks
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
The Surprising Effectiveness of SP Voting with Partial Preferences
Mitigating Object Hallucination via Concentric Causal Attention
Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models
An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models
SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization
Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA
Many-Shot In-Context Learning
MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution
Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning
Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
GO4Align: Group Optimization for Multi-Task Alignment
Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry
NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction
Efficient Adversarial Training in LLMs with Continuous Attacks
Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
ReplaceAnything3D: Text-Guided Object Replacement in 3D Scenes with Compositional Scene Representations
SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention
QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint Videos
All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation
Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features
Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models
PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding
Energy-based Epistemic Uncertainty for Graph Neural Networks
Fair and Welfare-Efficient Constrained Multi-Matchings under Uncertainty
MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models
LION: Linear Group RNN for 3D Object Detection in Point Clouds
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization
ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
Adaptable Logical Control for Large Language Models
FNP: Fourier Neural Processes for Arbitrary-Resolution Data Assimilation
ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention
Differentially Private Optimization with Sparse Gradients
DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain
Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training
OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding
Learning-Augmented Algorithms for the Bahncard Problem
Geometric-Averaged Preference Optimization for Soft Preference Labels
Bridging semantics and pragmatics in information-theoretic emergent communication
Replicability in Learning: Geometric Partitions and KKM-Sperner Lemma
Exclusively Penalized Q-learning for Offline Reinforcement Learning
Bayesian-guided Label Mapping for Visual Reprogramming
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
Mobility-LLM: Learning Visiting Intentions and Travel Preference from Human Mobility Data with Large Language Models
Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning
FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributions
Learning-Augmented Algorithms with Explicit Predictors
Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning
$\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation
Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach
Extracting Training Data from Molecular Pre-trained Models
PTQ4DiT: Post-training Quantization for Diffusion Transformers
Global Distortions from Local Rewards: Neural Coding Strategies in Path-Integrating Neural Systems
ActSort: An active-learning accelerated cell sorting algorithm for large-scale calcium imaging datasets
Aligning Large Language Models with Representation Editing: A Control Perspective
Scanning Trojaned Models Using Out-of-Distribution Samples
Why are Visually-Grounded Language Models Bad at Image Classification?
DataComp-LM: In search of the next generation of training sets for language models
Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
Decentralized Noncooperative Games with Coupled Decision-Dependent Distributions
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
What makes unlearning hard and what to do about it
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
Grammar-Aligned Decoding
We use cookies to store which papers have been visited.
I agree
Successful Page Load
NeurIPS uses cookies for essential functions only. We do not sell your personal information.
Our Privacy Policy »
Accept Cookies
We use cookies to store which papers have been visited.
I agree