NeurIPS 2023 Papers

Browse

mini compact detail

Reinforcement Learning with Fast and Forgetful Memory

Generalised f-Mean Aggregation for Graph Neural Networks

A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning

Generalization in the Face of Adaptivity: A Bayesian Perspective

Characterizing Out-of-Distribution Error via Optimal Transport

ChatGPT-Powered Hierarchical Comparisons for Image Classification

Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials

ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise

Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms

SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations

Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models

State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory

SHAP-IQ: Unified Approximation of any-order Shapley Interactions

GLIME: General, Stable and Local LIME Explanation

Reliable learning in challenging environments

Learning with Explanation Constraints

Curvature Filtrations for Graph Generative Model Evaluation

Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression

Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks

Exploring Why Object Recognition Performance Degrades Across Income Levels and Geographies with Factor Annotations

SANFlow: Semantic-Aware Normalizing Flow for Anomaly Detection

Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness

Structured Neural-PI Control with End-to-End Stability and Output Tracking Guarantees

Causal Discovery in Semi-Stationary Time Series

EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding

Extensible Prompts for Language Models on Zero-shot Language Style Customization

Speculative Decoding with Big Little Decoder

Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources

Latent Graph Inference with Limited Supervision

Constructing Non-isotropic Gaussian Diffusion Model Using Isotropic Gaussian Diffusion Model for Image Editing

R-divergence for Estimating Model-oriented Distribution Discrepancy

Hypothesis Selection with Memory Constraints

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions

The Memory-Perturbation Equation: Understanding Model's Sensitivity to Data

Predicting mutational effects on protein-protein binding via a side-chain diffusion probabilistic model

GAUCHE: A Library for Gaussian Processes in Chemistry

Rank-N-Contrast: Learning Continuous Representations for Regression

On Masked Pre-training and the Marginal Likelihood

Text Promptable Surgical Instrument Segmentation with Vision-Language Models

An Inverse Scaling Law for CLIP Training

Generalized test utilities for long-tail performance in extreme multi-label classification

Simultaneous embedding of multiple attractor manifolds in a recurrent neural network using constrained gradient optimization

DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets

Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption

Mathematical Capabilities of ChatGPT

Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks

rPPG-Toolbox: Deep Remote PPG Toolbox

Emergence of Shape Bias in Convolutional Neural Networks through Activation Sparsity

Harnessing the power of choices in decision tree learning

Learning Mixtures of Gaussians Using the DDPM Objective

A Bayesian Approach To Analysing Training Data Attribution In Deep Learning

RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency

The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation

Score-based Source Separation with Applications to Digital Communication Signals

Characterizing the Impacts of Semi-supervised Learning for Weak Supervision

SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality

Wyze Rule: Federated Rule Dataset for Rule Recommendation Benchmarking

Conformal Prediction for Uncertainty-Aware Planning with Diffusion Dynamics Model

Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context

An Information Theory Perspective on Variance-Invariance-Covariance Regularization

Protein Design with Guided Discrete Diffusion

Should We Learn Most Likely Functions or Parameters?

Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution

Learning a 1-layer conditional generative model in total variation

Weitzman's Rule for Pandora's Box with Correlations

Counterfactual Evaluation of Peer-Review Assignment Policies

Feature Selection in the Contrastive Analysis Setting

PAPR: Proximity Attention Point Rendering

A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs

Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information

Deep Patch Visual Odometry

SmoothHess: ReLU Network Feature Interactions via Stein's Lemma

Disentanglement via Latent Quantization

Time Series as Images: Vision Transformer for Irregularly Sampled Time Series

Neural Injective Functions for Multisets, Measures and Graphs via a Finite Witness Theorem

Sampling from Structured Log-Concave Distributions via a Soft-Threshold Dikin Walk

OpenAssistant Conversations - Democratizing Large Language Model Alignment

Pseudo-Likelihood Inference

Easy Learning from Label Proportions

From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces

Exact recovery and Bregman hard clustering of node-attributed Stochastic Block Model

Group Robust Classification Without Any Group Information

MADLAD-400: A Multilingual And Document-Level Large Audited Dataset

Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets

SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs

Adaptive Online Replanning with Diffusion Models

Gigastep - One Billion Steps per Second Multi-agent Reinforcement Learning

Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness

Sequential Preference Ranking for Efficient Reinforcement Learning from Human Feedback

Optimal Learners for Realizable Regression: PAC Learning and Online Learning

Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization

Replicable Clustering

Replicability in Reinforcement Learning

FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow

Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision

Contrastive Moments: Unsupervised Halfspace Learning in Polynomial Time

StableFDG: Style and Attention Based Learning for Federated Domain Generalization

Objaverse-XL: A Universe of 10M+ 3D Objects

Exploring Geometry of Blind Spots in Vision models

What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement.

The Grand Illusion: The Myth of Software Portability and Implications for ML Progress.

Relax, it doesn’t matter how you get there: A new self-supervised approach for multi-timescale behavior analysis

Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models

Should Under-parameterized Student Networks Copy or Average Teacher Weights?

OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents

Scaling Data-Constrained Language Models

Extracting Reward Functions from Diffusion Models

A Unified, Scalable Framework for Neural Population Decoding

Human-Guided Complexity-Controlled Abstractions

A Bayesian Take on Gaussian Process Networks

Optimal Rates for Bandit Nonstochastic Control

Expressivity-Preserving GNN Simulation

Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment

Self-Refine: Iterative Refinement with Self-Feedback

CLadder: A Benchmark to Assess Causal Reasoning Capabilities of Language Models

Differentiable sorting for censored time-to-event data.

Simple and Asymmetric Graph Contrastive Learning without Augmentations

Multiplication-Free Transformer Training via Piecewise Affine Operations

Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception

Trans-Dimensional Generative Modeling via Jump Diffusion Models

Optimal Unbiased Randomizers for Regression with Label Differential Privacy

DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries

Equal Opportunity of Coverage in Fair Regression

MeGraph: Capturing Long-Range Interactions by Alternating Local and Hierarchical Aggregation on Multi-Scaled Graph Hierarchy

COOM: A Game Benchmark for Continual Reinforcement Learning

Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach

Adapting Neural Link Predictors for Data-Efficient Complex Query Answering

EDGI: Equivariant Diffusion for Planning with Embodied Agents

Geometric Algebra Transformer

Variational Gaussian processes for linear inverse problems

Unbiased learning of deep generative models with structured discrete representations

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Variational Inference with Gaussian Score Matching

Provable convergence guarantees for black-box variational inference

Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions

On the Need for a Language Describing Distribution Shifts: Illustrations on Tabular Datasets

Conformal Meta-learners for Predictive Inference of Individual Treatment Effects

PlanE: Representation Learning over Planar Graphs

Zero-One Laws of Graph Neural Networks

Parallel-mentoring for Offline Model-based Optimization

Robust Matrix Sensing in the Semi-Random Model

Plug-and-Play Stability for Intracortical Brain-Computer Interfaces: A One-Year Demonstration of Seamless Brain-to-Text Communication

Personalized Dictionary Learning for Heterogeneous Datasets

Compositional Generalization from First Principles

Alexa Arena: A User-Centric Interactive Platform for Embodied AI

Minimum norm interpolation by perceptra: Explicit regularization and implicit bias

Convolution Monge Mapping Normalization for learning on sleep data

SARAMIS: Simulation Assets for Robotic Assisted and Minimally Invasive Surgery

Riemannian Laplace approximations for Bayesian neural networks

Effective Robustness against Natural Distribution Shifts for Models with Different Training Data

Individualized Dosing Dynamics via Neural Eigen Decomposition

The Utility of “Even if” Semifactual Explanation to Optimise Positive Outcomes

Language Model Alignment with Elastic Reset

Arbitrarily Scalable Environment Generators via Neural Cellular Automata

Neural Data Transformer 2: Multi-context Pretraining for Neural Spiking Activity

Scalable Membership Inference Attacks via Quantile Regression

Cascading Bandits: Optimizing Recommendation Frequency in Delayed Feedback Environments

SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation

Data-Driven Network Neuroscience: On Data Collection and Benchmark

Algorithm Selection for Deep Active Learning with Imbalanced Datasets

Globally solving the Gromov-Wasserstein problem for point clouds in low dimensional Euclidean spaces

Representation Equivalent Neural Operators: a Framework for Alias-free Operator Learning

AMAG: Additive, Multiplicative and Adaptive Graph Neural Network For Forecasting Neuron Activity

Convolutional Neural Operators for robust and accurate learning of PDEs

Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach

DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model

Fair Graph Distillation

PrObeD: Proactive Object Detection Wrapper

L-C2ST: Local Diagnostics for Posterior Approximations in Simulation-Based Inference

Demo2Code: From Summarizing Demonstrations to Synthesizing Code via Extended Chain-of-Thought

RegBN: Batch Normalization of Multimodal Data with Regularization

Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement

Sorting with Predictions

Wasserstein distributional robustness of neural networks

ResMem: Learn what you can and memorize the rest

Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization

Deep Contract Design via Discontinuous Networks

YouTubePD: A Multimodal Benchmark for Parkinson’s Disease Analysis

Sharp Calibrated Gaussian Processes

Diverse Shape Completion via Style Modulated Generative Adversarial Networks

Structure from Duplicates: Neural Inverse Graphics from a Pile of Objects

Distribution-Free Model-Agnostic Regression Calibration via Nonparametric Methods

STREAMER: Streaming Representation Learning and Event Segmentation in a Hierarchical Manner

PDF: Point Diffusion Implicit Function for Large-scale Scene Neural Representation

Secure Out-of-Distribution Task Generalization with Energy-Based Models

TART: A plug-and-play Transformer module for task-agnostic reasoning

Large language models implicitly learn to straighten neural sentence trajectories to construct a predictive representation of natural language.

Robust Second-Order Nonconvex Optimization and Its Application to Low Rank Matrix Sensing

No-regret Algorithms for Fair Resource Allocation

Resolving the Tug-of-War: A Separation of Communication and Learning in Federated Learning

BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information

On the Relationship Between Relevance and Conflict in Online Social Link Recommendations

Lift Yourself Up: Retrieval-augmented Text Generation with Self-Memory

Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models

Neural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential Equations

Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning

Nearly Optimal Bounds for Cyclic Forgetting

Certifiably Robust Graph Contrastive Learning

Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective

Mean-field Langevin dynamics: Time-space discretization, stochastic gradient, and variance reduction

Clifford Group Equivariant Neural Networks

Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection

Kernel-Based Tests for Likelihood-Free Hypothesis Testing

NIS3D: A Completely Annotated Benchmark for Dense 3D Nuclei Image Segmentation

Private Distribution Learning with Public Data: The View from Sample Compression

Distribution Learnability and Robustness

[Re] Numerical influence of ReLU'(0) on backpropagation

An Alternating Optimization Method for Bilevel Problems under the Polyak-Łojasiewicz Condition

SLM: A Smoothed First-Order Lagrangian Method for Structured Constrained Nonconvex Optimization

Faster approximate subgraph counts with privacy

IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI

Estimating Noise Correlations Across Continuous Conditions With Wishart Processes

Binary Classification with Confidence Difference

Zero-sum Polymatrix Markov Games: Equilibrium Collapse and Efficient Computation of Nash Equilibria

Attentive Transfer Entropy to Exploit Transient Emergence of Coupling Effect

POMDP Planning for Object Search in Partially Unknown Environment

Massively Multilingual Corpus of Sentiment Datasets and Multi-faceted Sentiment Classification Benchmark

Fast Asymptotically Optimal Algorithms for Non-Parametric Stochastic Bandits

Non-Asymptotic Analysis of a UCB-based Top Two Algorithm

A Massive Scale Semantic Similarity Dataset of Historical English

PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis

Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory

Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder

Sketching Algorithms for Sparse Dictionary Learning: PTAS and Turnstile Streaming

MADG: Margin-based Adversarial Learning for Domain Generalization

Polynomial-Time Linear-Swap Regret Minimization in Imperfect-Information Sequential Games

CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders

Glance and Focus: Memory Prompting for Multi-Event Video Question Answering

Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization

Accurate Interpolation for Scattered Data through Hierarchical Residual Refinement

Bringing regularized optimal transport to lightspeed: a splitting method adapted for GPUs

Don't be so Monotone: Relaxing Stochastic Line Search in Over-Parameterized Models

Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures

Breadcrumbs to the Goal: Supervised Goal Selection from Human-in-the-Loop Feedback

Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games

Convergence analysis of ODE models for accelerated first-order methods via positive semidefinite kernels

Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation

On the Sublinear Regret of GP-UCB

Optimal Treatment Allocation for Efficient Policy Evaluation in Sequential Decision Making

Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems

Test-Time Distribution Normalization for Contrastively Learned Visual-language Models

DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models

Global Structure-Aware Diffusion Process for Low-light Image Enhancement

Video Dynamics Prior: An Internal Learning Approach for Robust Video Enhancements

Described Object Detection: Liberating Object Detection with Flexible Expressions

Maximum Independent Set: Self-Training through Dynamic Programming

On the Convergence of Encoder-only Shallow Transformers

On Measuring Fairness in Generative Models

Adversarial Counterfactual Environment Model Learning

A State Representation for Diminishing Rewards

Successor-Predecessor Intrinsic Exploration

MLFMF: Data Sets for Machine Learning for Mathematical Formalization

Implicit Variational Inference for High-Dimensional Posteriors

Distributional Pareto-Optimal Multi-Objective Reinforcement Learning

Quantum Bayesian Optimization

Quasi-Monte Carlo Graph Random Features

Operation-Level Early Stopping for Robustifying Differentiable NAS

Color Equivariant Convolutional Networks

Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation

Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces

Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator

Test-time Training for Matching-based Video Object Segmentation

Geometry-Aware Adaptation for Pretrained Models

FlowPG: Action-constrained Policy Gradient with Normalizing Flows

Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline

To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis

Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning

Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning

Generator Born from Classifier

Precise asymptotic generalization for multiclass classification with overparameterized linear models

Complexity Matters: Rethinking the Latent Space for Generative Modeling

Learning Mask-aware CLIP Representations for Zero-Shot Segmentation

Many-body Approximation for Non-negative Tensors

REFINE: A Fine-Grained Medication Recommendation System Using Deep Learning and Personalized Drug Interaction Modeling

NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function

A High-Resolution Dataset for Instance Detection with Multi-View Object Capture

DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model

Scaling laws for language encoding models in fMRI

Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback

ViSt3D: Video Stylization with 3D CNN

Bootstrapping Vision-Language Learning with Decoupled Language Pre-training

LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day

Anytime-Competitive Reinforcement Learning with Policy Prior

Recurrent Temporal Revision Graph Networks

Learning Time-Invariant Representations for Individual Neurons from Population Dynamics

New Bounds for Hyperparameter Tuning of Regression Problems Across Instances

Lookaround Optimizer: $k$ steps around, 1 step average

Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints

Score-based Data Assimilation

k-Median Clustering via Metric Embedding: Towards Better Initialization with Differential Privacy

Accelerated On-Device Forward Neural Network Training with Module-Wise Descending Asynchronism

OpenDataVal: a Unified Benchmark for Data Valuation

Large language models transition from integrating across position-yoked, exponential windows to structure-yoked, power-law windows

Assumption violations in causal discovery and the robustness of score matching

Leveraging sparse and shared feature activations for disentangled representation learning

ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training

Latent Space Translation via Semantic Alignment

Rotating Features for Object Discovery

Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling

Provably Safe Reinforcement Learning with Step-wise Violation Constraints

Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization

Structural Pruning for Diffusion Models

LLM-Pruner: On the Structural Pruning of Large Language Models

Learning DAGs from Data with Few Root Causes

Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting

Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints

Grammar Prompting for Domain-Specific Language Generation with Large Language Models

LEACE: Perfect linear concept erasure in closed form

The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs

Emergent and Predictable Memorization in Large Language Models

General Munchausen Reinforcement Learning with Tsallis Kullback-Leibler Divergence

Stable Diffusion is Unstable

Automatic Integration for Spatiotemporal Neural Point Processes

TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs

Outlier-Robust Gromov-Wasserstein for Graph Data

Improving neural network representations using human similarity judgments

Does progress on ImageNet transfer to real-world datasets?

HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork

InsActor: Instruction-driven Physics-based Characters

Mutual Information Regularized Offline Reinforcement Learning

Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback

Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value

Continuous-time Analysis of Anchor Acceleration

Accelerating Value Iteration with Anchoring

DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology

RH-BrainFS: Regional Heterogeneous Multimodal Brain Networks Fusion Strategy

MGDD: A Meta Generator for Fast Dataset Distillation

Curriculum Learning With Infant Egocentric Videos

HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution

SustainGym: Reinforcement Learning Environments for Sustainable Energy Systems

When are ensembles really effective?

A Heavy-Tailed Algebra for Probabilistic Programming

Exploring and Interacting with the Set of Good Sparse Generalized Additive Models

This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations

The Rashomon Importance Distribution: Getting RID of Unstable, Single Model-based Variable Importance

Visual Instruction Inversion: Image Editing via Image Prompting

Transformers learn to implement preconditioned gradient descent for in-context learning

On the impact of activation and normalization in obtaining isometric embeddings at initialization

PreDiff: Precipitation Nowcasting with Latent Diffusion Models

Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting

Frequency-Enhanced Data Augmentation for Vision-and-Language Navigation

GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients

A Theory of Transfer-Based Black-Box Attacks: Explanation and Implications

Smoothed Analysis of Sequential Probability Assignment

One Less Reason for Filter Pruning: Gaining Free Adversarial Robustness with Structured Grouped Kernel Pruning

Compression with Bayesian Implicit Neural Representations

Unsupervised Semantic Correspondence Using Stable Diffusion

A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction

Gaussian Mixture Solvers for Diffusion Models

Efficient Diffusion Policies For Offline Reinforcement Learning

On Evaluating Adversarial Robustness of Large Vision-Language Models

On Calibrating Diffusion Probabilistic Models

CBD: A Certified Backdoor Detector Based on Local Dominant Probability

3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection

Diffusion Probabilistic Models for Structured Node Classification

On the Convergence of Black-Box Variational Inference

On Learning Necessary and Sufficient Causal Graphs

Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games

A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm

Near-Optimal Algorithms for Gaussians with Huber Contamination: Mean Estimation and Linear Regression

Optimistic Rates for Multi-Task Representation Learning

Multi-Agent Learning with Heterogeneous Linear Contextual Bandits

TOA: Task-oriented Active VQA

HIQL: Offline Goal-Conditioned RL with Latent States as Actions

TradeMaster: A Holistic Quantitative Trading Platform Empowered by Reinforcement Learning

EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset

RealTime QA: What's the Answer Right Now?

Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation

H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Towards Optimal Caching and Model Selection for Large Model Inference

Efficient Online Clustering with Moving Costs

Keypoint-Augmented Self-Supervised Learning for Medical Image Segmentation with Limited Annotation

f-Policy Gradients: A General Framework for Goal-Conditioned RL using f-Divergences

Analyzing Generalization of Neural Networks through Loss Path Kernels

DISCO-10M: A Large-Scale Music Dataset

Kernel Stein Discrepancy thinning: a theoretical perspective of pathologies and a practical fix with regularization

Large Language Models are Visual Reasoning Coordinators

Visual Instruction Tuning

Scaling Laws for Hyperparameter Optimization

Adversarial Learning for Feature Shift Detection and Correction

Unlocking Deterministic Robustness Certification on ImageNet

Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees

Evaluating the Moral Beliefs Encoded in LLMs

The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data Only

A Competitive Algorithm for Agnostic Active Learning

For SALE: State-Action Representation Learning for Deep Reinforcement Learning

Thought Cloning: Learning to Think while Acting by Imitating Human Thinking

Federated Multi-Objective Learning

Collapsed Inference for Bayesian Deep Learning

Continuous-Time Functional Diffusion Processes

Self-Supervised Learning with Lie Symmetries for Partial Differential Equations

$p$-Poisson surface reconstruction in curl-free flow from point clouds

Are Emergent Abilities of Large Language Models a Mirage?

Randomized Sparse Neural Galerkin Schemes for Solving Evolution Equations with Deep Networks

Your representations are in the network: composable and parallel adaptation for large scale models

Online Nonstochastic Model-Free Reinforcement Learning

HeadSculpt: Crafting 3D Head Avatars with Text

Object-Centric Slot Diffusion

Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense

MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data

Static and Sequential Malicious Attacks in the Context of Selective Forgetting

Learning to Group Auxiliary Datasets for Molecule

TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery

Learning via Wasserstein-Based High Probability Generalisation Bounds

Large Language Models are Fixated by Red Herrings: Exploring Creative Problem Solving and Einstellung Effect using the Only Connect Wall Dataset

Estimating Riemannian Metric with Noise-Contaminated Intrinsic Distance

Benchmarking Distribution Shift in Tabular Data with TableShift

Humans in Kitchens: A Dataset for Multi-Person Human Motion Forecasting with Scene Context

Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

Counterfactually Comparing Abstaining Classifiers

Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms

Thrust: Adaptively Propels Large Language Models with External Knowledge

Creating Multi-Level Skill Hierarchies in Reinforcement Learning

Neural Lighting Simulation for Urban Scenes

Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions

Bicriteria Approximation Algorithms for the Submodular Cover Problem

Fair Adaptive Experiments

MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation

Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition

Are Vision Transformers More Data Hungry Than Newborn Visual Systems?

RETVec: Resilient and Efficient Text Vectorizer

An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits

Hierarchical Randomized Smoothing

(Provable) Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More

Multi-Head Adapter Routing for Cross-Task Generalization

Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions

Focused Transformer: Contrastive Training for Context Scaling

Faster Margin Maximization Rates for Generic Optimization Methods

OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects

Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models

Correlation Aware Sparsified Mean Estimation Using Random Projection

Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors

Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation

Policy Space Diversity for Non-Transitive Games

Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games

Language Models can Solve Computer Tasks

Team-PSRO for Learning Approximate TMECor in Large Team Games via Cooperative Reinforcement Learning

Safety Verification of Decision-Tree Policies in Continuous Time

Necessary and Sufficient Conditions for Optimal Decision Trees using Dynamic Programming

Are These the Same Apple? Comparing Images Based on Object Intrinsics

CHAMMI: A benchmark for channel-adaptive models in microscopy imaging

Solving Inverse Physics Problems with Score Matching

Matrix Compression via Randomized Low Rank and Low Precision Factorization

Spatial-frequency channels, shape bias, and adversarial robustness

Sparsity-Preserving Differentially Private Training of Large Embedding Models

SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds

Efficient Beam Tree Recursion

Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goal

Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability

Self-Correcting Bayesian Optimization through Bayesian Active Learning

Optimization of Inter-group criteria for clustering with minimum size constraints

SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics

Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network

Learning Invariant Representations with a Nonparametric Nadaraya-Watson Head

Scientific Document Retrieval using Multi-level Aspect-based Queries

Neural Graph Generation from Graph Statistics

Augmentation-free Dense Contrastive Distillation for Efficient Semantic Segmentation

Fair Canonical Correlation Analysis

Max-Margin Token Selection in Attention Mechanism

Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement

Distributed Personalized Empirical Risk Minimization

Geometry-Informed Neural Operator for Large-Scale 3D PDEs

Mixture Weight Estimation and Model Prediction in Multi-source Multi-target Domain Adaptation

Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models

Order Matters in the Presence of Dataset Imbalance for Multilingual Learning

Active Vision Reinforcement Learning under Limited Visual Observability

Cognitive Model Discovery via Disentangled RNNs

An NLP Benchmark Dataset for Assessing Corporate Climate Policy Engagement

Tools for Verifying Neural Models' Training Data

Amazon-M2: A Multilingual Multi-locale Shopping Session Dataset for Recommendation and Text Generation

Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?

Towards Label Position Bias in Graph Neural Networks

Dynamic Pricing and Learning with Bayesian Persuasion

Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency

From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion

DICES Dataset: Diversity in Conversational AI Evaluation for Safety

On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence

Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack

Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards

Task-aware Distributed Source Coding under Dynamic Bandwidth

Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark

HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation

Module-wise Adaptive Distillation for Multimodality Foundation Models

Structured Federated Learning through Clustered Additive Modeling

Label Poisoning is All You Need

Evaluating Self-Supervised Learning for Molecular Graph Embeddings

No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models

Dis-inhibitory neuronal circuits can control the sign of synaptic plasticity

Reliable Off-Policy Learning for Dosage Combinations

Tester-Learners for Halfspaces: Universal Algorithms

Agnostically Learning Single-Index Models using Omnipredictors

Stability Guarantees for Feature Attributions with Multiplicative Smoothing

Energy Transformer

A Combinatorial Algorithm for Approximating the Optimal Transport in the Parallel and MPC Settings

When Demonstrations meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning

Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization

DISCS: A Benchmark for Discrete Sampling

Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis

Uncovering motifs of concurrent signaling across multiple neuronal populations

Long Sequence Hopfield Memory

Data Portraits: Recording Foundation Model Training Data

PID-Inspired Inductive Biases for Deep Reinforcement Learning in Partially Observable Control Tasks

Grassmann Manifold Flows for Stable Shape Generation

Bayesian target optimisation for high-precision holographic optogenetics

EvoPrompting: Language Models for Code-Level Neural Architecture Search

Online Adaptive Policy Selection in Time-Varying Systems: No-Regret via Contractive Perturbations

Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks

Alignment with human representations supports robust few-shot learning

TD Convergence: An Optimization Perspective

BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimization

Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration

PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation

Prediction and Control in Continual Reinforcement Learning

Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees

Interpretability at Scale: Identifying Causal Mechanisms in Alpaca

Future-Dependent Value-Based Off-Policy Evaluation in POMDPs

Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage

Adversarial Robustness through Random Weight Sampling

Polyhedron Attention Module: Learning Adaptive-order Interactions

Distributed Inference and Fine-tuning of Large Language Models Over The Internet

Training Energy-Based Normalizing Flow with Score-Matching Objectives

Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL

A Unified Fast Gradient Clipping Framework for DP-SGD

Large-Scale Distributed Learning via Private On-Device LSH

SEGA: Instructing Text-to-Image Models using Semantic Guidance

Neural Foundations of Mental Simulation: Future Prediction of Latent Representations on Dynamic Scenes

Imitation Learning from Vague Feedback

UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models

On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling and Beyond

The Tunnel Effect: Building Data Representations in Deep Neural Networks

Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method

Reverse Engineering Self-Supervised Learning

Simplifying Neural Network Training Under Class Imbalance

Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning

LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios

DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting

Fast Trainable Projection for Robust Fine-tuning

Characteristic Circuits

Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costs

OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling

One Fits All: Power General Time Series Analysis by Pretrained LM

Effective Bayesian Heteroscedastic Regression with Deep Neural Networks

Feature Likelihood Score: Evaluating the Generalization of Generative Models Using Samples

Federated Linear Bandits with Finite Adversarial Actions

Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities

Training on Foveated Images Improves Robustness to Adversarial Attacks

An information-theoretic quantification of the content of communication between brain regions

Concentration analysis of multivariate elliptic diffusions

DELTA: Diverse Client Sampling for Fasting Federated Learning

Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach

Monte Carlo Tree Search with Boltzmann Exploration

Operator Learning with Neural Fields: Tackling PDEs on General Geometries

On the Variance, Admissibility, and Stability of Empirical Risk Minimization

Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment

Simple, Scalable and Effective Clustering via One-Dimensional Projections

DäRF: Boosting Radiance Fields from Sparse Input Views with Monocular Depth Adaptation

Revisiting Logistic-softmax Likelihood in Bayesian Meta-Learning for Few-Shot Classification

Multi Time Scale World Models

Utilitarian Algorithm Configuration

Reduced Policy Optimization for Continuous Control with Hard Constraints

Two Sides of The Same Coin: Bridging Deep Equilibrium Models and Neural ODEs via Homotopy Continuation

SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning

Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks

Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis

Separable Physics-Informed Neural Networks

Mip-Grid: Anti-aliased Grid Representations for Neural Radiance Fields

Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills

Adapting to Continuous Covariate Shift via Online Density Ratio Estimation

Online (Multinomial) Logistic Bandit: Improved Regret and Constant Computation Cost

Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers

The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit

Scaling MLPs: A Tale of Inductive Bias

Improving Adversarial Robustness via Information Bottleneck Distillation

Lung250M-4B: A Combined 3D Dataset for CT- and Point Cloud-Based Intra-Patient Lung Registration

Functional Equivalence and Path Connectivity of Reducible Hyperbolic Tangent Networks

Holistic Evaluation of Text-to-Image Models

Intervention Generalization: A View from Factor Graph Models

QATCH: Benchmarking SQL-centric tasks with Table Representation Learning Models on Your Data

Nash Regret Guarantees for Linear Bandits

Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures

DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics

Neural Lad: A Neural Latent Dynamics Framework for Times Series Modeling

Emergent Communication in Interactive Sketch Question Answering

Boundary Guided Learning-Free Semantic Control with Diffusion Models

Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data

Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark

TRIAGE: Characterizing and auditing training data for improved regression

The Waymo Open Sim Agents Challenge

Improving Graph Matching with Positional Reconstruction Encoder-Decoder Network

Metropolis Sampling for Constrained Diffusion Models

Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion Model

Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms

Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering

[Re] Exploring the Role of Grammar and Word Choice in Bias Toward African American English (AAE) in Hate Speech Classification

Learning Transformer Programs

Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control

False Discovery Proportion control for aggregated Knockoffs

Posterior Sampling for Competitive RL: Function Approximation and Partial Observation

Digital Typhoon: Long-term Satellite Image Dataset for the Spatio-Temporal Modeling of Tropical Cyclones

Online Inventory Problems: Beyond the i.i.d. Setting with Online Convex Optimization

AiluRus: A Scalable ViT Framework for Dense Prediction

Minimum Description Length and Generalization Guarantees for Representation Learning

CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inference

Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time

ANPL: Towards Natural Programming with Interactive Decomposition

Diffused Redundancy in Pre-trained Representations

Crystal Structure Prediction by Joint Equivariant Diffusion

CSMeD: Bridging the Dataset Gap in Automated Citation Screening for Systematic Literature Reviews

User-Level Differential Privacy With Few Examples Per User

Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer

Benchmarking Foundation Models with Language-Model-as-an-Examiner

Physics-Informed Bayesian Optimization of Variational Quantum Circuits

[Re] On Explainability of Graph Neural Networks via Subgraph Explorations

CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society

Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings

DynaDojo: An Extensible Platform for Benchmarking Scaling in Dynamical System Identification

CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data

Multimodal Deep Learning Model Unveils Behavioral Dynamics of V1 Activity in Freely Moving Mice

Analyzing Vision Transformers for Image Classification in Class Embedding Space

Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models

Efficient Exploration in Continuous-time Model-based Reinforcement Learning

Boosting Spectral Clustering on Incomplete Data via Kernel Correction and Affinity Learning

Natural Language Instruction-following with Task-related Language Development and Translation

Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations

DrugCLIP: Contrasive Protein-Molecule Representation Learning for Virtual Screening

Toward Understanding Generative Data Augmentation

Stochastic Approximation Approaches to Group Distributionally Robust Optimization

Multi-task Representation Learning for Pure Exploration in Bilinear Bandits

Faith and Fate: Limits of Transformers on Compositionality

SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

Interpreting Unsupervised Anomaly Detection in Security via Rule Extraction

On the Last-iterate Convergence in Time-varying Zero-sum Games: Extra Gradient Succeeds where Optimism Fails

SHOT: Suppressing the Hessian along the Optimization Trajectory for Gradient-Based Meta-Learning

Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transport

Brain encoding models based on multimodal transformers can transfer across language and vision

Similarity-based cooperative equilibrium

Multi-resolution Spectral Coherence for Graph Generation with Score-based Diffusion

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals

SPRING: Studying Papers and Reasoning to play Games

Learning Large Graph Property Prediction via Graph Segment Training

Swarm Reinforcement Learning for Adaptive Mesh Refinement

Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift

Large Language Models as Commonsense Knowledge for Large-Scale Task Planning

Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback

Exploring Loss Functions for Time-based Training Strategy in Spiking Neural Networks

Finding Safe Zones of Markov Decision Processes Policies

Towards Optimal Effective Resistance Estimation

Adaptive Uncertainty Estimation via High-Dimensional Testing on Latent Representations

Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation

SwiFT: Swin 4D fMRI Transformer

CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning

Hypervolume Maximization: A Geometric View of Pareto Set Learning

LoRA: A Logical Reasoning Augmented Dataset for Visual Question Answering

Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning

Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks

SLaM: Student-Label Mixing for Distillation with Unlabeled Examples

NeRF Revisited: Fixing Quadrature Instability in Volume Rendering

Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance

NAP: Neural 3D Articulated Object Prior

Resilient Constrained Learning

MotionGPT: Human Motion as a Foreign Language

Maximization of Average Precision for Deep Learning with Adversarial Ranking Robustness

Context-PIPs: Persistent Independent Particles Demands Context Features

$\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning

Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion

Training Transformers with 4-bit Integers

Large Language Models of Code Fail at Completing Code with Potential Bugs

Counterfactual Memorization in Neural Language Models

Exploiting Correlated Auxiliary Feedback in Parameterized Bandits

On the Robustness of Removal-Based Feature Attributions

Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data

Optimal and Fair Encouragement Policy Evaluation and Learning

DP-Mix: Mixup-based Data Augmentation for Differentially Private Learning

Neural Fields with Hard Constraints of Arbitrary Differential Order

ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram

Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch

Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Paths

Wasserstein Quantum Monte Carlo: A Novel Approach for Solving the Quantum Many-Body Schrödinger Equation

Flow Factorized Representation Learning

Lie Point Symmetry and Physics-Informed Networks

The Distortion of Binomial Voting Defies Expectation

LayoutGPT: Compositional Visual Planning and Generation with Large Language Models

Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning

Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information

Two-Stage Learning to Defer with Multiple Experts

Switching Autoregressive Low-rank Tensor Models

Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets

MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks

Generative Category-level Object Pose Estimation via Diffusion Models

The Behavior and Convergence of Local Bayesian Optimization

Experiment Planning with Function Approximation

Supervised Pretraining Can Learn In-Context Reinforcement Learning

Perception Test: A Diagnostic Benchmark for Multimodal Video Models

Efficient Learning of Linear Graph Neural Networks via Node Subsampling

Should I Stop or Should I Go: Early Stopping with Heterogeneous Populations

Hierarchical Gaussian Mixture based Task Generative Model for Robust Meta-Learning

GlyphControl: Glyph Conditional Control for Visual Text Generation

Adversarial Model for Offline Reinforcement Learning

Survival Instinct in Offline Reinforcement Learning

Convolutional State Space Models for Long-Range Spatiotemporal Modeling

Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory

On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm

Bicriteria Multidimensional Mechanism Design with Side Information

Computing Approximate $\ell_p$ Sensitivities

Riemannian Projection-free Online Learning

Representation Learning via Consistent Assignment of Views over Random Partitions

Inferring Hybrid Neural Fluid Fields from Videos

VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation

A Randomized Approach to Tight Privacy Accounting

Bridging Discrete and Backpropagation: Straight-Through and Beyond

Semi-Implicit Denoising Diffusion Models (SIDDMs)

Textually Pretrained Speech Language Models

Simple and Controllable Music Generation

Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning

Revisiting the Minimalist Approach to Offline Reinforcement Learning

Katakomba: Tools and Benchmarks for Data-Driven NetHack

An Optimal Structured Zeroth-order Algorithm for Non-smooth Optimization

QuACK: Accelerating Gradient-Based Quantum Optimization with Koopman Operator Learning

Reproducibility Study of ”CartoonX: Cartoon Explanations of Image Classifiers”

Reproducibility study of the Fairness-enhanced Node Representation Learning

Small Transformers Compute Universal Metric Embeddings

Explain Any Concept: Segment Anything Meets Concept-Based Explanation

Topological RANSAC for instance verification and retrieval without fine-tuning

Honesty Is the Best Policy: Defining and Mitigating AI Deception

Parameterizing Context: Unleashing the Power of Parameter-Efficient Fine-Tuning and In-Context Tuning for Continual Table Semantic Parsing

Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks

NAS-X: Neural Adaptive Smoothing via Twisting

SatLM: Satisfiability-Aided Language Models Using Declarative Prompting

Neural Processes with Stability

Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization

Q-DM: An Efficient Low-bit Quantized Diffusion Model

The Crucial Role of Normalization in Sharpness-Aware Minimization

Probabilistic Weight Fixing: Large-scale training of neural network weight uncertainties for quantisation.

Fast Optimal Locally Private Mean Estimation via Random Projections

Class-Distribution-Aware Pseudo-Labeling for Semi-Supervised Multi-Label Learning

Online Ad Procurement in Non-stationary Autobidding Worlds

Revisiting Implicit Differentiation for Learning Problems in Optimal Control

Certification of Distributional Individual Fairness

A Theory of Multimodal Learning

FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning

On student-teacher deviations in distillation: does it pay to disobey?

Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models

Anytime Model Selection in Linear Bandits

Greedy Poisson Rejection Sampling

[Re] VAE Approximation Error: ELBO and Exponential Families

Computing a human-like reaction time metric from stable recurrent vision models

Diffusion Schrödinger Bridge Matching

When Do Graph Neural Networks Help with Node Classification? Investigating the Homophily Principle on Node Distinguishability

A Definition of Continual Reinforcement Learning

Unifying Predictions of Deterministic and Stochastic Physics in Mesh-reduced Space with Sequential Flow Generative Model

On Separate Normalization in Self-supervised Transformers

Neural Circuits for Fast Poisson Compressed Sensing in the Olfactory Bulb

Cal-DETR: Calibrated Detection Transformer

[Re] Hierarchical Shrinkage: Improving the Accuracy and Interpretability of Tree-Based Methods

Learning Curves for Deep Structured Gaussian Feature Models

Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective

A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs

Lo-Hi: Practical ML Drug Discovery Benchmark

MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing

AllSim: Simulating and Benchmarking Resource Allocation Policies in Multi-User Systems

Learning Energy-based Model via Dual-MCMC Teaching

Uncertainty Quantification over Graph with Conformalized Graph Neural Networks

Nonparametric Boundary Geometry in Physics Informed Deep Learning

Towards a Unified Analysis of Kernel-based Methods Under Covariate Shift

Scalable Fair Influence Maximization

On-the-Fly Adapting Code Summarization on Trainable Cost-Effective Language Models

On Single-Index Models beyond Gaussian Data

TextDiffuser: Diffusion Models as Text Painters

VTaC: A Benchmark Dataset of Ventricular Tachycardia Alarms from ICU Monitors

Ess-InfoGAIL: Semi-supervised Imitation Learning from Imbalanced Demonstrations

Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics

Online Corrupted User Detection and Regret Minimization

Domain Agnostic Fourier Neural Operators

Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models

MomentDiff: Generative Video Moment Retrieval from Random to Real

Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation

Adversarially Robust Learning with Uncertain Perturbation Sets

Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimization

Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy

Neural-Logic Human-Object Interaction Detection

Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization

Multi-modal Queried Object Detection in the Wild

Optimal cross-learning for contextual bandits with unknown context distributions

Communication-Efficient Federated Bilevel Optimization with Global and Local Lower Level Problems

Imagine That! Abstract-to-Intricate Text-to-Image Synthesis with Scene Graph Hallucination Diffusion

TWIGMA: A dataset of AI-Generated Images with Metadata From Twitter

Better Correlation and Robustness: A Distribution-Balanced Self-Supervised Learning Framework for Automatic Dialogue Evaluation

“Why Not Looking backward?” A Robust Two-Step Method to Automatically Terminate Bayesian Optimization

What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models

[Re] CrossWalk: Fairness-enhanced Node Representation Learning

Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neural Networks without Weight Symmetry

Causal Interpretation of Self-Attention in Pre-Trained Transformers

RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing

A Unified Approach for Maximizing Continuous DR-submodular Functions

Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalization

EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding

OpenProteinSet: Training data for structural biology at scale

How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization

Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds

Bounded rationality in structured density estimation

Self-Predictive Universal AI

NetHack is Hard to Hack

Causal Fairness for Outcome Control

Beyond Confidence: Reliable Models Should Also Consider Atypicality

Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking

Game Solving with Online Fine-Tuning

Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmark

Time-uniform confidence bands for the CDF under nonstationarity

Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt

An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient

Learning Generalizable Agents via Saliency-guided Features Decorrelation

Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysis

Equivariant Flow Matching with Hybrid Probability Transport for 3D Molecule Generation

Decentralized Matrix Sensing: Statistical Guarantees and Fast Convergence

Demystifying the Optimal Performance of Multi-Class Classification

From Trainable Negative Depth to Edge Heterophily in Graphs

Ensemble-based Deep Reinforcement Learning for Vehicle Routing Problems under Distribution Shift

Relative Entropic Optimal Transport: a (Prior-aware) Matching Perspective to (Unbalanced) Classification

DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction

Double Gumbel Q-Learning

Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer

Worst-case Performance of Popular Approximate Nearest Neighbor Search Implementations: Guarantees and Limitations

Meta-AdaM: An Meta-Learned Adaptive Optimizer with Momentum for Few-Shot Learning

An Efficient and Robust Framework for Approximate Nearest Neighbor Search with Attribute Constraint

VOCE: Variational Optimization with Conservative Estimation for Offline Safe Reinforcement Learning

Aggregating Capacity in FL through Successive Layer Training for Computationally-Constrained Devices

Differentiable Clustering with Perturbed Spanning Forests

DRAUC: An Instance-wise Distributionally Robust AUC Optimization Framework

Transfer learning for atomistic simulations using GNNs and kernel mean embeddings

Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering

On the Size and Approximation Error of Distilled Datasets

StyleGAN knows Normal, Depth, Albedo, and More

Comparing Apples to Oranges: Learning Similarity Functions for Data Produced by Different Distributions

Doubly Robust Augmented Transfer for Meta-Reinforcement Learning

Template-free Articulated Neural Point Clouds for Reposable View Synthesis

Prototypical Variational Autoencoder for 3D Few-shot Object Detection

Unexpected Improvements to Expected Improvement for Bayesian Optimization

Triangulation Residual Loss for Data-efficient 3D Pose Estimation

Conditional Matrix Flows for Gaussian Graphical Models

Learning Re-sampling Methods with Parameter Attribution for Image Super-resolution

SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models

Norm-guided latent space exploration for text-to-image generation

Scaling Riemannian Diffusion Models

Supply-Side Equilibria in Recommender Systems

Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks

Unleash the Potential of Image Branch for Cross-modal 3D Object Detection

Adaptive whitening with fast gain modulation and slow synaptic plasticity

Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features

FAMO: Fast Adaptive Multitask Optimization

Optimal Treatment Regimes for Proximal Causal Learning

Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning

CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation

Errors-in-variables Fr\'echet Regression with Low-rank Covariate Approximation

Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision

Conditional Mutual Information for Disentangled Representations in Reinforcement Learning

Birth of a Transformer: A Memory Viewpoint

Swap Agnostic Learning, or Characterizing Omniprediction via Multicalibration

Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems

FaceComposer: A Unified Model for Versatile Facial Content Creation

Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs

A Unified Discretization Framework for Differential Equation Approach with Lyapunov Arguments for Convex Optimization

Fair Allocation of Indivisible Chores: Beyond Additive Costs

Towards Better Dynamic Graph Learning: New Architecture and Unified Library

Orthogonal Non-negative Tensor Factorization based Multi-view Clustering

Improving *day-ahead* Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context

Estimating Koopman operators with sketching to provably learn large scale dynamical systems

Federated Learning with Bilateral Curation for Partially Class-Disjoint Data

Expert load matters: operating networks at high accuracy and low manual effort

Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms

Language-driven Scene Synthesis using Multi-conditional Diffusion Model

Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation

A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)

Minimax Optimal Rate for Parameter Estimation in Multivariate Deviated Models

Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models

Fully Dynamic $k$-Clustering in $\tilde O(k)$ Update Time

A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspective

Structured Voronoi Sampling

Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity

Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications

Sample-efficient Multi-objective Molecular Optimization with GFlowNets

Small Total-Cost Constraints in Contextual Bandits with Knapsacks, with Application to Fairness

Test-Time Amendment with a Coarse Classifier for Fine-Grained Classification

On Generalization Bounds for Projective Clustering

Focus Your Attention when Few-Shot Classification

BanditPAM++: Faster $k$-medoids Clustering

(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability

Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences

Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Method

Learning List-Level Domain-Invariant Representations for Ranking

Distributional Learning of Variational AutoEncoder: Application to Synthetic Data Generation

Contrastive Sampling Chains in Diffusion Models

SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting

Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks

GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph

Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners

Can semi-supervised learning use all the data effectively? A lower bound perspective

Enhancing Knowledge Transfer for Task Incremental Learning with Data-free Subnetwork

Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign?

Transformers over Directed Acyclic Graphs

Improving Self-supervised Molecular Representation Learning using Persistent Homology

CELLE-2: Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transformer

Implicit Regularization in Over-Parameterized Support Vector Machine

Spatio-Angular Convolutions for Super-resolution in Diffusion MRI

Connecting Pre-trained Language Model and Downstream Task via Properties of Representation

Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data

Complex-valued Neurons Can Learn More but Slower than Real-valued Neurons via Gradient Descent

Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial?

Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts

Incentivized Communication for Federated Bandits

Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach

From Distribution Learning in Training to Gradient Search in Testing for Combinatorial Optimization

SatBird: a Dataset for Bird Species Distribution Modeling using Remote Sensing and Citizen Science Data

Normalization Layers Are All That Sharpness-Aware Minimization Needs

MarioGPT: Open-Ended Text2Level Generation through Large Language Models

A Unified Conditional Framework for Diffusion-based Image Restoration

JourneyDB: A Benchmark for Generative Image Understanding

Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation

Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks

Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks

Bias in Evaluation Processes: An Optimization-Based Model

Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery

Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction

ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation

Towards Last-layer Retraining for Group Robustness with Fewer Annotations

Not All Out-of-Distribution Data Are Harmful to Open-Set Active Learning

Localized Symbolic Knowledge Distillation for Visual Commonsense Models

Break It Down: Evidence for Structural Compositionality in Neural Networks

Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation

Learning to Parameterize Visual Attributes for Open-set Fine-grained Retrieval

Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability

OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping

Parallel Submodular Function Minimization

PoET: A generative model of protein families as sequences-of-sequences

Students Parrot Their Teachers: Membership Inference on Model Distillation

Are aligned neural networks adversarially aligned?

Privacy Auditing with One (1) Training Run

Optimal Transport-Guided Conditional Score-Based Diffusion Model

[Re] Variational Neural Cellular Automata

Improving Language Plasticity via Pretraining with Active Forgetting

Network Regression with Graph Laplacians

Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks

FLuID: Mitigating Stragglers in Federated Learning using Invariant Dropout

On the spectral bias of two-layer linear networks

Optimal Algorithms for the Inhomogeneous Spiked Wigner Model

Permutation Equivariant Neural Functionals

Neural Functional Transformers

Language Models are Weak Learners

On the Importance of Exploration for Generalization in Reinforcement Learning

AndroidInTheWild: A Large-Scale Dataset For Android Device Control

Maximum State Entropy Exploration using Predecessor and Successor Representations

DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimization

Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision

DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method

DataComp: In search of the next generation of multimodal datasets

Robust Learning for Smoothed Online Convex Optimization with Feedback Delay

DesCo: Learning Object Recognition with Rich Language Descriptions

Optimal Excess Risk Bounds for Empirical Risk Minimization on $p$-Norm Linear Regression

Recurrent Hypernetworks are Surprisingly Strong in Meta-RL

Towards Self-Interpretable Graph-Level Anomaly Detection

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation

EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learning

Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective

DiffUTE: Universal Text Editing Diffusion Model

ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion

A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting

Global Optimality in Bivariate Gradient-based DAG Learning

Toward Re-Identifying Any Animal

FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space

Accelerating Molecular Graph Neural Networks via Knowledge Distillation

Opening the Vocabulary of Egocentric Actions

Hierarchical Adaptive Value Estimation for Multi-modal Visual Reinforcement Learning

Jailbroken: How Does LLM Safety Training Fail?

Efficient Training of Energy-Based Models Using Jarzynski Equality

Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing

Exponentially Convergent Algorithms for Supervised Matrix Factorization

Sequential Subset Matching for Dataset Distillation

Dynamic Sparsity Is Channel-Level Sparsity Learner

Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond

Sequential Memory with Temporal Predictive Coding

Uncertainty-Aware Alignment Network for Cross-Domain Video-Text Retrieval

Sharp Bounds for Generalized Causal Sensitivity Analysis

State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding

Inverse Preference Learning: Preference-based RL without a Reward Function

Learning Cuts via Enumeration Oracles

LD2: Scalable Heterophilous Graph Neural Network with Decoupled Embeddings

DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning

Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets

Cross-Episodic Curriculum for Transformer Agents

On Learning Latent Models with Multi-Instance Weak Supervision

Query-based Temporal Fusion with Explicit Motion for 3D Object Detection

Solving a Class of Non-Convex Minimax Optimization in Federated Learning

Composable Coresets for Determinant Maximization: Greedy is Almost Optimal

Generalizable One-shot 3D Neural Head Avatar

Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection

Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data

Rethinking Conditional Diffusion Sampling with Progressive Guidance

Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models

Inferring the Future by Imagining the Past

Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards

Diversify \& Conquer: Outcome-directed Curriculum RL via Out-of-Distribution Disagreement

Budgeting Counterfactual for Offline RL

Learning Dictionary for Visual Attention

Epistemic Neural Networks

RECKONING: Reasoning through Dynamic Knowledge Encoding

Learning Nonparametric Latent Causal Graphs with Unknown Interventions

Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms

Scale-Space Hypernetworks for Efficient Biomedical Image Analysis

StateMask: Explaining Deep Reinforcement Learning through State Mask

Segment Everything Everywhere All at Once

Double and Single Descent in Causal Inference with an Application to High-Dimensional Synthetic Control

FABind: Fast and Accurate Protein-Ligand Binding

LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition

CP-SLAM: Collaborative Neural Point-based SLAM System

Fed-CO$_{2}$: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning

Exploring Diverse In-Context Configurations for Image Captioning

Demystifying Softmax Gating Function in Gaussian Mixture of Experts

Hybrid Search for Efficient Planning with Completeness Guarantees

Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space

Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection

Deep learning with kernels through RKHM and the Perron-Frobenius operator

Training Chain-of-Thought via Latent-Variable Inference

Bayesian Extensive-Rank Matrix Factorization with Rotational Invariant Priors

NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries

Meta-Adapter: An Online Few-shot Learner for Vision-Language Model

Estimating the Rate-Distortion Function by Wasserstein Gradient Descent

Adaptive Algorithms for Relaxed Pareto Set Identification

Differentially Private Image Classification by Learning Priors from Random Processes

Algorithmic Regularization in Tensor Optimization: Towards a Lifted Approach in Matrix Sensing

Auditing Fairness by Betting

Asymmetric Certified Robustness via Feature-Convex Neural Networks

Convergence of Alternating Gradient Descent for Matrix Factorization

Cause-Effect Inference in Location-Scale Noise Models: Maximum Likelihood vs. Independence Testing

Non-Convex Bilevel Optimization with Time-Varying Objective Functions

On the Ability of Graph Neural Networks to Model Interactions Between Vertices

Neural Sampling in Hierarchical Exponential-family Energy-based Models

Persuading Farsighted Receivers in MDPs: the Power of Honesty

RanPAC: Random Projections and Pre-trained Models for Continual Learning

Drift doesn't Matter: Dynamic Decomposition with Diffusion Reconstruction for Unstable Multivariate Time Series Anomaly Detection

MG-ViT: A Multi-Granularity Method for Compact and Efficient Vision Transformers

Feature Adaptation for Sparse Linear Regression

ClusterFomer: Clustering As A Universal Visual Learner

Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension

Differentially Private Approximate Near Neighbor Counting in High Dimensions

WalkLM: A Uniform Language Model Fine-tuning Framework for Attributed Graph Embedding

Elastic Decision Transformer

Leveraging the two-timescale regime to demonstrate convergence of neural networks

Continuous Parametric Optical Flow

PCF-GAN: generating sequential data via the characteristic function of measures on the path space

Random Cuts are Optimal for Explainable k-Medians

Embedding Space Interpolation Beyond Mini-Batch, Beyond Pairs and Beyond Examples

Regularizing Neural Networks with Meta-Learning Generative Models

Depth-discriminative Metric Learning for Monocular 3D Object Detection

Sparse Parameterization for Epitomic Dataset Distillation

A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning

Characterization and Learning of Causal Graphs with Small Conditioning Sets

Counterfactually Fair Representation

Class-Conditional Conformal Prediction with Many Classes

Uncertainty-Aware Instance Reweighting for Off-Policy Learning

SE(3) Equivariant Augmented Coupling Flows

An Inductive Bias for Tabular Deep Learning

Self-Weighted Contrastive Learning among Multiple Views for Mitigating Representation Degeneration

Improvements on Uncertainty Quantification for Node Classification via Distance Based Regularization

Time-Independent Information-Theoretic Generalization Bounds for SGLD

Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework

STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning

Reflexion: language agents with verbal reinforcement learning

Hybrid Policy Optimization from Imperfect Demonstrations

Unsupervised Anomaly Detection with Rejection

Approximate inference of marginals using the IBIA framework

Non-autoregressive Machine Translation with Probabilistic Context-free Grammar

Characterization of Overfitting in Robust Multiclass Classification

CS-Isolate: Extracting Hard Confident Examples by Content and Style Isolation

Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning

Advice Querying under Budget Constraint for Online Algorithms

Inference for Gaussian Processes with Matern Covariogram on Compact Riemannian Manifolds

ProteinNPT: Improving protein property prediction and design with non-parametric transformers

Lending Interaction Wings to Recommender Systems with Conversational Agents

AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weeks

M$^2$Hub: Unlocking the Potential of Machine Learning for Materials Discovery

Is RLHF More Difficult than Standard RL? A Theoretical Perspective

Neural Algorithmic Reasoning Without Intermediate Supervision

Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser

Model and Feature Diversity for Bayesian Neural Networks in Mutual Learning

Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning

A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning

Real-World Image Variation by Aligning Diffusion Inversion Chain

Geodesic Multi-Modal Mixup for Robust Fine-Tuning

Hardware Resilience Properties of Text-Guided Image Classifiers

InstanT: Semi-supervised Learning with Instance-dependent Thresholds

DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning

Cross-Domain Policy Adaptation via Value-Guided Data Filtering

Alleviating the Semantic Gap for Generalized fMRI-to-Image Reconstruction

Label Correction of Crowdsourced Noisy Annotations with an Instance-Dependent Noise Transition Model

Parallel Sampling of Diffusion Models

SEENN: Towards Temporal Spiking Early Exit Neural Networks

A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence

SOL: Sampling-based Optimal Linear bounding of arbitrary scalar functions

Training Neural Networks is NP-Hard in Fixed Dimension

RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion

Learning Energy-Based Prior Model with Diffusion-Amortized MCMC

Iterative Reachability Estimation for Safe Reinforcement Learning

Spatially Resolved Gene Expression Prediction from Histology Images via Bi-modal Contrastive Learning

Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations

Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning

A Scalable Neural Network for DSIC Affine Maximizer Auction Design

Variational Imbalanced Regression: Fair Uncertainty Quantification via Probabilistic Smoothing

BIOT: Biosignal Transformer for Cross-data Learning in the Wild

Taking the neural sampling code very seriously: A data-driven approach for evaluating generative models of the visual system

Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation

Learning Multi-agent Behaviors from Distributed and Streaming Demonstrations

Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders

Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition

The emergence of clusters in self-attention dynamics

Enhancing Adaptive History Reserving by Spiking Convolutional Block Attention Module in Recurrent Neural Networks

Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection

On the Planning Abilities of Large Language Models - A Critical Investigation

Differentiable Random Partition Models

From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Models to Pre-trained Machine Reader

CamoPatch: An Evolutionary Strategy for Generating Camoflauged Adversarial Patches

A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning

Efficient Equivariant Transfer Learning from Pretrained Models

Training Private Models That Know What They Don’t Know

Discrete-Smoothness in Online Algorithms with Predictions

Brant: Foundation Model for Intracranial Neural Signal

Online POMDP Planning with Anytime Deterministic Guarantees

On Computing Pairwise Statistics with Local Differential Privacy

The Adversarial Consistency of Surrogate Risks for Binary Classification

Live Graph Lab: Towards Open, Dynamic and Real Transaction Graphs with NFT

Scale-teaching: Robust Multi-scale Training for Time Series Classification with Noisy Labels

One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation

FLAIR : a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery

GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image

MiliPoint: A Point Cloud Dataset for mmWave Radar

Video Timeline Modeling For News Story Understanding

CARE-MI: Chinese Benchmark for Misinformation Evaluation in Maternity and Infant Care

Revisiting the Evaluation of Image Synthesis with GANs

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning

Generating QM1B with PySCF$_{\text{IPU}}$

EMBERSim: A Large-Scale Databank for Boosting Similarity Search in Malware Analysis

Pairwise GUI Dataset Construction Between Android Phones and Tablets

DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models

OpenGSL: A Comprehensive Benchmark for Graph Structure Learning

FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation

LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

GSLB: The Graph Structure Learning Benchmark

CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion

What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation

StressID: a Multimodal Dataset for Stress Identification

SubseasonalClimateUSA: A Dataset for Subseasonal Forecasting and Benchmarking

FELM: Benchmarking Factuality Evaluation of Large Language Models

MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning

M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models

Auslan-Daily: Australian Sign Language Translation for Daily Communication and News

C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models

AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web

SG×P : A Sorghum Genotype × Phenotype Prediction Dataset and Benchmark

Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs

EV-Eye: Rethinking High-frequency Eye Tracking through the Lenses of Event Cameras

How to Data in Datathons

VidChapters-7M: Video Chapters at Scale

Realistic Synthetic Financial Transactions for Anti-Money Laundering Models

WBCAtt: A White Blood Cell Dataset Annotated with Detailed Morphological Attributes

Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean

CAPP-130: A Corpus of Chinese Application Privacy Policy Summarization and Interpretation

Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning

Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory

OFCOURSE: A Multi-Agent Reinforcement Learning Environment for Order Fulfillment

Fast Online Changepoint Detection via Functional Pruning CUSUM Statistics

Variational Gibbs Inference for Statistical Model Estimation from Incomplete Data

On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes

ASL Citizen: A Community-Sourced Dataset for Advancing Isolated Sign Language Recognition

Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes

GPEX, A Framework For Interpreting Artificial Neural Networks

Exponential Lower Bounds for Fictitious Play in Potential Games

BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing

Toolbox for Multimodal Learn (scikit-multimodallearn)

Reproducibility Study of ”Label-Free Explainability for Unsupervised Models”

Blockwise Parallel Transformers for Large Context Models

NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications

AVIDa-hIL6: A Large-Scale VHH Dataset Produced from an Immunized Alpaca for Predicting Antigen-Antibody Interactions

On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration

Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving

Suggesting Variable Order for Cylindrical Algebraic Decomposition via Reinforcement Learning

PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning

Federated Conditional Stochastic Optimization

FIRAL: An Active Learning Algorithm for Multinomial Logistic Regression

MultiVENT: Multilingual Videos of Events and Aligned Natural Text

What can a Single Attention Layer Learn? A Study Through the Random Features Lens

Streaming Algorithms and Lower Bounds for Estimating Correlation Clustering Cost

Classical Simulation of Quantum Circuits: Parallel Environments and Benchmark

Smoothed Online Learning for Prediction in Piecewise Affine Systems

A new perspective on building efficient and expressive 3D equivariant graph neural networks

Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning

Faster Discrete Convex Function Minimization with Predictions: The M-Convex Case

GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition

SynMob: Creating High-Fidelity Synthetic GPS Trajectory Dataset for Urban Mobility Analysis

NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations

The Target-Charging Technique for Privacy Analysis across Interactive Computations

De novo Drug Design using Reinforcement Learning with Multiple GPT Agents

Interactive Visual Reasoning under Uncertainty

Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks

Sample Complexity of Forecast Aggregation

Building Socio-culturally Inclusive Stereotype Resources with Community Engagement

Revisiting Adversarial Robustness Distillation from the Perspective of Robust Fairness

Max-Sliced Mutual Information

Euler-Lagrange Analysis of Generative Adversarial Networks

ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation

AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models

3D-Aware Visual Question Answering about Parts, Poses and Occlusions

Modeling Dynamics over Meshes with Gauge Equivariant Nonlinear Message Passing

Evaluating Open-QA Evaluation

[Re] FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles

Taylor TD-learning

BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks

OceanBench: The Sea Surface Height Edition

Tartarus: A Benchmarking Platform for Realistic And Practical Inverse Molecular Design

Efficient Model-Free Exploration in Low-Rank MDPs

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning

URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates

Selective Sampling and Imitation Learning via Online Regression

Temporal Graph Benchmark for Machine Learning on Temporal Graphs

Reproducibility study of 'Proto2Proto: Can you recognise the car, the way I do?'

Provably (More) Sample-Efficient Offline RL with Options

IDRNet: Intervention-Driven Relation Network for Semantic Segmentation

Meta-in-context learning in large language models

Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation

Reconciling Competing Sampling Strategies of Network Embedding

Scaling Up Differentially Private LASSO Regularized Logistic Regression via Faster Frank-Wolfe Iterations

UniT: A Unified Look at Certified Robust Training against Text Adversarial Perturbation

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

Neural Priming for Sample-Efficient Adaptation

Optimality in Mean Estimation: Beyond Worst-Case, Beyond Sub-Gaussian, and Beyond $1+\alpha$ Moments

Balancing Risk and Reward: A Batched-Bandit Strategy for Automated Phased Release

ConRad: Image Constrained Radiance Fields for 3D Generation from a Single Image

A normative theory of social conflict

Lossy Image Compression with Conditional Diffusion Models

Conditional Distribution Function Estimation Using Neural Networks for Censored and Uncensored Data

May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations

Graph Denoising Diffusion for Inverse Protein Folding

Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex

Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning

Dream the Impossible: Outlier Imagination with Diffusion Models

An Adaptive Algorithm for Learning with Unknown Distribution Drift

FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy

ForecastPFN: Synthetically-Trained Zero-Shot Forecasting

PPi: Pretraining Brain Signal Model for Patient-independent Seizure Detection

Tailoring Self-Attention for Graph via Rooted Subtrees

HASSOD: Hierarchical Adaptive Self-Supervised Object Detection

VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset

A Measure-Theoretic Axiomatisation of Causality

Error Bounds for Learning with Vector-Valued Random Features

Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies

Stochastic Multi-armed Bandits: Optimal Trade-off among Optimality, Consistency, and Tail Risk

Learning Efficient Surrogate Dynamic Models with Graph Spline Networks

Bayesian nonparametric (non-)renewal processes for analyzing neural spike train variability

Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm

Convolutional Visual Prompt for Robust Visual Perception

Inner-Outer Aware Reconstruction Model for Monocular 3D Scene Reconstruction

A Dual-Stream Neural Network Explains the Functional Segregation of Dorsal and Ventral Visual Pathways in Human Brains

VaRT: Variational Regression Trees

One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models

Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective

Improving Diffusion-Based Image Synthesis with Context Prediction

How Does Adaptive Optimization Impact Local Neural Network Geometry?

Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition

PromptRestorer: A Prompting Image Restoration Method with Degradation Perception

Large Language Models Are Zero-Shot Time Series Forecasters

Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities

Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation

Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards

Deep Momentum Multi-Marginal Schrödinger Bridge

Disentangling Voice and Content with Self-Supervision for Speaker Recognition

Learning Large-Scale MTP$_2$ Gaussian Graphical Models via Bridge-Block Decomposition

Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models

FourierHandFlow: Neural 4D Hand Representation Using Fourier Query Flow

Strong and Precise Modulation of Human Percepts via Robustified ANNs

Geometric Analysis of Matrix Sensing over Graphs

Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

Beta Diffusion

Robust Lipschitz Bandits to Adversarial Corruptions

Optimization or Architecture: How to Hack Kalman Filtering

Mutual-Information Regularized Multi-Agent Policy Iteration

Structured State Space Models for In-Context Reinforcement Learning

An Iterative Self-Learning Framework for Medical Domain Generalization

Addressing Negative Transfer in Diffusion Models

Are GATs Out of Balance?

Evolving Connectivity for Recurrent Spiking Neural Networks

Neuro-symbolic Learning Yielding Logical Constraints

Randomized and Deterministic Maximin-share Approximations for Fractionally Subadditive Valuations

Frequency Domain-Based Dataset Distillation

Any-to-Any Generation via Composable Diffusion

Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding

Online RL in Linearly $q^\pi$-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore

Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning

Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment

Guide Your Agent with Adaptive Multimodal Rewards

Rewiring Neurons in Non-Stationary Environments

On Sparse Modern Hopfield Model

IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers

Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models

Cognitive Steering in Deep Neural Networks via Long-Range Modulatory Feedback Connections

GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks

Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

SOAR: Improved Indexing for Approximate Nearest Neighbor Search

A Unified Framework for U-Net Design and Analysis

Zeroth-Order Methods for Nondifferentiable, Nonconvex, and Hierarchical Federated Optimization

PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.

CorresNeRF: Image Correspondence Priors for Neural Radiance Fields

Adaptive Linear Estimating Equations

Neural Multi-Objective Combinatorial Optimization with Diversity Enhancement

Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization

Active Learning-Based Species Range Estimation

Linear Time Algorithms for k-means with Multi-Swap Local Search

Rethinking the Backward Propagation for Adversarial Transferability

Explainable and Efficient Randomized Voting Rules

Inconsistency, Instability, and Generalization Gap of Deep Neural Network Training

Learning Regularized Monotone Graphon Mean-Field Games

Debiasing Conditional Stochastic Optimization

Imbalanced Mixed Linear Regression

Fast Rank-1 Lattice Targeted Sampling for Black-box Optimization

On the Power of SVD in the Stochastic Block Model

Prompt-augmented Temporal Point Process for Streaming Event Sequence

SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation

Stabilizing the Optimization of Neural Signed Distance Functions and Finer Shape Representation

From Tempered to Benign Overfitting in ReLU Neural Networks

Adversarial Examples Are Not Real Features

SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling

Flow-Attention-based Spatio-Temporal Aggregation Network for 3D Mask Detection

Episodic Multi-Task Learning with Heterogeneous Neural Processes

ReTR: Modeling Rendering Via Transformer for Generalizable Neural Surface Reconstruction

Discovering Intrinsic Spatial-Temporal Logic Rules to Explain Human Actions

A Unified Solution for Privacy and Communication Efficiency in Vertical Federated Learning

Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense

Squared Neural Families: A New Class of Tractable Density Models

Context-lumpable stochastic bandits

Revisit Weakly-Supervised Audio-Visual Video Parsing from the Language Perspective

The probability flow ODE is provably fast

Towards Free Data Selection with General-Purpose Models

Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling

Paxion: Patching Action Knowledge in Video-Language Foundation Models

SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation

Autodecoding Latent 3D Diffusion Models

Learning Trajectories are Generalization Indicators

MAG-GNN: Reinforcement Learning Boosted Graph Neural Network

Train Hard, Fight Easy: Robust Meta Reinforcement Learning

On Imitation in Mean-field Games

MAViL: Masked Audio-Video Learners

Removing Hidden Confounding in Recommendation: A Unified Multi-Task Learning Approach

Knowledge Diffusion for Distillation

Networks are Slacking Off: Understanding Generalization Problem in Image Deraining

Policy Gradient for Rectangular Robust Markov Decision Processes

A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories

Alternation makes the adversary weaker in two-player games

Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning

Three Towers: Flexible Contrastive Learning with Pretrained Image Models

Multi-Objective Intrinsic Reward Learning for Conversational Recommender Systems

Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data

3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes

Calibration by Distribution Matching: Trainable Kernel Calibration Metrics

Towards Consistent Video Editing with Text-to-Image Diffusion Models

Improving CLIP Training with Language Rewrites

Learning Dense Flow Field for Highly-accurate Cross-view Camera Localization

On quantum backpropagation, information reuse, and cheating measurement collapse

Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation

All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation

Towards Semi-Structured Automatic ICD Coding via Tree-based Contrastive Learning

Binarized Spectral Compressive Imaging

Zero-Regret Performative Prediction Under Inequality Constraints

Reward Imputation with Sketching for Contextual Batched Bandits

Gaussian Differential Privacy on Riemannian Manifolds

NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning

LuminAIRe: Illumination-Aware Conditional Image Repainting for Lighting-Realistic Generation

SQ Lower Bounds for Learning Mixtures of Linear Classifiers

Optimal Transport for Treatment Effect Estimation

PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model

A Fast and Accurate Estimator for Large Scale Linear Model via Data Averaging

A One-Size-Fits-All Approach to Improving Randomness in Paper Assignment

List and Certificate Complexities in Replicable Learning

On Class Distributions Induced by Nearest Neighbor Graphs for Node Classification of Tabular Data

Contextual Gaussian Process Bandits with Neural Networks

Newton–Cotes Graph Neural Networks: On the Time Evolution of Dynamic Systems

Counting Distinct Elements in the Turnstile Model with Differential Privacy under Continual Observation

An Empirical Study Towards Prompt-Tuning for Graph Contrastive Pre-Training in Recommendations

Prefix-Tree Decoding for Predicting Mass Spectra from Molecules

Computing Optimal Nash Equilibria in Multiplayer Games

Towards Efficient Pre-Trained Language Model via Feature Correlation Distillation

Subclass-Dominant Label Noise: A Counterexample for the Success of Early Stopping

$k$-Means Clustering with Distance-Based Privacy

L2T-DLN: Learning to Teach with Dynamic Loss Network

Domain Re-Modulation for Few-Shot Generative Domain Adaptation

Finite-Time Analysis of Single-Timescale Actor-Critic

Moral Responsibility for AI Systems

Exploiting Contextual Objects and Relations for 3D Visual Grounding

RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths

When Visual Prompt Tuning Meets Source-Free Domain Adaptive Semantic Segmentation

DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models

Meet in the Middle: A New Pre-training Paradigm

Optimal approximation using complex-valued neural networks

SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networks

Causal discovery from observational and interventional data across multiple environments

Learning From Biased Soft Labels

Incomplete Multimodality-Diffused Emotion Recognition

Recommender Systems with Generative Retrieval

Flow: Per-instance Personalized Federated Learning

Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation

Passive learning of active causal strategies in agents and language models

Improving Robustness with Adaptive Weight Decay

Model-Free Reinforcement Learning with the Decision-Estimation Coefficient

Generalized Information-theoretic Multi-view Clustering

Affinity-Aware Graph Networks

Outlier-Robust Wasserstein DRO

Neural (Tangent Kernel) Collapse

A Trichotomy for Transductive Online Learning

Category-Extensible Out-of-Distribution Detection via Hierarchical Context Descriptions

Effectively Learning Initiation Sets in Hierarchical Reinforcement Learning

Statistical Knowledge Assessment for Large Language Models

Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL

Automated Classification of Model Errors on ImageNet

DynPoint: Dynamic Neural Point For View Synthesis

Generator Identification for Linear SDEs with Additive and Multiplicative Noise

Modulated Neural ODEs

ReSync: Riemannian Subgradient-based Robust Rotation Synchronization

CosNet: A Generalized Spectral Kernel Network

Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs

Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage

Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration

Granger Components Analysis: Unsupervised learning of latent temporal dependencies

Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark

Token-Scaled Logit Distillation for Ternary Weight Generative Language Models

FAST: a Fused and Accurate Shrinkage Tree for Heterogeneous Treatment Effects Estimation

Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias

DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization

Effective Targeted Attacks for Adversarial Self-Supervised Learning

CARE: Modeling Interacting Dynamics Under Temporal Environmental Variation

MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates

What You See is What You Read? Improving Text-Image Alignment Evaluation

Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models

On the Identifiability and Interpretability of Gaussian Process Models

Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes

Leveraging Early-Stage Robustness in Diffusion Models for Efficient and High-Quality Image Synthesis

Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation

CoLLAT: On Adding Fine-grained Audio Understanding to Language Models using Token-Level Locked-Language Tuning

Reducing Shape-Radiance Ambiguity in Radiance Fields with a Closed-Form Color Estimation Method

Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction

Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity

One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning

Cookie Consent Has Disparate Impact on Estimation Accuracy

L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priors

Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping

ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors

Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network

DIFFER:Decomposing Individual Reward for Fair Experience Replay in Multi-Agent Reinforcement Learning

State-Action Similarity-Based Representations for Off-Policy Evaluation

LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite

Private Federated Frequency Estimation: Adapting to the Hardness of the Instance

AdANNS: A Framework for Adaptive Semantic Search

Validated Image Caption Rating Dataset

Why think step by step? Reasoning emerges from the locality of experience

Parsel🐍: Algorithmic Reasoning with Language Models by Composing Decompositions

ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP

Conformal Prediction Sets for Ordinal Classification

Robust Mean Estimation Without Moments for Symmetric Distributions

AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback

BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning

Hierarchical VAEs provide a normative account of motion processing in the primate brain

On the Role of Entanglement and Statistics in Learning

Sparse Modular Activation for Efficient Sequence Modeling

Towards Personalized Federated Learning via Heterogeneous Model Reassembly

Fast Approximation of Similarity Graphs with Kernel Density Estimation

Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes

Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability

Intelligent Knee Sleeves: A Real-time Multimodal Dataset for 3D Lower Body Motion Estimation Using Smart Textile

Recovering Unbalanced Communities in the Stochastic Block Model with Application to Clustering with a Faulty Oracle

LeanDojo: Theorem Proving with Retrieval-Augmented Language Models

Online Performative Gradient Descent for Learning Nash Equilibria in Decision-Dependent Games

LithoBench: Benchmarking AI Computational Lithography for Semiconductor Manufacturing

Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation

Augmenting Language Models with Long-Term Memory

Fast Partitioned Learned Bloom Filter

INSPECT: A Multimodal Dataset for Patient Outcome Prediction of Pulmonary Embolisms

Adversarially Robust Distributed Count Tracking via Partial Differential Privacy

Joint Attribute and Model Generalization Learning for Privacy-Preserving Action Recognition

Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples

Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings

Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry

SEEDS: Exponential SDE Solvers for Fast High-Quality Sampling from Diffusion Models

Temporal Conditioning Spiking Latent Variable Models of the Neural Response to Natural Visual Scenes

When can Regression-Adjusted Control Variate Help? Rare Events, Sobolev Embedding and Minimax Optimality

Expressive Sign Equivariant Networks for Spectral Geometric Learning

PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction

Horospherical Decision Boundaries for Large Margin Classification in Hyperbolic Space

Enhancing Sharpness-Aware Optimization Through Variance Suppression

Dense-Exponential Random Features: Sharp Positive Estimators of the Gaussian Kernel

Reusing Pretrained Models by Multi-linear Operators for Efficient Training

$S^3$: Increasing GPU Utilization during Generative Inference for Higher Throughput

Multi-Swap k-Means++

A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence

CaMP: Causal Multi-policy Planning for Interactive Navigation in Multi-room Scenes

PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

Credal Marginal MAP

BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis

TIES-Merging: Resolving Interference When Merging Models

Fitting trees to $\ell_1$-hyperbolic distances

Compact Neural Volumetric Video Representations with Dynamic Codebooks

Robust Model Reasoning and Fitting via Dual Sparsity Pursuit

Stability of Random Forests and Coverage of Random-Forest Prediction Intervals

FedNAR: Federated Optimization with Normalized Annealing Regularization

Online Constrained Meta-Learning: Provable Guarantees for Generalization

ContinuAR: Continuous Autoregression For Infinite-Fidelity Fusion

Provable benefits of score matching

Ambient Diffusion: Learning Clean Distributions from Corrupted Data

Hyper-HMM: aligning human brains and semantic features in a common latent event space

Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework

Online PCA in Converging Self-consistent Field Equations

MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion

Training Your Image Restoration Network Better with Random Weight Network as Optimization Function

FairLISA: Fair User Modeling with Limited Sensitive Attributes Information

Efficient Robust Bayesian Optimization for Arbitrary Uncertain inputs

Understanding Deep Gradient Leakage via Inversion Influence Functions

Achieving Cross Modal Generalization with Multimodal Unified Representation

Dynamically Masked Discriminator for GANs

AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis

EgoEnv: Human-centric environment representations from egocentric video

ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections

Brain Dissection: fMRI-trained Networks Reveal Spatial Selectivity in the Processing of Natural Images

Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks

An active learning framework for multi-group mean estimation

Gradient Informed Proximal Policy Optimization

Individual Arbitrariness and Group Fairness

Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima

Regret Matching+: (In)Stability and Fast Convergence in Games

Predicting Global Label Relationship Matrix for Graph Neural Networks under Heterophily

Regret Minimization via Saddle Point Optimization

DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis

Mixed-Initiative Multiagent Apprenticeship Learning for Human Training of Robot Teams

Implicit Contrastive Representation Learning with Guided Stop-gradient

Meta-Learning Adversarial Bandit Algorithms

CORNN: Convex optimization of recurrent neural networks for rapid inference of neural dynamics

Perceptual Kalman Filters: Online State Estimation under a Perfect Perceptual-Quality Constraint

Cocktail: Mixing Multi-Modality Control for Text-Conditional Image Generation

Generating Images with Multimodal Language Models

Auditing for Human Expertise

The s-value: evaluating stability with respect to distributional shifts

Fast Attention Over Long Sequences With Dynamic Sparse Flash Attention

Asynchrony-Robust Collaborative Perception via Bird's Eye View Flow

MultiMoDN—Multimodal, Multi-Task, Interpretable Modular Networks

MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detection

GEQ: Gaussian Kernel Inspired Equilibrium Models

Information Geometry of the Retinal Representation Manifold

Uniform Convergence with Square-Root Lipschitz Loss

Dataset Diffusion: Diffusion-based Synthetic Data Generation for Pixel-Level Semantic Segmentation

Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer

ARTree: A Deep Autoregressive Model for Phylogenetic Inference

FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning

Better Private Linear Regression Through Better Private Feature Selection

DeepPCR: Parallelizing Sequential Operations in Neural Networks

Text-to-Image Diffusion Models are Zero Shot Classifiers

Hardness of Low Rank Approximation of Entrywise Transformed Matrix Products

Gacs-Korner Common Information Variational Autoencoder

PROTES: Probabilistic Optimization with Tensor Sampling

Task-Robust Pre-Training for Worst-Case Downstream Adaptation

Towards a Unified Framework of Contrastive Learning for Disentangled Representations

Multi-Agent Meta-Reinforcement Learning: Sharper Convergence Rates with Task Similarity

Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning

Combinatorial Optimization with Policy Adaptation using Latent Space Search

On Robust Streaming for Learning with Experts: Algorithms and Lower Bounds

Nearly Tight Bounds For Differentially Private Multiway Cut

Unified 3D Segmenter As Prototypical Classifiers

Human-in-the-Loop Optimization for Deep Stimulus Encoding in Visual Prostheses

Goal Driven Discovery of Distributional Differences via Language Descriptions

Generalized equivalences between subsampling and ridge regularization

Momentum Provably Improves Error Feedback!

Structure of universal formulas

Dynamic Regret of Adversarial Linear Mixture MDPs

Temporal Robustness against Data poisoning

Reading Relevant Feature from Global Representation Memory for Visual Object Tracking

Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image Restoration

Theoretically Guaranteed Bidirectional Data Rectification for Robust Sequential Recommendation

Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection

The CLIP Model is Secretly an Image-to-Prompt Converter

Unsupervised Learning for Solving the Travelling Salesman Problem

Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples

Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction

Exact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Models

Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems

Knowledge Distillation for High Dimensional Search Index

Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model

Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction

Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment

Boosting Adversarial Transferability by Achieving Flat Local Maxima

Aligning Gradient and Hessian for Neural Signed Distance Function

Actively Testing Your Model While It Learns: Realizing Label-Efficient Learning in Practice

Improving Adversarial Transferability via Intermediate-level Perturbation Decay

Constrained Policy Optimization with Explicit Behavior Density For Offline Reinforcement Learning

Group Fairness in Peer Review

Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator

Semi-Supervised Domain Generalization with Known and Unknown Classes

Context-guided Embedding Adaptation for Effective Topic Modeling in Low-Resource Regimes

Tight Bounds for Volumetric Spanners and Applications

Tight Risk Bounds for Gradient Descent on Separable Data

Self-Chained Image-Language Model for Video Localization and Question Answering

Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction

Risk-Averse Active Sensing for Timely Outcome Prediction under Cost Pressure

On kernel-based statistical learning theory in the mean field limit

Puzzlefusion: Unleashing the Power of Diffusion Models for Spatial Puzzle Solving

Online Map Vectorization for Autonomous Driving: A Rasterization Perspective

STEVE-1: A Generative Model for Text-to-Behavior in Minecraft

MoVie: Visual Model-Based Policy Adaptation for View Generalization

ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling

Towards Higher Ranks via Adversarial Weight Pruning

Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videos

Mirror Diffusion Models for Constrained and Watermarked Generation

DreamWaltz: Make a Scene with Complex 3D Animatable Avatars

Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly

Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models

Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification

Cheaply Estimating Inference Efficiency Metrics for Autoregressive Transformer Models

Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction

Public Opinion Field Effect Fusion in Representation Learning for Trending Topics Diffusion

Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problem

VanillaNet: the Power of Minimalism in Deep Learning

OV-PARTS: Towards Open-Vocabulary Part Segmentation

Estimating Generic 3D Room Structures from 2D Annotations

QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules

Into the Single Cell Multiverse: an End-to-End Dataset for Procedural Knowledge Extraction in Biomedical Texts

Implicit Bias of (Stochastic) Gradient Descent for Rank-1 Linear Neural Network

Responsible AI (RAI) Games and Ensembles

ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning

How Re-sampling Helps for Long-Tail Learning?

Window-Based Distribution Shift Detection for Deep Neural Networks

Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks

Experimental Designs for Heteroskedastic Variance

Training biologically plausible recurrent neural networks on cognitive tasks with long-term dependencies

A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning

Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation

Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP

Layer-Neighbor Sampling --- Defusing Neighborhood Explosion in GNNs

DAW: Exploring the Better Weighting Function for Semi-supervised Semantic Segmentation

Switching Temporary Teachers for Semi-Supervised Semantic Segmentation

Global Identifiability of $\ell_1$-based Dictionary Learning via Matrix Volume Optimization

Evaluating and Inducing Personality in Pre-trained Language Models

Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent

Machine learning detects terminal singularities

Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data

Spiking PointNet: Spiking Neural Networks for Point Clouds

Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models

Information-guided Planning: An Online Approach for Partially Observable Problems

A Long $N$-step Surrogate Stage Reward for Deep Reinforcement Learning

PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification

DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data

Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback

Equivariant Neural Simulators for Stochastic Spatiotemporal Dynamics

Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization

Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs

Mitigating the Effect of Incidental Correlations on Part-based Learning

Learning Shared Safety Constraints from Multi-task Demonstrations

Real-World Image Super-Resolution as Multi-Task Learning

Joint processing of linguistic properties in brains and language models

Masked Image Residual Learning for Scaling Deeper Vision Transformers

Logarithmic-Regret Quantum Learning Algorithms for Zero-Sum Games

Pairwise Causality Guided Transformers for Event Sequences

Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance

Fast Bellman Updates for Wasserstein Distributionally Robust MDPs

Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval

GeoPhy: Differentiable Phylogenetic Inference via Geometric Gradients of Tree Topologies

Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy

Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback

Schema-learning and rebinding as mechanisms of in-context learning and emergence

How a Student becomes a Teacher: learning and forgetting through Spectral methods

Two-Stage Predict+Optimize for MILPs with Unknown Parameters in Constraints

Score-based Generative Models with Lévy Processes

AirDelhi: Fine-Grained Spatio-Temporal Particulate Matter Dataset From Delhi For ML based Modeling

OpenAGI: When LLM Meets Domain Experts

PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change

RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization

STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events

trajdata: A Unified Interface to Multiple Human Trajectory Datasets

WCLD: Curated Large Dataset of Criminal Cases from Wisconsin Circuit Courts

Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-Start

Posthoc privacy guarantees for collaborative inference with modified Propose-Test-Release

POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images

Dynamic Personalized Federated Learning with Adaptive Differential Privacy

Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration

FedFed: Feature Distillation against Data Heterogeneity in Federated Learning

Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks

DeWave: Discrete Encoding of EEG Waves for EEG to Text Translation

Learning Motion Refinement for Unsupervised Face Animation

Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone

Macro Placement by Wire-Mask-Guided Black-Box Optimization

Learning To Dive In Branch And Bound

Test-time Adaptation of Discriminative Models via Diffusion Generative Feedback

Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping

Continual Learning for Instruction Following from Realtime Feedback

MathNAS: If Blocks Have a Role in Mathematical Architecture Design

Evaluating Post-hoc Explanations for Graph Neural Networks via Robustness Analysis

DOSE: Diffusion Dropout with Adaptive Prior for Speech Enhancement

ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns

CAPro: Webly Supervised Learning with Cross-modality Aligned Prototypes

Expanding Small-Scale Datasets with Guided Imagination

Fast Scalable and Accurate Discovery of DAGs Using the Best Order Score Search and Grow Shrink Trees

Efficient Neural Music Generation

Robustness Guarantees for Adversarially Trained Neural Networks

Strategic Behavior in Two-sided Matching Markets with Prediction-enhanced Preference-formation

Injecting Multimodal Information into Rigid Protein Docking via Bi-level Optimization

TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models

Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative MARL

SaVeNet: A Scalable Vector Network for Enhanced Molecular Representation Learning

Bayesian Optimization with Cost-varying Variable Subsets

Learning the Efficient Frontier

When is Agnostic Reinforcement Learning Statistically Tractable?

Strategic Classification under Unknown Personalized Manipulation

The Gain from Ordering in Online Learning

ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation

Self-supervised video pretraining yields robust and more human-aligned visual representations

LinkerNet: Fragment Poses and Linker Co-Design with 3D Equivariant Diffusion

Diffusion Model for Graph Inverse Problems: Towards Effective Source Localization on Complex Networks

Does a sparse ReLU network training problem always admit an optimum ?

Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models

Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics

Adaptive recurrent vision performs zero-shot computation scaling to unseen difficulty levels

Facing Off World Model Backbones: RNNs, Transformers, and S4

Human spatiotemporal pattern learning as probabilistic program synthesis

Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms

Efficient Activation Function Optimization through Surrogate Modeling

DiffComplete: Diffusion-based Generative 3D Shape Completion

Recasting Continual Learning as Sequence Modeling

DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics

Byzantine-Tolerant Methods for Distributed Variational Inequalities

Block Low-Rank Preconditioner with Shared Basis for Stochastic Optimization

DreamSparse: Escaping from Plato’s Cave with 2D Diffusion Model Given Sparse Views

Payoff-based Learning with Matrix Multiplicative Weights in Quantum Games

The Equivalence of Dynamic and Strategic Stability under Regularized Learning in Games

Exploiting hidden structures in non-convex games for convergence to Nash equilibrium

Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing

BERT Lost Patience Won't Be Robust to Adversarial Slowdown

SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process

Fast Attention Requires Bounded Entries

Penalising the biases in norm regularisation enforces sparsity

Task-aware world model learning with meta weighting via bi-level optimization

Implicit variance regularization in non-contrastive SSL

Normalization-Equivariant Neural Networks with Application to Image Denoising

Faster Query Times for Fully Dynamic $k$-Center Clustering with Outliers

PromptIR: Prompting for All-in-One Image Restoration

Partial Multi-Label Learning with Probabilistic Graphical Disambiguation

$p$-value Adjustment for Monotonous, Unbiased, and Fast Clustering Comparison

Statistical Analysis of Quantum State Learning Process in Quantum Neural Networks

Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

Optimistic Exploration in Reinforcement Learning Using Symbolic Model Estimates

Adapting Fairness Interventions to Missing Values

Towards a fuller understanding of neurons with Clustered Compositional Explanations

Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation

Online Pricing for Multi-User Multi-Item Markets

When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment

High Precision Causal Model Evaluation with Conditional Randomization

Object-centric Learning with Cyclic Walks between Parts and Whole

Understanding and Improving Ensemble Adversarial Defense

Lightweight Vision Transformer with Bidirectional Interaction

Unsupervised Protein-Ligand Binding Energy Prediction via Neural Euler's Rotation Equation

ReHLine: Regularized Composite ReLU-ReHU Loss Minimization with Linear Computation and Linear Convergence

AVIS: Autonomous Visual Information Seeking with Large Language Model Agent

GeoTMI: Predicting Quantum Chemical Property with Easy-to-Obtain Geometry via Positional Denoising

Learning Interpretable Low-dimensional Representation via Physical Symmetry

Towards Accelerated Model Training via Bayesian Data Selection

Idempotent Learned Image Compression with Right-Inverse

Collaboratively Learning Linear Models with Structured Missing Data

Single-Stage Visual Query Localization in Egocentric Videos

Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction

What Do Deep Saliency Models Learn about Visual Attention?

Double Auctions with Two-sided Bandit Feedback

Mode Connectivity in Auction Design

Combining Behaviors with the Successor Features Keyboard

Data Pruning via Moving-one-Sample-out

Characterizing the Optimal $0-1$ Loss for Multi-class Classification with a Test-time Attacker

Adjustable Robust Reinforcement Learning for Online 3D Bin Packing

Covariance-adaptive best arm identification

Exact Verification of ReLU Neural Control Barrier Functions

Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment

Fine-Grained Theoretical Analysis of Federated Zeroth-Order Optimization

Collaborative Score Distillation for Consistent Visual Editing

MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining

Universal Prompt Tuning for Graph Neural Networks

LogSpecT: Feasible Graph Learning Model from Stationary Signals with Recovery Guarantees

Rubik's Cube: High-Order Channel Interactions with a Hierarchical Receptive Field

Deep Fractional Fourier Transform

Beyond MLE: Convex Learning for Text Generation

Jigsaw: Learning to Assemble Multiple Fractured Objects

What Knowledge Gets Distilled in Knowledge Distillation?

Augmented Memory Replay-based Continual Learning Approaches for Network Intrusion Detection

Domain Adaptive Imitation Learning with Visual Observation

Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning

Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability

4D Panoptic Scene Graph Generation

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification

A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm

Causal Imitability Under Context-Specific Independence Relations

Local Convergence of Gradient Methods for Min-Max Games: Partial Curvature Generically Suffices

SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models

Unsupervised Image Denoising with Score Function

Zero-Shot Anomaly Detection via Batch Normalization

VRA: Variational Rectified Activation for Out-of-distribution Detection

Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels

Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning

Abide by the law and follow the flow: conservation laws for gradient flows

Delayed Algorithms for Distributed Stochastic Weakly Convex Optimization

Learning better with Dale’s Law: A Spectral Perspective

Sensitivity in Translation Averaging

A General Framework for Robust G-Invariance in G-Equivariant Networks

Energy-Efficient Scheduling with Predictions

Visual Programming for Step-by-Step Text-to-Image Generation and Evaluation

BiMatting: Efficient Video Matting via Binarization

Segment Anything in High Quality

LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images

[Re] Pure Noise to the Rescue of Insufficient Data

Don’t Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner

Bayesian Optimisation of Functions on Graphs

On the Convergence of No-Regret Learning Dynamics in Time-Varying Games

Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models

Quantum speedups for stochastic optimization

Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization

ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer

GraphMP: Graph Neural Network-based Motion Planning with Efficient Graph Search

Provable Guarantees for Neural Networks via Gradient Feature Learning

Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs

Gaussian Process Probes (GPP) for Uncertainty-Aware Probing

RGMIL: Guide Your Multiple-Instance Learning Model with Regressor

Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning

Progressive Ensemble Distillation: Building Ensembles for Efficient Inference

Fundamental Limits and Tradeoffs in Invariant Representation Learning

Restart Sampling for Improving Generative Processes

Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training

BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing

Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis

No-Regret Online Prediction with Strategic Experts

Tracking Most Significant Shifts in Nonparametric Contextual Bandits

When Can We Track Significant Preference Shifts in Dueling Bandits?

IEBins: Iterative Elastic Bins for Monocular Depth Estimation

Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models

Conditional independence testing under misspecified inductive biases

Deep Insights into Noisy Pseudo Labeling on Graph Data

Adaptive Topological Feature via Persistent Homology: Filtration Learning for Point Clouds

Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities

Compositional Foundation Models for Hierarchical Planning

LayoutPrompter: Awaken the Design Ability of Large Language Models

Complexity of Derivative-Free Policy Optimization for Structured $\mathcal{H}_\infty$ Control

Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks

SLIBO-Net: Floorplan Reconstruction via Slicing Box Representation with Local Geometry Regularization

Mind2Web: Towards a Generalist Agent for the Web

Customizable Image Synthesis with Multiple Subjects

SODA: Robust Training of Test-Time Data Adaptors

Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy

Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation

Fine-Tuning Language Models with Just Forward Passes

Object Reprojection Error (ORE): Camera pose benchmarks from lightweight tracking annotations

DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Field

NICE: NoIse-modulated Consistency rEgularization for Data-Efficient GANs

FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing

Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning

Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks

EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought

What Makes Good Examples for Visual In-Context Learning?

Time Series Kernels based on Nonlinear Vector AutoRegressive Delay Embeddings

CQM: Curriculum Reinforcement Learning with a Quantized World Model

Graph Contrastive Learning with Stable and Scalable Spectral Encoding

Pruning vs Quantization: Which is Better?

AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation

Learning Universal Policies via Text-Guided Video Generation

WildfireSpreadTS: A dataset of multi-modal time series for wildfire spread prediction

S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions

Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions

Adversarial Attacks on Online Learning to Rank with Click Feedback

RECESS Vaccine for Federated Learning: Proactive Defense Against Model Poisoning Attacks

ToolQA: A Dataset for LLM Question Answering with External Tools

AdaPlanner: Adaptive Planning from Feedback with Language Models

Revisiting Area Convexity: Faster Box-Simplex Games and Spectrahedral Generalizations

Structured Semidefinite Programming for Recovering Structured Preconditioners

Data Selection for Language Models via Importance Resampling

Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data

Multi-Player Zero-Sum Markov Games with Networked Separable Interactions

LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections

Learning Human Action Recognition Representations Without Real Humans

Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy

A General Theory of Correct, Incorrect, and Extrinsic Equivariance

How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources

SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multipiece Explanations

Nearly Optimal VC-Dimension and Pseudo-Dimension Bounds for Deep Neural Network Derivatives

Near-Linear Time Algorithm for the Chamfer Distance

Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies

Instructing Goal-Conditioned Reinforcement Learning Agents with Temporal Logic Objectives

Ignorance is Bliss: Robust Control via Information Gating

Language Models Meet World Models: Embodied Experiences Enhance Language Models

Optimal testing using combined test statistics across independent studies

CAT-Walk: Inductive Hypergraph Learning via Set Walks

No Representation Rules Them All in Category Discovery

Neural approximation of Wasserstein distance via a universal architecture for symmetric and factorwise group invariant functions

Closing the gap between the upper bound and lower bound of Adam's iteration complexity

Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception

Extremal Domain Translation with Neural Optimal Transport

Volume Feature Rendering for Fast Neural Radiance Field Reconstruction

TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials

Implicit Transfer Operator Learning: Multiple Time-Resolution Models for Molecular Dynamics

Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation

SNEkhorn: Dimension Reduction with Symmetric Entropic Affinities

PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds

Scale Alone Does not Improve Mechanistic Interpretability in Vision Models

CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models

Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond

Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts

Revisit the Power of Vanilla Knowledge Distillation: from Small Scale to Large Scale

Mitigating the Popularity Bias of Graph Collaborative Filtering: A Dimensional Collapse Perspective

Optimal Block-wise Asymmetric Graph Construction for Graph-based Semi-supervised Learning

Point Cloud Completion with Pretrained Text-to-Image Diffusion Models

On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks

Optimistic Meta-Gradients

Understanding and Improving Feature Learning for Out-of-Distribution Generalization

Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities

On the Pareto Front of Multilingual Neural Machine Translation

SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents

FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations

Calibrating “Cheap Signals” in Peer Review without a Prior

VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models

Causal Effect Identification in Uncertain Causal Networks

2Direction: Theoretically Faster Distributed Training with Bidirectional Communication Compression

Equivariant Adaptation of Large Pretrained Models

Hierarchical Multi-Agent Skill Discovery

Weighted ROC Curve in Cost Space: Extending AUC to Cost-Sensitive Learning

Self-Supervised Visual Acoustic Matching

Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors

Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning

SALSA VERDE: a machine learning attack on LWE with sparse small secrets

Incentives in Federated Learning: Equilibria, Dynamics, and Mechanisms for Welfare Maximization

Generalization bounds for neural ordinary differential equations and deep residual networks

Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression

End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes

Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis

UltraRE: Enhancing RecEraser for Recommendation Unlearning via Error Decomposition

Distribution-Free Statistical Dispersion Control for Societal Applications

Training neural operators to preserve invariant measures of chaotic attractors

Punctuation-level Attack: Single-shot and Single Punctuation Can Fool Text Models

A Riemannian Exponential Augmented Lagrangian Method for Computing the Projection Robust Wasserstein Distance

Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent

MixFormerV2: Efficient Fully Transformer Tracking

Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances

DAC-DETR: Divide the Attention Layers and Conquer

UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition

Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning

Hierarchical Integration Diffusion Model for Realistic Image Deblurring

Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models

Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design

Few-shot Generation via Recalling Brain-Inspired Episodic-Semantic Memory

Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing

Exact Bayesian Inference on Discrete Models via Probability Generating Functions: A Probabilistic Programming Approach

A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm

Off-Policy Evaluation for Human Feedback

AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking

Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance

Advancing Bayesian Optimization via Learning Correlated Latent Space

NuTrea: Neural Tree Search for Context-guided Multi-hop KGQA

Multi-Agent First Order Constrained Optimization in Policy Space

Optimal Time Complexities of Parallel Stochastic Optimization Methods Under a Fixed Computation Model

Learning Functional Transduction

Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation

Add and Thin: Diffusion for Temporal Point Processes

Learning Adaptive Tensorial Density Fields for Clean Cryo-ET Reconstruction

A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability

AIMS: All-Inclusive Multi-Level Segmentation for Anything

Empowering Convolutional Neural Nets with MetaSin Activation

Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks

Doubly Constrained Fair Clustering

Differentiable Neuro-Symbolic Reasoning on Large-Scale Knowledge Graphs

Core-sets for Fair and Diverse Data Summarization

Understanding the Limitations of Deep Models for Molecular property prediction: Insights and Solutions

The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter

No-Regret Learning with Unbounded Losses: The Case of Logarithmic Pooling

StreamNet: Memory-Efficient Streaming Tiny Deep Learning Inference on the Microcontroller

MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers

Module-wise Training of Neural Networks via the Minimizing Movement Scheme

Evolving Standardization for Continual Domain Generalization over Temporal Drift

Why Did This Model Forecast This Future? Information-Theoretic Saliency for Counterfactual Explanations of Probabilistic Regression Models

Self-Adaptive Motion Tracking against On-body Displacement of Flexible Sensors

Geometric Transformer with Interatomic Positional Encoding

Efficiently incorporating quintuple interactions into geometric deep learning force fields

Don’t just prune by magnitude! Your mask topology is a secret weapon

One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated Learning

Fine-Grained Visual Prompting

Shape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching via Unsupervised Functional Map Regularized Reconstruction

Efficient Testable Learning of Halfspaces with Adversarial Label Noise

Gradient Flossing: Improving Gradient Descent through Dynamic Control of Jacobians

Rehearsal Learning for Avoiding Undesired Future

Synthetic Combinations: A Causal Inference Framework for Combinatorial Interventions

A Framework for Fast and Stable Representations of Multiparameter Persistent Homology Decompositions

Variational Monte Carlo on a Budget — Fine-tuning pre-trained Neural Wavefunctions

Equivariant Single View Pose Prediction Via Induced and Restriction Representations

Debiased and Denoised Entity Recognition from Distant Supervision

UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models

Conformal PID Control for Time Series Prediction

The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions

Aligning Synthetic Medical Images with Clinical Knowledge using Human Feedback

CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement

Small batch deep reinforcement learning

Active representation learning for general task space with applications in robotics

Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks

The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification

Active Reasoning in an Open-World Environment

An Optimization-based Approach To Node Role Discovery in Networks: Approximating Equitable Partitions

Score-based Generative Modeling through Stochastic Evolution Equations in Hilbert Spaces

SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models

PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation

An Exploration-by-Optimization Approach to Best of Both Worlds in Linear Bandits

Probabilistic Inference in Reinforcement Learning Done Right

Diversify Your Vision Datasets with Automatic Diffusion-based Augmentation

Labeling Neural Representations with Inverse Recognition

Where Did I Come From? Origin Attribution of AI-Generated Images

Incentivizing Honesty among Competitors in Collaborative Learning and Optimization

LART: Neural Correspondence Learning with Latent Regularization Transformer for 3D Motion Transfer

In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer

Practical and Asymptotically Exact Conditional Sampling in Diffusion Models

XAGen: 3D Expressive Human Avatars Generation

ASPEN: Breaking Operator Barriers for Efficient Parallelization of Deep Neural Networks

Double Randomized Underdamped Langevin with Dimension-Independent Convergence Guarantee

Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach

What Planning Problems Can A Relational Neural Network Solve?

Revisiting Visual Model Robustness: A Frequency Long-Tailed Distribution View

Unlimiformer: Long-Range Transformers with Unlimited Length Input

Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism

DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models

Deep Reinforcement Learning with Plasticity Injection

Semi-Supervised Contrastive Learning for Deep Regression with Ordinal Rankings from Spectral Seriation

A Partially-Supervised Reinforcement Learning Framework for Visual Active Search

Neural Oscillators are Universal

QLoRA: Efficient Finetuning of Quantized LLMs

Rigorous Runtime Analysis of MOEA/D for Solving Multi-Objective Minimum Weight Base Problems

Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraints

Trade-off Between Efficiency and Consistency for Removal-based Explanations

Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms

Transition-constant Normalization for Image Enhancement

Directed Cyclic Graph for Causal Discovery from Multivariate Functional Data

GRAND-SLAMIN’ Interpretable Additive Modeling with Structural Constraints

H3T: Efficient Integration of Memory Optimization and Parallelism for Large-scale Transformer Training

Reusable Slotwise Mechanisms

FLSL: Feature-level Self-supervised Learning

Meta-Learning with Neural Bandit Scheduler

Deep Recurrent Optimal Stopping

Conditional score-based diffusion models for Bayesian inference in infinite dimensions

Rank-DETR for High Quality Object Detection

Importance-aware Co-teaching for Offline Model-based Optimization

Bayesian Learning via Q-Exponential Process

Online Clustering of Bandits with Misspecified User Models

Model-Based Control with Sparse Neural Dynamics

Synthetic Experience Replay

LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference

Scalarization for Multi-Task and Multi-Domain Learning at Scale

Stable Nonconvex-Nonconcave Training via Linear Interpolation

Intensity Profile Projection: A Framework for Continuous-Time Representation Learning for Dynamic Networks

Hierarchical clustering with dot products recovers hidden tree structure

A Hierarchical Spatial Transformer for Massive Point Samples in Continuous Space

Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training

Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts

How to Turn Your Knowledge Graph Embeddings into Generative Models

Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration

Promises and Pitfalls of Threshold-based Auto-labeling

Mitigating Source Bias for Fairer Weak Supervision

Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification

Skill-it! A data-driven skills framework for understanding and training language models

Anonymous and Copy-Robust Delegations for Liquid Democracy

Online Control for Meta-optimization

Long-Term Fairness with Unknown Dynamics

3D molecule generation by denoising voxel grids

Near-Optimal $k$-Clustering in the Sliding Window Model

Data Minimization at Inference Time

Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms

Ordering-based Conditions for Global Convergence of Policy Gradient Methods

SpecTr: Fast Speculative Decoding via Optimal Transport

The Separation Capacity of Random Neural Networks

Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models

Disentangled Wasserstein Autoencoder for T-Cell Receptor Engineering

Unleashing the Power of Randomization in Auditing Differentially Private ML

What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks

Attention as Implicit Structural Inference

A Reduction-based Framework for Sequential Decision Making with Delayed Feedback

Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction

Dynamic Tensor Decomposition via Neural Diffusion-Reaction Processes

OBJECT 3DIT: Language-guided 3D-aware Image Editing

Cola: A Benchmark for Compositional Text-to-image Retrieval

Learning to Influence Human Behavior with Offline Reinforcement Learning

Explaining V1 Properties with a Biologically Constrained Deep Learning Architecture

A Privacy-Friendly Approach to Data Valuation

On the Learnability of Multilabel Ranking

On Proper Learnability between Average- and Worst-case Robustness

GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection

Towards Robust and Expressive Whole-body Human Pose and Shape Estimation

SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation

Direct Preference-based Policy Optimization without Reward Modeling

Global Convergence Analysis of Local SGD for Two-layer Neural Network without Overparameterization

Into the LAION’s Den: Investigating Hate in Multimodal Datasets

Asynchronous Proportional Response Dynamics: Convergence in Markets with Adversarial Scheduling

What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization

Sharpness-Aware Minimization Leads to Low-Rank Features

Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer

Weakly-Supervised Audio-Visual Segmentation

DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation

CS4ML: A general framework for active learning with arbitrary data based on Christoffel functions

Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability

Approximately Equivariant Graph Networks

Active Bipartite Ranking

A fast heuristic to optimize time-space tradeoff for large models

Quilt-1M: One Million Image-Text Pairs for Histopathology

LightSpeed: Light and Fast Neural Light Fields on Mobile Devices

Stable and low-precision training for large-scale vision-language models

Stabilized Neural Differential Equations for Learning Dynamics with Explicit Constraints

Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

Rethinking the Role of Token Retrieval in Multi-Vector Retrieval

Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks

Learning to Tokenize for Generative Retrieval

Diversifying Spatial-Temporal Perception for Video Domain Generalization

Fine-Grained Human Feedback Gives Better Rewards for Language Model Training

Maximum Average Randomly Sampled: A Scale Free and Non-parametric Algorithm for Stochastic Bandits

LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation

PHOTOSWAP: Personalized Subject Swapping in Images

Provably Efficient Algorithm for Nonstationary Low-Rank MDPs

Binary Radiance Fields

Causal Discovery from Subsampled Time Series with Proxy Variables

One-Step Diffusion Distillation via Deep Equilibrium Models

PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile

Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks

Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective

Balancing memorization and generalization in RNNs for high performance brain-machine Interfaces

An Efficient Dataset Condensation Plugin and Its Application to Continual Learning

A Bounded Ability Estimation for Computerized Adaptive Testing

Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts

Efficient Hyper-parameter Optimization with Cubic Regularization

Invariant Learning via Probability of Sufficient and Necessary Causes

Towards A Richer 2D Understanding of Hands at Scale

Policy Optimization for Continuous Reinforcement Learning

On the Generalization Properties of Diffusion Models

Residual Q-Learning: Offline and Online Policy Customization without Value

Uncovering Neural Scaling Laws in Molecular Representation Learning

Convergence of Actor-Critic with Multi-Layer Neural Networks

Discriminative Calibration: Check Bayesian Computation from Simulations and Flexible Classifier

Diverse Conventions for Human-AI Collaboration

Temporal Dynamic Quantization for Diffusion Models

Non-Stationary Bandits with Auto-Regressive Temporal Dependency

AMDP: An Adaptive Detection Procedure for False Discovery Rate Control in High-Dimensional Mediation Analysis

Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation

A Robust and Opponent-Aware League Training Method for StarCraft II

Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?

Boosting Learning for LDPC Codes to Improve the Error-Floor Performance

Transformer-based Planning for Symbolic Regression

Fast Exact Leverage Score Sampling from Khatri-Rao Products with Applications to Tensor Decomposition

Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models

Sample based Explanations via Generalized Representers

MIM4DD: Mutual Information Maximization for Dataset Distillation

Post-processing Private Synthetic Data for Improving Utility on Selected Measures

Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement Learning

Efficient Symbolic Policy Learning with Differentiable Symbolic Expression

Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning

Context Shift Reduction for Offline Meta-Reinforcement Learning

Modeling Human Visual Motion Processing with Trainable Motion Energy Sensing and a Self-attention Network

Generalized Belief Transport

D$^2$CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts

UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction

Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objects

Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions

A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods

Finding Local Minima Efficiently in Decentralized Optimization

Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

Convex-Concave Zero-Sum Stochastic Stackelberg Games

Robust Learning with Progressive Data Expansion Against Spurious Correlation

Partial Label Learning with Dissimilarity Propagation guided Candidate Label Shrinkage

On the Adversarial Robustness of Out-of-distribution Generalization Models

Exact Optimality of Communication-Privacy-Utility Tradeoffs in Distributed Mean Estimation

Smooth Flipping Probability for Differential Private Sign Random Projection Methods

CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection

Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series

Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection

A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference

UDC-SIT: A Real-World Dataset for Under-Display Cameras

BayesDAG: Gradient-Based Posterior Inference for Causal Discovery

One-step differentiation of iterative algorithms

Low Tensor Rank Learning of Neural Dynamics

Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion

Data-Dependent Bounds for Online Portfolio Selection Without Lipschitzness and Smoothness

A Path to Simpler Models Starts With Noise

Attacks on Online Learners: a Teacher-Student Analysis

Tracr: Compiled Transformers as a Laboratory for Interpretability

New Complexity-Theoretic Frontiers of Tractability for Neural Network Training

GEO-Bench: Toward Foundation Models for Earth Monitoring

Coop: Memory is not a Commodity

TransHP: Image Classification with Hierarchical Prompting

RevColV2: Exploring Disentangled Representations in Masked Image Modeling

Synthetic-to-Real Pose Estimation with Geometric Reconstruction

PTADisc: A Cross-Course Dataset Supporting Personalized Learning in Cold-Start Scenarios

Stein $\Pi$-Importance Sampling

A Unified Detection Framework for Inference-Stage Backdoor Defenses

MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing

MARBLE: Music Audio Representation Benchmark for Universal Evaluation

Bayes beats Cross Validation: Efficient and Accurate Ridge Regression via Expectation Maximization

PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning

Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection

Certified Minimax Unlearning with Generalization Rates and Deletion Capacity

Failure-Aware Gaussian Process Optimization with Regret Bounds

SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions

CAST: Cross-Attention in Space and Time for Video Action Recognition

Best Arm Identification with Fixed Budget: A Large Deviation Perspective

RELIC: Reproducibility and Extension on LIC metric in quantifying bias in captioning models

Investigating how ReLU-networks encode symmetries

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives

A case for reframing automated medical image classification as segmentation

A generative model of the hippocampal formation trained with theta driven local learning rules

An Empirical Investigation of the Role of Pre-training in Lifelong Learning

Do Not Marginalize Mechanisms, Rather Consolidate!

Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction

GloptiNets: Scalable Non-Convex Optimization with Certificates

Latent exploration for Reinforcement Learning

Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods

Asymptotics of Bayesian Uncertainty Estimation in Random Features Regression

Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes

Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases

A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation

Optimization and Bayes: A Trade-off for Overparameterized Neural Networks

Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits

On the Statistical Consistency of Risk-Sensitive Bayesian Decision-Making

Exact Representation of Sparse Networks with Symmetric Nonnegative Embeddings

Efficient Subgame Refinement for Extensive-form Games

AmadeusGPT: a natural language interface for interactive animal behavioral analysis

Systematic Visual Reasoning through Object-Centric Relational Abstraction

Streaming PCA for Markovian Data

Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture

LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark

SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning

Improved Convergence in High Probability of Clipped Gradient Methods with Heavy Tailed Noise

NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics

RDumb: A simple approach that questions our progress in continual test-time adaptation

Behavior Alignment via Reward Function Optimization

Theoretical and Practical Perspectives on what Influence Functions Do

Effective Human-AI Teams via Learned Natural Language Rules and Onboarding

Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio

Sample Complexity of Goal-Conditioned Hierarchical Reinforcement Learning

Designing Robust Transformers using Robust Kernel Density Estimation

[Re] Masked Autoencoders Are Small Scale Vision Learners: A Reproduction Under Resource Constraints

Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning

Faster Relative Entropy Coding with Greedy Rejection Coding

AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs

Learning Space-Time Continuous Latent Neural PDEs from Partially Observed States

Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL

When Does Optimizing a Proper Loss Yield Calibration?

Survival Permanental Processes for Survival Analysis with Time-Varying Covariates

Accessing Higher Dimensions for Unsupervised Word Translation

A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems

ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields

No-Regret Learning in Dynamic Competition with Reference Effects Under Logit Demand

BubbleML: A Multiphase Multiphysics Dataset and Benchmarks for Machine Learning

Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities

Addressing the speed-accuracy simulation trade-off for adaptive spiking neurons

Information Theoretic Lower Bounds for Information Theoretic Upper Bounds

Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance

REx: Data-Free Residual Quantization Error Expansion

Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers

ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling

Learning from Active Human Involvement through Proxy Value Propagation

On Convergence of Polynomial Approximations to the Gaussian Mixture Entropy

Computational Guarantees for Doubly Entropic Wasserstein Barycenters

A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation

$H$-Consistency Bounds: Characterization and Extensions

Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation

PETAL: Physics Emulation Through Averaged Linearizations for Solving Inverse Problems

GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation

Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence

Diffusion Self-Guidance for Controllable Image Generation

Large Language Models can Implement Policy Iteration

SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding

Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift

On the Constrained Time-Series Generation Problem

Limits, approximation and size transferability for GNNs on sparse graphs via graphops

Hierarchical Open-vocabulary Universal Image Segmentation

SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning

GUST: Combinatorial Generalization by Unsupervised Grouping with Neuronal Coherence

Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models

In-Context Learning Unlocked for Diffusion Models

Offline Imitation Learning with Variational Counterfactual Reasoning

Cross-Scale MAE: A Tale of Multiscale Exploitation in Remote Sensing

Bilevel Coreset Selection in Continual Learning: A New Formulation and Algorithm

Gaussian Membership Inference Privacy

Noether Embedding: Efficient Learning of Temporal Regularities

Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates

NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding

Framework and Benchmarks for Combinatorial and Mixed-variable Bayesian Optimization

Hyper-Skin: A Hyperspectral Dataset for Reconstructing Facial Skin-Spectra from RGB Images

A Dataset of Relighted 3D Interacting Hands

A benchmark of categorical encoders for binary classification

Datasets and Benchmarks for Nanophotonic Structure and Parametric Design Simulations

Ethical Considerations for Responsible Data Curation

A Comprehensive Benchmark for Neural Human Radiance Fields

ProteinShake: Building datasets and benchmarks for deep learning on protein structures

RoboHive: A Unified Framework for Robot Learning

Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning

HubRouter: Learning Global Routing via Hub Generation and Pin-hub Connection

Strategic Data Sharing between Competitors

Towards Efficient Image Compression Without Autoregressive Models

M5HisDoc: A Large-scale Multi-style Chinese Historical Document Analysis Benchmark

CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra

Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint

ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation

Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics

PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers

The geometry of hidden representations of large transformer models

Formalizing locality for normative synaptic plasticity models

Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask?

Three Iterations of (d − 1)-WL Test Distinguish Non Isometric Clouds of d-dimensional Points

NCDL: A Framework for Deep Learning on non-Cartesian Lattices

The Geometry of Neural Nets' Parameter Spaces Under Reparametrization

When Does Confidence-Based Cascade Deferral Suffice?

Geometric Neural Diffusion Processes

Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents

What Can We Learn from Unlearnable Datasets?

Understanding and Mitigating Copying in Diffusion Models

On the Exploitability of Instruction Tuning

How to Scale Your EMA

Towards In-context Scene Understanding

Taming Local Effects in Graph-based Spatiotemporal Forecasting

Learning threshold neurons via edge of stability

Optimized Covariance Design for AB Test on Social Network under Interference

FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models

The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications

Participatory Personalization in Classification

Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Events

Adaptive Test-Time Personalization for Federated Learning

Graph-Structured Gaussian Processes for Transferable Graph Learning

Guiding Large Language Models via Directional Stimulus Prompting

Contextual Bandits and Imitation Learning with Preference-Based Active Queries

Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task

Regularity as Intrinsic Reward for Free Play

Can Language Models Teach? Teacher Explanations Improve Student Performance via Personalization

Exploring Question Decomposition for Zero-Shot VQA

Kernelized Cumulants: Beyond Kernel Mean Embeddings

ChessGPT: Bridging Policy Learning and Language Modeling

Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior

P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting

GEX: A flexible method for approximating influence via Geometric Ensemble

Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition

Accelerating Exploration with Unlabeled Prior Data

Counterfactual Generation with Identifiability Guarantees

Benchmarking and Analyzing 3D-aware Image Synthesis with a Modularized Codebase

Federated Learning with Client Subsampling, Data Heterogeneity, and Unbounded Smoothness: A New Algorithm and Lower Bounds

Spectral Evolution and Invariance in Linear-width Neural Networks

Unsupervised Graph Neural Architecture Search with Disentangled Self-Supervision

Multi-task Graph Neural Architecture Search with Task-aware Collaboration and Curriculum

OpenMask3D: Open-Vocabulary 3D Instance Segmentation

Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approach

Riemannian SAM: Sharpness-Aware Minimization on Riemannian Manifolds

A Metadata-Driven Approach to Understand Graph Neural Networks

A Sublinear-Time Spectral Clustering Oracle with Improved Preprocessing Time

QuIP: 2-Bit Quantization of Large Language Models With Guarantees

Cascading Contextual Assortment Bandits

Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation

DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation

Generalizing Nonlinear ICA Beyond Structural Sparsity

Joint Data-Task Generation for Auxiliary Learning

Tanh Works Better with Asymmetry

Demographic Parity Constrained Minimax Optimal Regression under Linear Model

Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning

Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems

D4: Improving LLM Pretraining via Document De-Duplication and Diversification

CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labels

RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability

Self-Supervised Reinforcement Learning that Transfers using Random Features

Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses

Fine-grained Expressivity of Graph Neural Networks

Analyzing the Sample Complexity of Self-Supervised Image Reconstruction Methods

PUe: Biased Positive-Unlabeled Learning Enhancement by Causal Inference

Collaborative Learning via Prediction Consensus

Likelihood-Based Diffusion Language Models

HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception

Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars

Simplifying and Empowering Transformers for Large-Graph Representations

Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models

HiBug: On Human-Interpretable Model Debug

A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression

Causal normalizing flows: from theory to practice

CMMA: Benchmarking Multi-Affection Detection in Chinese Multi-Modal Conversations

RRHF: Rank Responses to Align Language Models with Human Feedback

Causes and Effects of Unanticipated Numerical Deviations in Neural Network Inference Frameworks

Learning Invariant Molecular Representation in Latent Discrete Space

A Dataset for Analyzing Streaming Media Performance over HTTP/3 Browsers

The Transient Nature of Emergent In-Context Learning in Transformers

Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition

Tree Variational Autoencoders

Improving Compositional Generalization using Iterated Learning and Simplicial Embeddings

Direct Diffusion Bridge using Data Consistency for Inverse Problems

Interpretable Prototype-based Graph Information Bottleneck

Latent Field Discovery in Interacting Dynamical Systems with Neural Fields

Supported Value Regularization for Offline Reinforcement Learning

Homotopy-based training of NeuralODEs for accurate dynamics discovery

An Efficient End-to-End Training Approach for Zero-Shot Human-AI Coordination

Knowledge Distillation Performs Partial Variance Reduction

On the Consistency of Maximum Likelihood Estimation of Probabilistic Principal Component Analysis

Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration

ZipLM: Inference-Aware Structured Pruning of Language Models

Block Coordinate Plug-and-Play Methods for Blind Inverse Problems

PaintSeg: Painting Pixels for Training-free Segmentation

A Batch-to-Online Transformation under Random-Order Model

Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick

Accelerating Motion Planning via Optimal Transport

GenEval: An object-focused framework for evaluating text-to-image alignment

ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling

DVSOD: RGB-D Video Salient Object Detection

Beyond Normal: On the Evaluation of Mutual Information Estimators

MMD-Fuse: Learning and Combining Kernels for Two-Sample Testing Without Data Splitting

Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization

IDEA: An Invariant Perspective for Efficient Domain Adaptive Image Retrieval

A Robust Exact Algorithm for the Euclidean Bipartite Matching Problem

Parameter-efficient Tuning of Large-scale Multimodal Foundation Model

Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks

FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models

Coherent Soft Imitation Learning

Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics

A Cross-Moment Approach for Causal Effect Estimation

Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning

Beyond probability partitions: Calibrating neural networks with semantic aware grouping

Compressed Video Prompt Tuning

Semantic HELM: A Human-Readable Memory for Reinforcement Learning

Universality laws for Gaussian mixtures in generalized linear models

Model-Free Active Exploration in Reinforcement Learning

Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models

Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance

LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching

Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models

DP-HyPO: An Adaptive Private Framework for Hyperparameter Optimization

Epidemic Learning: Boosting Decentralized Learning with Randomized Communication

Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds

Boosting with Tempered Exponential Measures

Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis

Two Heads are Better Than One: A Simple Exploration Framework for Efficient Multi-Agent Reinforcement Learning

Brain-like Flexible Visual Inference by Harnessing Feedback Feedforward Alignment

Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models

Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks

Intrinsic Gaussian Process on Unknown Manifolds with Probabilistic Metrics

DataPerf: Benchmarks for Data-Centric AI Development

Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans

Towards Distribution-Agnostic Generalized Category Discovery

The Best of Both Worlds in Network Population Games: Reaching Consensus and Convergence to Equilibrium

SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoning

Large sample spectral analysis of graph-based multi-manifold clustering

Slimmed Asymmetrical Contrastive Learning and Cross Distillation for Lightweight Model Training

Self-Evaluation Guided Beam Search for Reasoning

Mitigating Test-Time Bias for Fair Image Retrieval

Hyperbolic VAE via Latent Gaussian Distributions

What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?

Identifiable Contrastive Learning with Automatic Feature Importance Discovery

Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reduction

RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars

ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings

Neural Lyapunov Control for Discrete-Time Systems

You Only Condense Once: Two Rules for Pruning Condensed Datasets

ExPT: Synthetic Pretraining for Few-Shot Experimental Design

Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective

Implicit Convolutional Kernels for Steerable CNNs

ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection

The Cambridge Law Corpus: A Corpus for Legal AI Research

Stable Bias: Evaluating Societal Representations in Diffusion Models

RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation

M$^{2}$SODAI: Multi-Modal Maritime Object Detection Dataset With RGB and Hyperspectral Image Sensors

BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting

RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments

Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning

Learning from Visual Observation via Offline Pretrained State-to-Go Transformer

Robust Data Valuation with Weighted Banzhaf Values

Implicit Manifold Gaussian Process Regression

Semantic segmentation of sparse irregular point clouds for leaf/wood discrimination

Language Model Tokenizers Introduce Unfairness Between Languages

Common Ground in Cooperative Communication

Vocabulary-free Image Classification

Optimal privacy guarantees for a relaxed threat model: Addressing sub-optimal adversaries in differentially private machine learning

Learning Provably Robust Estimators for Inverse Problems via Jittering

Rethinking Gauss-Newton for learning over-parameterized models

Entropic Neural Optimal Transport via Diffusion Processes

Latent SDEs on Homogeneous Spaces

SoTTA: Robust Test-Time Adaptation on Noisy Data Streams

Does Continual Learning Meet Compositionality? New Benchmarks and An Evaluation Framework

Large Language Models Are Semi-Parametric Reinforcement Learning Agents

Towards a Comprehensive Benchmark for High-Level Synthesis Targeted to FPGAs

ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation

Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval

Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models

T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation

Memory Efficient Optimizers with 4-bit States

Unleashing the Full Potential of Product Quantization for Large-Scale Image Retrieval

ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation

VideoComposer: Compositional Video Synthesis with Motion Controllability

Learning to Modulate pre-trained Models in RL

LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning

Nonparametric Teaching for Multiple Learners

Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?

Federated Learning via Meta-Variational Dropout

Minimax Risks and Optimal Procedures for Estimation under Functional Local Differential Privacy

CLeAR: Continual Learning on Algorithmic Reasoning for Human-like Intelligence

DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation

Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models

Enhancing Adversarial Robustness via Score-Based Optimization

D-Separation for Causal Self-Explanation

Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations

ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction

Enhancing Robot Program Synthesis Through Environmental Context

Enhancing Minority Classes by Mixing: An Adaptative Optimal Transport Approach for Long-tailed Classification

Learning and processing the ordinal information of temporal sequences in recurrent neural circuits

Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion

Emergent Communication for Rules Reasoning

A Variational Perspective on High-Resolution ODEs

AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix

Quantification of Uncertainty with Adversarial Models

Minimax Forward and Backward Learning of Evolving Tasks with Performance Guarantees

Degraded Polygons Raise Fundamental Questions of Neural Network Perception

Interaction Measures, Partition Lattices and Kernel Tests for High-Order Interactions

Provably Efficient Offline Reinforcement Learning in Regular Decision Processes

Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships

GMSF: Global Matching Scene Flow

Parts of Speech–Grounded Subspaces in Vision-Language Models

Subject-driven Text-to-Image Generation via Apprenticeship Learning

On permutation symmetries in Bayesian neural network posteriors: a variational perspective

Language Semantic Graph Guided Data-Efficient Learning

Isometric Quotient Variational Auto-Encoders for Structure-Preserving Representation Learning

Learning World Models with Identifiable Factorization

Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union

A Dynamical System View of Langevin-Based Non-Convex Sampling

Stochastic Approximation Algorithms for Systems of Interacting Particles

Synthcity: a benchmark framework for diverse use cases of tabular synthetic data

Multitask Learning with No Regret: from Improved Confidence Bounds to Active Learning

On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay

Content-based Unrestricted Adversarial Attack

Regularization properties of adversarially-trained linear regression

State Regularized Policy Optimization on Data with Dynamics Shift

KuaiSim: A Comprehensive Simulator for Recommender Systems

Leveraging Locality and Robustness to Achieve Massively Scalable Gaussian Process Regression

RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization

E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning

Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff

Unbiased constrained sampling with Self-Concordant Barrier Hamiltonian Monte Carlo

Harnessing Hard Mixed Samples with Decoupled Regularizer

On the Minimax Regret for Online Learning with Feedback Graphs

Retaining Beneficial Information from Detrimental Data for Neural Network Repair

Sparse Graph Learning from Spatiotemporal Time Series

StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners

InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Temporal Continual Learning with Prior Compensation for Human Motion Prediction

DreamHuman: Animatable 3D Avatars from Text

TriRE: A Multi-Mechanism Learning Paradigm for Continual Knowledge Retention and Promotion

ESSEN: Improving Evolution State Estimation for Temporal Networks using Von Neumann Entropy

Thinker: Learning to Plan and Act

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

Spontaneous symmetry breaking in generative diffusion models

Adversarial Training from Mean Field Perspective

Self-Supervised Motion Magnification by Backpropagating Through Optical Flow

Are Diffusion Models Vision-And-Language Reasoners?

Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion

Learning Layer-wise Equivariances Automatically using Gradients

Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning

Understanding Few-Shot Learning: Measuring Task Relatedness and Adaptation Difficulty via Attributes

Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models

Fairly Recommending with Social Attributes: A Flexible and Controllable Optimization Approach

Unifying GANs and Score-Based Diffusion as Generative Particle Models

Bi-Level Offline Policy Optimization with Limited Exploration

NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF

Coneheads: Hierarchy Aware Attention

Towards Label-free Scene Understanding by Vision Foundation Models

Transient Neural Radiance Fields for Lidar View Synthesis and 3D Reconstruction

Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments

Why Does Sharpness-Aware Minimization Generalize Better Than SGD?

Training Transitive and Commutative Multimodal Transformers with LoReTTa

A graphon-signal analysis of graph neural networks

Structure Learning with Adaptive Random Neighborhood Informed MCMC

On the Role of Randomization in Adversarially Robust Classification

Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows

GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces

Delegated Classification

Fast Projected Newton-like Method for Precision Matrix Estimation under Total Positivity

Explaining Predictive Uncertainty with Information Theoretic Shapley Values

Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering

GLEMOS: Benchmark for Instantaneous Graph Learning Model Selection

MMD Aggregated Two-Sample Test

Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation

Statistical and Computational Trade-off in Multi-Agent Multi-Armed Bandits

A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints

Understanding the detrimental class-level effects of data augmentation

Optimistic Active Exploration of Dynamical Systems

Beyond Average Return in Markov Decision Processes

Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference

Low-shot Object Learning with Mutual Exclusivity Bias

4M: Massively Multimodal Masked Modeling

What’s Left? Concept Grounding with Logic-Enhanced Foundation Models

[Re] On the Reproducibility of “FairCal: Fairness Calibration for Face Verification”

Grounding Neural Inference with Satisfiability Modulo Theories

FedL2P: Federated Learning to Personalize

Variational Weighting for Kernel Density Ratios

Temporally Disentangled Representation Learning under Unknown Nonstationarity

Improving multimodal datasets with image captioning

On the Connection between Pre-training Data Diversity and Fine-tuning Robustness

Towards robust and generalizable representations of extracellular data using contrastive learning

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild

Encoding Human Behavior in Information Design through Deep Learning

High-dimensional Contextual Bandit Problem without Sparsity

In-Context Impersonation Reveals Large Language Models' Strengths and Biases

On the Interplay between Social Welfare and Tractability of Equilibria

Finding Counterfactually Optimal Action Sequences in Continuous State Spaces

Human-Aligned Calibration for AI-Assisted Decision Making

Loss Dynamics of Temporal Difference Reinforcement Learning

Strategic Distribution Shift of Interacting Agents via Coupled Gradient Flows

A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games

Data-Centric Learning from Unlabeled Graphs with Diffusion Model

Structured Neural Networks for Density Estimation and Causal Inference

MVDoppler: Unleashing the Power of Multi-View Doppler for MicroMotion-based Gait Classification

Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images

Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor

Percentile Criterion Optimization in Offline Reinforcement Learning

On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes

Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models

Projection-Free Methods for Solving Nonconvex-Concave Saddle Point Problems

Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning

Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels

Deep Stochastic Processes via Functional Markov Transition Operators

CoDrug: Conformal Drug Property Prediction with Density Estimation under Covariate Shift

Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers

Multiclass Boosting: Simple and Intuitive Weak Learning Criteria

Multiply Robust Federated Estimation of Targeted Average Treatment Effects

PTQD: Accurate Post-Training Quantization for Diffusion Models

Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure

3D-LLM: Injecting the 3D World into Large Language Models

Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion

The Impact of Positional Encoding on Length Generalization in Transformers

Riemannian Residual Neural Networks

Bayesian Active Causal Discovery with Multi-Fidelity Experiments

V-InFoR: A Robust Graph Neural Networks Explainer for Structurally Corrupted Graphs

Cross-links Matter for Link Prediction: Rethinking the Debiased GNN from a Data Perspective

Model-enhanced Vector Index

RD-Suite: A Benchmark for Ranking Distillation

ADGym: Design Choices for Deep Anomaly Detection

Online List Labeling with Predictions

Federated Compositional Deep AUC Maximization

Non-Smooth Weakly-Convex Finite-sum Coupled Compositional Optimization

SpatialRank: Urban Event Ranking with NDCG Optimization on Spatiotemporal Data

GAN You See Me? Enhanced Data Reconstruction Attacks against Split Inference

Dynamic Non-monotone Submodular Maximization

Lovász Principle for Unsupervised Graph Representation Learning

Graph Convolutional Kernel Machine versus Graph Convolutional Networks

Learning Domain-Aware Detection Head with Prompt Tuning

Model Shapley: Equitable Model Valuation with Black-box Access

Incentives in Private Collaborative Machine Learning

Factorized Contrastive Learning: Going Beyond Multi-view Redundancy

IBA: Towards Irreversible Backdoor Attacks in Federated Learning

Black-box Backdoor Defense via Zero-shot Image Purification

DiViNeT: 3D Reconstruction from Disparate Views using Neural Template Regularization

Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning

What Truly Matters in Trajectory Prediction for Autonomous Driving?

Binarized Neural Machine Translation

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Block-Coordinate Methods and Restarting for Solving Extensive-Form Games

Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power

Causal-structure Driven Augmentations for Text OOD Generalization

Don’t blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy

Enhancing User Intent Capture in Session-Based Recommendation with Attribute Patterns

Evaluating Neuron Interpretation Methods of NLP Models

Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation

A Computationally Efficient Sparsified Online Newton Method

Gradient-Based Feature Learning under Structured Data

Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language

Going beyond persistent homology using persistent homology

A Scale-Invariant Sorting Criterion to Find a Causal Order in Additive Noise Models

Towards Unbounded Machine Unlearning

On the Exploration of Local Significant Differences For Two-Sample Test

Tame a Wild Camera: In-the-Wild Monocular Camera Calibration

NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks

Is Heterogeneity Notorious? Taming Heterogeneity to Handle Test-Time Shift in Federated Learning

Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation

Towards Symmetry-Aware Generation of Periodic Materials

Conditional Score Guidance for Text-Driven Image-to-Image Translation

Towards Efficient and Accurate Winograd Convolution via Full Quantization

StyleDrop: Text-to-Image Synthesis of Any Style

On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences

Detection Based Part-level Articulated Object Reconstruction from Single RGBD Image

Explore to Generalize in Zero-Shot RL

Adversarial Resilience in Sequential Prediction via Abstention

Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck

Practical Contextual Bandits with Feedback Graphs

Graph Clustering with Graph Neural Networks

Block-State Transformers

Flow Matching for Scalable Simulation-Based Inference

Text Alignment Is An Efficient Unified Model for Massive NLP Tasks

Concept Algebra for (Score-Based) Text-Controlled Generative Models

Image Captioners Are Scalable Vision Learners Too

Diverse Community Data for Benchmarking Data Privacy Algorithms

Generalized Bayesian Inference for Scientific Simulators via Amortized Cost Estimation

ANTN: Bridging Autoregressive Neural Networks and Tensor Networks for Quantum Many-Body Simulation

Front-door Adjustment Beyond Markov Equivalence with Limited Graph Knowledge

FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networks

Anchor Data Augmentation

RADAR: Robust AI-Text Detection via Adversarial Learning

HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models

Uncovering and Quantifying Social Biases in Code Generation

Deep Equilibrium Based Neural Operators for Steady-State PDEs

COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs

Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning

Higher-Order Uncoupled Dynamics Do Not Lead to Nash Equilibrium - Except When They Do

Handling Data Heterogeneity via Architectural Design for Federated Visual Recognition

ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design

Resetting the Optimizer in Deep RL: An Empirical Study

A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks

The Bayesian Stability Zoo

Optimal Preconditioning and Fisher Adaptive Langevin Sampling

Revealing the unseen: Benchmarking video action recognition under occlusion

Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks

Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models

Reversible and irreversible bracket-based dynamics for deep graph neural networks

SiT Dataset: Socially Interactive Pedestrian Trajectory Dataset for Social Navigation Robots

Information Design in Multi-Agent Reinforcement Learning

Representational Strengths and Limitations of Transformers

Renku: a platform for sustainable data science

Toolformer: Language Models Can Teach Themselves to Use Tools

Making Scalable Meta Learning Practical

Near-optimal learning with average Hölder smoothness

Learning Unseen Modality Interaction

Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation

Normalizing flow neural networks by JKO scheme

A Unified Algorithm Framework for Unsupervised Discovery of Skills based on Determinantal Point Process

Have it your way: Individualized Privacy Assignment for DP-SGD

Probabilistic Invariant Learning with Randomized Linear Classifiers

Distributionally Robust Ensemble of Lottery Tickets Towards Calibrated Sparse Network Training

BadTrack: A Poison-Only Backdoor Attack on Visual Object Tracking

Exposing Attention Glitches with Flip-Flop Language Modeling

Batchnorm Allows Unsupervised Radial Attacks

Graph of Circuits with GNN for Exploring the Optimal Design Space

Offline Reinforcement Learning for Mixture-of-Expert Dialogue Management

Label-Only Model Inversion Attacks via Knowledge Transfer

Likelihood Ratio Confidence Sets for Sequential Decision Making

LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction

RoboCLIP: One Demonstration is Enough to Learn Robot Policies

Use perturbations when learning from explanations

First- and Second-Order Bounds for Adversarial Linear Contextual Bandits

Kernelized Reinforcement Learning with Order Optimal Regret Bounds

WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data

Equivariant Neural Operator Learning with Graphon Convolution

Bypassing spike sorting: Density-based decoding using spike localization from dense multielectrode probes

Auxiliary Losses for Learning Generalizable Concept-based Models

Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design

Siamese Masked Autoencoders

How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Ego4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities

HT-Step: Aligning Instructional Articles with How-To Videos

CEIL: Generalized Contextual Imitation Learning

Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization

$L_2$-Uniform Stability of Randomized Learning Algorithms: Sharper Generalization Bounds and Confidence Boosting

Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems

DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models

Disentangling Cognitive Diagnosis with Limited Exercise Labels

ProPILE: Probing Privacy Leakage in Large Language Models

Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time

Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity

Towards Stable Backdoor Purification through Feature Shift Tuning

Flat Seeking Bayesian Neural Networks

Unified Lower Bounds for Interactive High-dimensional Estimation under Information Constraints

Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation

Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation

Fragment-based Pretraining and Finetuning on Molecular Graphs

Demystifying Oversmoothing in Attention-Based Graph Neural Networks

White-Box Transformers via Sparse Rate Reduction

Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection

Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization

Learning to Augment Distributions for Out-of-distribution Detection

Koopman Kernel Regression

Circuit as Set of Points

NeRF-IBVS: Visual Servo Based on NeRF for Visual Localization and Navigation

CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation

Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds

Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL

Nonparametric Identifiability of Causal Representations from Unknown Interventions

XES3G5M: A Knowledge Tracing Benchmark Dataset with Auxiliary Information

Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text

CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss

KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training

Inserting Anybody in Diffusion Models via Celeb Basis

Direct Training of SNN using Local Zeroth Order Method

MIMEx: Intrinsic Rewards from Masked Input Modeling

Contextually Affinitive Neighborhood Refinery for Deep Clustering

Diplomat: A Dialogue Dataset for Situated PragMATic Reasoning

Analysis of Variance of Multiple Causal Networks

FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective

Easy Bayesian Transfer Learning with Informative Priors

Predicting a Protein's Stability under a Million Mutations

Spike-driven Transformer

State Sequences Prediction via Fourier Transform for Representation Learning

Uncertainty Estimation for Safety-critical Scene Segmentation via Fine-grained Reward Maximization

Convergence of Adam Under Relaxed Assumptions

Convex and Non-convex Optimization Under Generalized Smoothness

K-Nearest-Neighbor Local Sampling Based Conditional Independence Testing

Slow and Weak Attractor Computation Embedded in Fast and Strong E-I Balanced Neural Dynamics

PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas

Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts

Model Sparsity Can Simplify Machine Unlearning

On the Powerfulness of Textual Outlier Exposure for Visual OoD Detection

Understanding Contrastive Learning via Distributionally Robust Optimization

Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift

Video-Mined Task Graphs for Keystep Recognition in Instructional Videos

PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization

GNeSF: Generalizable Neural Semantic Fields

Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference

Imitation Learning from Imperfection: Theoretical Justifications and Algorithms

Penguin: Parallel-Packed Homomorphic Encryption for Fast Graph Convolutional Network Inference

On the Identifiability of Sparse ICA without Assuming Non-Gaussianity

Exploiting Connections between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models

Decompose a Task into Generalizable Subtasks in Multi-Agent Reinforcement Learning

Kiki or Bouba? Sound Symbolism in Vision-and-Language Models

UP-NeRF: Unconstrained Pose Prior-Free Neural Radiance Field

DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions

Scalable Transformer for PDE Surrogate Modeling

Corruption-Robust Offline Reinforcement Learning with General Function Approximation

Minimax-Optimal Location Estimation

Navigating Data Heterogeneity in Federated Learning: A Semi-Supervised Approach for Object Detection

Generating Behaviorally Diverse Policies with Latent Diffusion Models

Semantic Image Synthesis with Unconditional Generator

Variational Gaussian Processes with Decoupled Conditionals

Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control

Private Everlasting Prediction

Calibrate and Boost Logical Expressiveness of GNN Over Multi-Relational and Temporal Graphs

An $\varepsilon$-Best-Arm Identification Algorithm for Fixed-Confidence and Beyond

Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery

Emergent Correspondence from Image Diffusion

Clustering the Sketch: Dynamic Compression for Embedding Tables

LIMA: Less Is More for Alignment

Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?

Amortized Reparametrization: Efficient and Scalable Variational Inference for Latent SDEs

Understanding Social Reasoning in Language Models with Language Models

Data-Informed Geometric Space Selection

Post Hoc Explanations of Language Models Can Improve Language Models

Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability

Evaluating Cognitive Maps and Planning in Large Language Models with CogEval

Benchmarking Robustness to Adversarial Image Obfuscations

Practical Equivariances via Relational Conditional Neural Processes

Learning Robust Statistics for Simulation-based Inference under Model Misspecification

Random-Access Infinite Context Length for Transformers

Preference-grounded Token-level Guidance for Language Model Fine-tuning

Critical Initialization of Wide and Deep Neural Networks using Partial Jacobians: General Theory and Applications

Bounding training data reconstruction in DP-SGD

Structured Prediction with Stronger Consistency Guarantees

SSL4EO-L: Datasets and Foundation Models for Landsat Imagery

Data Market Design through Deep Learning

History Filtering in Imperfect Information Games: Algorithms and Complexity

Guarantees for Self-Play in Multiplayer Games via Polymatrix Decomposability

VoxDet: Voxel Learning for Novel Instance Detection

Language Is Not All You Need: Aligning Perception with Language Models

The Pick-to-Learn Algorithm: Empowering Compression for Tight Generalization Bounds and Improved Post-training Performance

Model-free Posterior Sampling via Learning Rate Randomization

Adaptive Privacy Composition for Accuracy-first Mechanisms

Red Teaming Deep Neural Networks with Feature Synthesis Tools

Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies

VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution

Active Negative Loss Functions for Learning with Noisy Labels

Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent

Provably Bounding Neural Network Preimages

WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting

Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning

Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars

Density of States Prediction of Crystalline Materials via Prompt-guided Multi-Modal Transformer

Neural Harmonics: Bridging Spectral Embedding and Matrix Completion in Self-Supervised Learning

Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond

TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models

The ToMCAT Dataset

Loss Decoupling for Task-Agnostic Continual Learning

Reining Generalization in Offline Reinforcement Learning via Representation Distinction

Hierarchically Gated Recurrent Neural Network for Sequence Modeling

Universal Gradient Descent Ascent Method for Nonconvex-Nonconcave Minimax Optimization

HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds

Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation

Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models

Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection

Tanimoto Random Features for Scalable Molecular Machine Learning

Derandomized novelty detection with FDR control via conformal e-values

Birder: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN Training

Reinforcement Learning with Simple Sequence Priors

DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model

Private estimation algorithms for stochastic block models and mixture models

Optimal Transport Model Distributional Robustness

Robust covariance estimation with missing values and cell-wise contamination

Causal Component Analysis

BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization

Goal-conditioned Offline Planning from Curious Exploration

Online Learning under Adversarial Nonlinear Constraints

Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond

Unbalanced Low-rank Optimal Transport Solvers

DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing

Frequency-domain MLPs are More Effective Learners in Time Series Forecasting

The Pursuit of Human Labeling: A New Perspective on Unsupervised Learning

Energy Guided Diffusion for Generating Neurally Exciting Images

Spuriosity Didn’t Kill the Classifier: Using Invariant Predictions to Harness Spurious Features

AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation

Blurred-Dilated Method for Adversarial Attacks

CODA: Generalizing to Open and Unseen Domains with Compaction and Disambiguation

Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing

Fast Optimal Transport through Sliced Generalized Wasserstein Geodesics

VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks

Regularized Behavior Cloning for Blocking the Leakage of Past Action Information

Transformer as a hippocampal memory consolidation model based on NMDAR-inspired nonlinearity

RaLEs: a Benchmark for Radiology Language Evaluations

On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training

Proximity-Informed Calibration for Deep Neural Networks

Active Learning for Semantic Segmentation with Multi-class Label Query

On the Convergence of CART under Sufficient Impurity Decrease Condition

Non-Rigid Shape Registration via Deep Functional Maps Prior

A Diffusion-Model of Joint Interactive Navigation

Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection

Predict-then-Calibrate: A New Perspective of Robust Contextual LP

SAMoSSA: Multivariate Singular Spectrum Analysis with Stochastic Autoregressive Noise

Langevin Quasi-Monte Carlo

Anonymous Learning via Look-Alike Clustering: A Precise Analysis of Model Generalization

Mass-Producing Failures of Multimodal Systems with Language Models

ODE-based Recurrent Model-free Reinforcement Learning for POMDPs

Deductive Verification of Chain-of-Thought Reasoning

Controlling Text-to-Image Diffusion by Orthogonal Finetuning

$SE(3)$ Equivariant Convolution and Transformer in Ray Space

Memory-Constrained Algorithms for Convex Optimization

Neural Image Compression: Generalization, Robustness, and Spectral Biases

Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agents

OKRidge: Scalable Optimal k-Sparse Ridge Regression

Identification of Nonlinear Latent Hierarchical Models

Online Convex Optimization with Unbounded Memory

On the Gini-impurity Preservation For Privacy Random Forests

Learning Topology-Agnostic EEG Representations with Geometry-Aware Modeling

A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Causal Relationship

MeCo: Zero-Shot NAS with One Data and Single Forward Pass via Minimum Eigenvalue of Correlation

OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization

Statistically Valid Variable Importance Assessment through Conditional Permutations

Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise

Topology-Aware Uncertainty for Image Segmentation

Lexinvariant Language Models

PRODIGY: Enabling In-context Learning Over Graphs

Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model

Reproducibility Study of “Quantifying Societal Bias Amplification in Image Captioning”

PopSign ASL v1.0: An Isolated American Sign Language Dataset Collected via Smartphones

Black-Box Differential Privacy for Interactive ML

FORB: A Flat Object Retrieval Benchmark for Universal Image Embedding

Latent Diffusion for Language Generation

$\mathbf{\mathbb{E}^{FWI}}$: Multiparameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties

SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction

ResoNet: Noise-Trained Physics-Informed MRI Off-Resonance Correction

Decorate3D: Text-Driven High-Quality Texture Generation for Mesh Decoration in the Wild

Robust Knowledge Transfer in Tiered Reinforcement Learning

Explainable Brain Age Prediction using coVariance Neural Networks

Refined Mechanism Design for Approximately Structured Priors via Active Regression

Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

Sharp Recovery Thresholds of Tensor PCA Spectral Algorithms

Estimating and Controlling for Equalized Odds via Sensitive Attribute Predictors

Star-Shaped Denoising Diffusion Probabilistic Models

Uncertainty Quantification via Neural Posterior Principal Components

CD-GraB: Coordinating Distributed Example Orders for Provably Accelerated Training

Fairness Aware Counterfactuals for Subgroups

Versatile Energy-Based Probabilistic Models for High Energy Physics

Agnostic Multi-Group Active Learning

ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification

Compositional Sculpting of Iterative Generative Processes

On the Robustness of Mechanism Design under Total Variation Distance

American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers

Residual Alignment: Uncovering the Mechanisms of Residual Networks

Optimizing Prompts for Text-to-Image Generation

Mobilizing Personalized Federated Learning in Infrastructure-Less and Heterogeneous Environments via Random Walk Stochastic ADMM

Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation

PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion Models

Empowering Collaborative Filtering with Principled Adversarial Contrastive Loss

Iteratively Learn Diverse Strategies with State Distance Information

Riemannian stochastic optimization methods avoid strict saddle points

Soft-Unification in Deep Probabilistic Logic

Belief Projection-Based Reinforcement Learning for Environments with Delayed Feedback

Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization

Tree-Based Diffusion Schrödinger Bridge with Applications to Wasserstein Barycenters

Diffused Task-Agnostic Milestone Planner

Provable Training for Graph Contrastive Learning

Self-supervised Object-Centric Learning for Videos

EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images

Slot-guided Volumetric Object Radiance Fields

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models

Topological Obstructions and How to Avoid Them

TopoSRL: Topology preserving self-supervised Simplicial Representation Learning

D-CIPHER: Discovery of Closed-form Partial Differential Equations

Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach

Contrastive Training of Complex-Valued Autoencoders for Object Discovery

Reinforcement-Enhanced Autoregressive Feature Transformation: Gradient-steered Search in Continuous Space for Postfix Expressions

TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation

Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties

Decompose Novel into Known: Part Concept Learning For 3D Novel Class Discovery

Propagating Knowledge Updates to LMs Through Distillation

Undirected Probabilistic Model for Tensor Decomposition

Lookup Table meets Local Laplacian Filter: Pyramid Reconstruction Network for Tone Mapping

GLOBER: Coherent Non-autoregressive Video Generation via GLOBal Guided Video DecodER

Pengi: An Audio Language Model for Audio Tasks

Multi-task learning with summary statistics

Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset

AVOIDDS: Aircraft Vision-based Intruder Detection Dataset and Simulator

Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization

GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning

Fast Model DeBias with Machine Unlearning

HyTrel: Hypergraph-enhanced Tabular Data Representation Learning

Intriguing Properties of Quantization at Scale

Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training

A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning

Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning

HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception

Learning to Reason and Memorize with Self-Notes

Can Language Models Solve Graph Problems in Natural Language?

Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data

Norm-based Generalization Bounds for Sparse Neural Networks

Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning

Multi-Fidelity Multi-Armed Bandits Revisited

Knowledge-based in silico models and dataset for the comparative evaluation of mammography AI for a range of breast characteristics, lesion conspicuities and doses

Inner Product-based Neural Network Similarity

HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding

Learning to Configure Separators in Branch-and-Cut

On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms

Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective

Language-based Action Concept Spaces Improve Video Self-Supervised Learning

Zero-shot causal learning

Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources

MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition

Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias

Variational Annealing on Graphs for Combinatorial Optimization

Streaming Factor Trajectory Learning for Temporal Tensor Decomposition

Multimodal Clinical Benchmark for Emergency Care (MC-BEC): A Comprehensive Benchmark for Evaluating Foundation Models in Emergency Medicine

Egocentric Planning for Scalable Embodied Task Achievement

Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests

Feature Learning for Interpretable, Performant Decision Trees

HOH: Markerless Multimodal Human-Object-Human Handover Dataset with Large Object Count

Expressive probabilistic sampling in recurrent neural networks

Functional Renyi Differential Privacy for Generative Modeling

Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization

Bayesian Risk-Averse Q-Learning with Streaming Observations

Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge Ensembles

Error Discovery By Clustering Influence Embeddings

[Re] Bandit Theory and Thompson Sampling-guided Directed Evolution for Sequence Optimization

Energy-based learning algorithms for analog computing: a comparative study

Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards

Nominality Score Conditioned Time Series Anomaly Detection by Point/Sequential Reconstruction

Coupled Reconstruction of Cortical Surfaces by Diffeomorphic Mesh Deformation

Active Observing in Continuous-time Control

Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy

A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning

Neural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysis

Feature-Learning Networks Are Consistent Across Widths At Realistic Scales

Retrieval-Augmented Multiple Instance Learning

Approximation-Generalization Trade-offs under (Approximate) Group Equivariance

Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity

Faster Differentially Private Convex Optimization via Second-Order Methods

UNSSOR: Unsupervised Neural Speech Separation by Leveraging Over-determined Training Mixtures

Principled Weight Initialisation for Input-Convex Neural Networks

Interpretable Graph Networks Formulate Universal Algebra Conjectures

Distributionally Robust Skeleton Learning of Discrete Bayesian Networks

How do Minimum-Norm Shallow Denoisers Look in Function Space?

DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection

QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution

Change point detection and inference in multivariate non-parametric models under mixing conditions

Perceptual adjustment queries and an inverted measurement paradigm for low-rank metric learning

Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies

Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation

The Graph Pencil Method: Mapping Subgraph Densities to Stochastic Block Models

A Single-Loop Accelerated Extra-Gradient Difference Algorithm with Improved Complexity Bounds for Constrained Minimax Optimization

Does Invariant Graph Learning via Environment Augmentation Learn Invariance?

SceneScape: Text-Driven Consistent Scene Generation

No Change, No Gain: Empowering Graph Neural Networks with Expected Model Change Maximization for Active Learning

A polar prediction model for learning to represent visual transformations

The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning

Thin and deep Gaussian processes

Bandit Social Learning under Myopic Behavior

Constant Approximation for Individual Preference Stable Clustering

Improved Frequency Estimation Algorithms with and without Predictions

A Fractional Graph Laplacian Approach to Oversmoothing

The Simplicity Bias in Multi-Task RNNs: Shared Attractors, Reuse of Dynamics, and Geometric Representation

LOVM: Language-Only Vision Model Selection

Learning Linear Causal Representations from Interventions under General Nonlinear Mixing

High-Fidelity Audio Compression with Improved RVQGAN

LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas

Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs

DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining

Beyond Invariance: Test-Time Label-Shift Adaptation for Addressing "Spurious" Correlations

Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?

SPACE: Single-round Participant Amalgamation for Contribution Evaluation in Federated Learning

DropCompute: simple and more robust distributed synchronous training via compute variance reduction

Mnemosyne: Learning to Train Transformers with Transformers

Estimating Propensity for Causality-based Recommendation without Exposure Data

On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective

Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding

First Order Stochastic Optimization with Oblivious Noise

Combating Representation Learning Disparity with Geometric Harmonization

Parameterizing Non-Parametric Meta-Reinforcement Learning Tasks via Subtask Decomposition

KD-Zero: Evolving Knowledge Distiller for Any Teacher-Student Pairs

[Re] End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking

Conservative State Value Estimation for Offline Reinforcement Learning

[Re] $\mathcal{G}$-Mixup: Graph Data Augmentation for Graph Classification

Benchmarking Large Language Models on CMExam - A comprehensive Chinese Medical Exam Dataset

CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graphs

On the Implicit Bias of Linear Equivariant Steerable Networks

Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals

Posterior Contraction Rates for Matérn Gaussian Processes on Riemannian Manifolds

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting

Sequential Predictive Two-Sample and Independence Testing

Distributionally Robust Linear Quadratic Control

Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces

Face Reconstruction from Facial Templates by Learning Latent Space of a Generator Network

Neural Modulation for Flash Memory: An Unsupervised Learning Framework for Improved Reliability

VPGTrans: Transfer Visual Prompt Generator across LLMs

A Unified Framework for Rank-based Loss Minimization

Model Spider: Learning to Rank Pre-Trained Models Efficiently

REASONER: An Explainable Recommendation Dataset with Comprehensive Labeling Ground Truths

Label-efficient Segmentation via Affinity Propagation

A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking

Benchmarking Encoder-Decoder Architectures for Biplanar X-ray to 3D Bone Shape Reconstruction

Does Graph Distillation See Like Vision Dataset Counterpart?

An Information-Theoretic Evaluation of Generative Models in Learning Multi-modal Distributions

[Re] On the Reproducibility of CartoonX

[Re] Fairness Guarantees under Demographic Shift

EPIC Fields: Marrying 3D Geometry and Video Understanding

ClimateSet: A Large-Scale Climate Model Dataset for Machine Learning

Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition

The Drunkard’s Odometry: Estimating Camera Motion in Deforming Scenes

LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models

Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images

VisIT-Bench: A Dynamic Benchmark for Evaluating Instruction-Following Vision-and-Language Models

InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback

BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset

LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting

Mr. HiSum: A Large-scale Dataset for Video Highlight Detection and Summarization

PIXIU: A Comprehensive Benchmark, Instruction Dataset and Large Language Model for Finance

Efficient Potential-based Exploration in Reinforcement Learning using Inverse Dynamic Bisimulation Metric

No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions

Gaussian Partial Information Decomposition: Bias Correction and Application to High-dimensional Data

Exploring the Optimal Choice for Generative Processes in Diffusion Models: Ordinary vs Stochastic Differential Equations

Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions

Foundation Model is Efficient Multimodal Multitask Model Selector

The Quantization Model of Neural Scaling

Learning to Receive Help: Intervention-Aware Concept Embedding Models

Adaptive Selective Sampling for Online Prediction with Experts

Multi-Modal Inverse Constrained Reinforcement Learning from a Mixture of Demonstrations

Recovering Simultaneously Structured Data via Non-Convex Iteratively Reweighted Least Squares

Composing Parameter-Efficient Modules with Arithmetic Operation

Globally injective and bijective neural operators

Tempo Adaptation in Non-stationary Reinforcement Learning

Unsupervised Optical Flow Estimation with Dynamic Timing Representation for Spike Camera

3D Indoor Instance Segmentation in an Open-World

Self-Supervised Learning of Representations for Space Generates Multi-Modular Grid Cells

Diffusion Representation for Asymmetric Kernels via Magnetic Transform

Learning to Discover Skills through Guidance

ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking

Invariant Anomaly Detection under Distribution Shifts: A Causal Perspective

Decision Tree for Locally Private Estimation with Public Data

Toward Better PAC-Bayes Bounds for Uniformly Stable Algorithms

C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder

BCDiff: Bidirectional Consistent Diffusion for Instantaneous Trajectory Prediction

Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment

GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization

A Unified Approach to Count-Based Weakly Supervised Learning

Deep Non-line-of-sight Imaging from Under-scanning Measurements

On Slicing Optimality for Mutual Information

On the Generalization Error of Stochastic Mirror Descent for Quadratically-Bounded Losses: an Improved Analysis

Multi-Step Generalized Policy Improvement by Leveraging Approximate Models

Trading-off price for data quality to achieve fair online allocation

Trial matching: capturing variability with data-constrained spiking neural networks

Learning Visual Prior via Generative Pre-Training

H-nobs: Achieving Certified Fairness and Robustness in Distributed Learning on Heterogeneous Datasets

To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning

EICIL: Joint Excitatory Inhibitory Cycle Iteration Learning for Deep Spiking Neural Networks

Achieving $\mathcal{O}(\epsilon^{-1.5})$ Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization

ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab

When Do Neural Nets Outperform Boosted Trees on Tabular Data?

An Optimal and Scalable Matrix Mechanism for Noisy Marginals under Convex Loss Functions

GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection

Strategyproof Voting under Correlated Beliefs

RangePerception: Taming LiDAR Range View for Efficient and Accurate 3D Object Detection

NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videos

Creating a Public Repository for Joining Private Data

Near Optimal Reconstruction of Spherical Harmonic Expansions

Path following algorithms for $\ell_2$-regularized $M$-estimation with approximation guarantee

Boosting Verification of Deep Reinforcement Learning via Piece-Wise Linear Decision Neural Networks

Minimum-Risk Recalibration of Classifiers

InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding

Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits

AND: Adversarial Neural Degradation for Learning Blind Image Super-Resolution

Accelerated Quasi-Newton Proximal Extragradient: Faster Rate for Smooth Convex Optimization

Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards

Canonical normalizing flows for manifold learning

The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks

Masked Two-channel Decoupling Framework for Incomplete Multi-view Weak Multi-label Learning

Universality and Limitations of Prompt Tuning

Aiming towards the minimizers: fast convergence of SGD for overparametrized problems

(Amplified) Banded Matrix Factorization: A unified approach to private training

Fast and Simple Spectral Clustering in Theory and Practice

(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy

BioMassters: A Benchmark Dataset for Forest Biomass Estimation using Multi-modal Satellite Time-series

Learning to Compress Prompts with Gist Tokens

A unified framework for information-theoretic generalization bounds

Robust low-rank training via approximate orthonormal constraints

Joint Training of Deep Ensembles Fails Due to Learner Collusion

On the choice of Perception Loss Function for Learned Video Compression

GenS: Generalizable Neural Surface Reconstruction from Multi-View Images

Social Motion Prediction with Cognitive Hierarchies

Self-supervised Graph Neural Networks via Low-Rank Decomposition

Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization

Spectral Co-Distillation for Personalized Federated Learning

Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation

Adversarial Self-Training Improves Robustness and Generalization for Gradual Domain Adaptation

CLIP4HOI: Towards Adapting CLIP for Practical Zero-Shot HOI Detection

Particle-based Variational Inference with Generalized Wasserstein Gradient Flow

Mask Propagation for Efficient Video Semantic Segmentation

UE4-NeRF:Neural Radiance Field for Real-Time Rendering of Large-Scale Scene

Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priors

Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration

ELDEN: Exploration via Local Dependencies

Im-Promptu: In-Context Composition from Image Prompts

Adaptive Data Analysis in a Balanced Adversarial Model

Turbulence in Focus: Benchmarking Scaling Behavior of 3D Volumetric Super-Resolution with BLASTNet 2.0 Data

Learning Rate Free Bayesian Inference in Constrained Domains

InfoCD: A Contrastive Chamfer Distance Loss for Point Cloud Completion

Towards Automated Circuit Discovery for Mechanistic Interpretability

Connecting Certified and Adversarial Training

CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography

A General Framework for Equivariant Neural Networks on Reductive Lie Groups

DISCOVER: Making Vision Networks Interpretable via Competition and Dissection

Probabilistic Exponential Integrators

How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budget

AbDiffuser: full-atom generation of in-vitro functioning antibodies

Energy Discrepancies: A Score-Independent Loss for Energy-Based Models

Learning from Both Structural and Textual Knowledge for Inductive Knowledge Graph Completion

Unsupervised Behavior Extraction via Random Intent Priors

Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels

SyncTREE: Fast Timing Analysis for Integrated Circuit Design through a Physics-informed Tree-based Graph Neural Network

Activity Grammars for Temporal Action Segmentation

Differentially Private Statistical Inference through $\beta$-Divergence One Posterior Sampling

LICO: Explainable Models with Language-Image COnsistency

AdaVAE: Bayesian Structural Adaptation for Variational Autoencoders

Scaling Open-Vocabulary Object Detection

xTrimoGene: An Efficient and Scalable Representation Learner for Single-Cell RNA-Seq Data

High-dimensional Asymptotics of Denoising Autoencoders

Combinatorial Group Testing with Selfish Agents

FouriDown: Factoring Down-Sampling into Shuffling and Superposing

Finite Population Regression Adjustment and Non-asymptotic Guarantees for Treatment Effect Estimation

Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots

End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics

Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning

Differentiable and Stable Long-Range Tracking of Multiple Posterior Modes

Learning Sample Difficulty from Pre-trained Models for Reliable Prediction

Recovering from Out-of-sample States via Inverse Dynamics in Offline Reinforcement Learning

Smooth, exact rotational symmetrization for deep learning on point clouds

Quantifying the Cost of Learning in Queueing Systems

Conformalized matrix completion

Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation

Approximate Allocation Matching for Structural Causal Bandits with Unobserved Confounders

Embracing the chaos: analysis and diagnosis of numerical instability in variational flows

Weakly Supervised 3D Open-vocabulary Segmentation

MCUFormer: Deploying Vision Tranformers on Microcontrollers with Limited Memory

Estimating Causal Effects Identifiable from a Combination of Observations and Experiments

Aligning Language Models with Human Preferences via a Bayesian Approach

Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger

Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations

A Logic for Expressing Log-Precision Transformers

Trust Your $\nabla$: Gradient-based Intervention Targeting for Causal Discovery

Online robust non-stationary estimation

Towards Test-Time Refusals via Concept Negation

A Spectral Theory of Neural Prediction and Alignment

Adaptive Normalization for Non-stationary Time Series Forecasting: A Temporal Slice Perspective

PAC Learning Linear Thresholds from Label Proportions

Efficient Batched Algorithm for Contextual Linear Bandits with Large Action Space via Soft Elimination

Sharp Spectral Rates for Koopman Operator Learning

Transportability for Bandits with Data from Different Environments

Adaptive Contextual Perception: How To Generalize To New Backgrounds and Ambiguous Objects

Physics-Driven ML-Based Modelling for Correcting Inverse Estimation

Nearest Neighbour with Bandit Feedback

Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions

Alternating Updates for Efficient Transformers

Equivariant flow matching

DSR: Dynamical Surface Representation as Implicit Neural Networks for Protein

MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues

H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection

Mechanic: A Learning Rate Tuner

Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusion

SwapPrompt: Test-Time Prompt Adaptation for Vision-Language Models

Transformers learn through gradual rank increase

PDP: Parameter-free Differentiable Pruning is All You Need

Joint Feature and Differentiable $ k $-NN Graph Learning using Dirichlet Energy

Non-adversarial training of Neural SDEs with signature kernel scores

AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset

GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction

Joint Prompt Optimization of Stacked LLMs using Variational Inference

CLIP-OGD: An Experimental Design for Adaptive Neyman Allocation in Sequential Experiments

Lower Bounds on Adaptive Sensing for Matrix Recovery

Block Broyden's Methods for Solving Nonlinear Equations

CluB: Cluster Meets BEV for LiDAR-Based 3D Object Detection

Fractal Landscapes in Policy Optimization

H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation

SQ Lower Bounds for Non-Gaussian Component Analysis with Weaker Assumptions

Stable Vectorization of Multiparameter Persistent Homology using Signed Barcodes as Measures

Learning Modulated Transformation in GANs

Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand

FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning

Directional diffusion models for graph representation learning

TaskMet: Task-driven Metric Learning for Model Learning

DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation

From ViT Features to Training-free Video Object Segmentation via Streaming-data Mixture Models

Bandit Task Assignment with Unknown Processing Time

Learning Reliable Logical Rules with SATNet

Saddle-to-Saddle Dynamics in Diagonal Linear Networks

Identifiability Guarantees for Causal Disentanglement from Soft Interventions

Oracle Complexity of Single-Loop Switching Subgradient Methods for Non-Smooth Weakly Convex Functional Constrained Optimization

Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models

PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning

Fantastic Robustness Measures: The Secrets of Robust Generalization

Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification

A Guide Through the Zoo of Biased SGD

Online learning of long-range dependencies

Back-Modality: Leveraging Modal Transformation for Data Augmentation

Data Quality in Imitation Learning

High dimensional, tabular deep learning with an auxiliary knowledge graph

Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

Unified Segment-to-Segment Framework for Simultaneous Sequence Generation

Integration-free Training for Spatio-temporal Multimodal Covariate Deep Kernel Point Processes

Entropy-based Training Methods for Scalable Neural Implicit Samplers

Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks

Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality

TabMT: Generating tabular data with masked transformers

Tuning Multi-mode Token-level Prompt Alignment across Modalities

Sampling weights of deep neural networks

ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning

Robust Bayesian Satisficing

Learning Causal Models under Independent Changes

Mechanism Design for Collaborative Normal Mean Estimation

Connecting Multi-modal Contrastive Representations

The Contextual Lasso: Sparse Linear Models via Deep Neural Networks

Self-Consistent Velocity Matching of Probability Flows

Pointwise uncertainty quantification for sparse variational Gaussian process regression with a Brownian motion prior

Information Maximization Perspective of Orthogonal Matching Pursuit with Applications to Explainable AI

Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning

On Differentially Private Sampling from Gaussian and Product Distributions

MMGP: a Mesh Morphing Gaussian Process-based machine learning method for regression of physical problems under nonparametrized geometrical variability

Is Learning in Games Good for the Learners?

Fairness-guided Few-shot Prompting for Large Language Models

A Hierarchical Training Paradigm for Antibody Structure-sequence Co-design

Generative Neural Fields by Mixtures of Neural Implicit Functions

How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception

Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization

A Unified Model and Dimension for Interactive Estimation

Convergence Analysis of Sequential Federated Learning on Heterogeneous Data

Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence

Asymptotically Optimal Quantile Pure Exploration for Infinite-Armed Bandits

Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete

Efficient Low-rank Backpropagation for Vision Transformer Adaptation

SUBP: Soft Uniform Block Pruning for 1$\times$N Sparse CNNs Multithreading Acceleration

Kernel Quadrature with Randomly Pivoted Cholesky

Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents

Offline Reinforcement Learning with Differential Privacy

Topological Parallax: A Geometric Specification for Deep Perception Models

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning

Optimal Exploration for Model-Based RL in Nonlinear Systems

Kissing to Find a Match: Efficient Low-Rank Permutation Representation

Enhancing Motion Deblurring in High-Speed Scenes with Spike Streams

Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking

Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents

Doubly-Robust Self-Training

Projection-Free Online Convex Optimization via Efficient Newton Iterations

On Certified Generalization in Structured Prediction

Partial Matrix Completion

Conformal Prediction for Time Series with Modern Hopfield Networks

Triple Eagle: Simple, Fast and Practical Budget-Feasible Mechanisms

Diffusion-Based Probabilistic Uncertainty Estimation for Active Domain Adaptation

Formulating Discrete Probability Flow Through Optimal Transport

Goal-Conditioned Predictive Coding for Offline Reinforcement Learning

PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoising

HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text

STXD: Structural and Temporal Cross-Modal Distillation for Multi-View 3D Object Detection

Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation

Conservative Offline Policy Adaptation in Multi-Agent Games

A Smooth Binary Mechanism for Efficient Private Continual Observation

A Theory of Unsupervised Translation Motivated by Understanding Animal Communication

Type-to-Track: Retrieve Any Object via Prompt-based Tracking

A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks

CoDet: Co-occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection

Fair, Polylog-Approximate Low-Cost Hierarchical Clustering

BayesTune: Bayesian Sparse Deep Model Fine-tuning

Replicable Reinforcement Learning

A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning

Logarithmic Bayes Regret Bounds

Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent

Adaptive Principal Component Regression with Applications to Panel Data

Strategic Apple Tasting

Multinomial Logistic Regression: Asymptotic Normality on Null Covariates in High-Dimensions

AI for Interpretable Chemistry: Predicting Radical Mechanistic Pathways via Contrastive Learning

NPCL: Neural Processes for Uncertainty-Aware Continual Learning

Federated Learning with Manifold Regularization and Normalized Update Reaggregation

AutoGO: Automated Computation Graph Optimization for Neural Network Evolution

First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities

Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Models

Reference-Based POMDPs

Full-Atom Protein Pocket Design via Iterative Refinement

Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training

Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency

Batch Bayesian Optimization For Replicable Experimental Design

Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective

Metis: Understanding and Enhancing In-Network Regular Expressions

Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First

A Causal Framework for Decomposing Spurious Variations

ReDS: Offline RL With Heteroskedastic Datasets via Support Constraints

Generalized Weighted Path Consistency for Mastering Atari Games

Learning Large-scale Neural Fields via Context Pruned Meta-Learning

QuadAttac$K$: A Quadratic Programming Approach to Learning Ordered Top-$K$ Adversarial Attacks

Balanced Training for Sparse GANs

Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability

Distributionally Robust Bayesian Optimization with $\varphi$-divergences

The expressive power of pooling in Graph Neural Networks

Eliminating Domain Bias for Federated Learning in Representation Space

How many samples are needed to leverage smoothness?

Unconstrained Dynamic Regret via Sparse Coding

Counting Distinct Elements Under Person-Level Differential Privacy

Prioritizing Samples in Reinforcement Learning with Reducible Loss

Robust Concept Erasure via Kernelized Rate-Distortion Maximization

Learning Invariant Representations of Graph Neural Networks via Cluster Generalization

Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior

Explore In-Context Learning for 3D Point Cloud Understanding

Statistical Insights into HSIC in High Dimensions

TexQ: Zero-shot Network Quantization with Texture Feature Distribution Calibration

Preconditioning Matters: Fast Global Convergence of Non-convex Matrix Factorization via Scaled Gradient Descent

Locality Sensitive Hashing in Fourier Frequency Domain For Soft Set Containment Search

Towards Combinatorial Generalization for Catalysts: A Kohn-Sham Charge-Density Approach

Robust and Actively Secure Serverless Collaborative Learning

Phase diagram of early training dynamics in deep neural networks: effect of the learning rate, depth, and width

Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off

On skip connections and normalisation layers in deep optimisation

Offline RL with Discrete Proxy Representations for Generalizability in POMDPs

Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples

PointGPT: Auto-regressively Generative Pre-training from Point Clouds

ProteinInvBench: Benchmarking Protein Inverse Folding on Diverse Tasks, Models, and Metrics

EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models

Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts

Detecting hidden confounding in observational data using multiple environments

$\varepsilon$-fractional core stability in Hedonic Games.

Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions

Debiasing Pretrained Generative Models by Uniformly Sampling Semantic Attributes

Weakly Coupled Deep Q-Networks

SoundCam: A Dataset for Finding Humans Using Room Acoustics

On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective

Bifurcations and loss jumps in RNN training

A Recurrent Neural Circuit Mechanism of Temporal-scaling Equivariant Representation

Uncovering Meanings of Embeddings via Partial Orthogonality

PyNeRF: Pyramidal Neural Radiance Fields

Truly Scale-Equivariant Deep Nets with Fourier Layers

Combating Bilateral Edge Noise for Robust Link Prediction

Chatting Makes Perfect: Chat-based Image Retrieval

Multi-Object Representation Learning via Feature Connectivity and Object-Centric Regularization

An Efficient Doubly-Robust Test for the Kernel Treatment Effect

Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research

RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

iSCAN: Identifying Causal Mechanism Shifts among Nonlinear Additive Noise Models

FIND: A Function Description Benchmark for Evaluating Interpretability Methods

Learning to Taste: A Multimodal Wine Dataset

Guiding The Last Layer in Federated Learning with Pre-Trained Models

ALGO: Synthesizing Algorithmic Programs with Generated Oracle Verifiers

Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairness

Single-Pass Pivot Algorithm for Correlation Clustering. Keep it simple!

SPA: A Graph Spectral Alignment Perspective for Domain Adaptation

Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing

Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing

Neural Frailty Machine: Beyond proportional hazard assumption in neural survival regressions

IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL

Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data

ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation

Practical Differentially Private Hyperparameter Tuning with Subsampling

Optimizing over trained GNNs via symmetry breaking

A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes

$\mathcal{M}^4$: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities and Models

Benchmark of Machine Learning Force Fields for Semiconductor Simulations: Datasets, Metrics, and Comparative Analysis

Contextual Stochastic Bilevel Optimization

Segment Anything in 3D with NeRFs

Closing the Computational-Statistical Gap in Best Arm Identification for Combinatorial Semi-bandits

Learning Exponential Families from Truncated Samples

Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attacks

Is Distance Matrix Enough for Geometric Deep Learning?

Beyond Myopia: Learning from Positive and Unlabeled Data through Holistic Predictive Trends

Cross-modal Active Complementary Learning with Self-refining Correspondence

Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman

Causal Effect Regularization: Automated Detection and Removal of Spurious Correlations

Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching

Locality-Aware Generalizable Implicit Neural Representation

Augmentation-Aware Self-Supervision for Data-Efficient GAN Training

VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens

Learning non-Markovian Decision-Making from State-only Sequences

Collaborative Alignment of NLP Models

Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents

Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks

GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels

ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding

Online Ad Allocation with Predictions

Greatness in Simplicity: Unified Self-Cycle Consistency for Parser-Free Virtual Try-On

Symbolic Discovery of Optimization Algorithms

Most Neural Networks Are Almost Learnable

GALOPA: Graph Transport Learning with Optimal Plan Alignment

Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning

On Private and Robust Bandits

Multi-scale Diffusion Denoised Smoothing

On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributions

Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards

Inverse Reinforcement Learning with the Average Reward Criterion

Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms

TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graph

Temporal Causal Mediation through a Point Process: Direct and Indirect Effects of Healthcare Interventions

Function Space Bayesian Pseudocoreset for Bayesian Neural Networks

Moment Matching Denoising Gibbs Sampling

D4Explainer: In-distribution Explanations of Graph Neural Network via Discrete Denoising Diffusion

Optimality of Message-Passing Architectures for Sparse Graphs

Markovian Sliced Wasserstein Distances: Beyond Independent Projections

Energy-Based Sliced Wasserstein Distance

StoryBench: A Multifaceted Benchmark for Continuous Story Visualization

Video Prediction Models as Rewards for Reinforcement Learning

Simplicity Bias in 1-Hidden Layer Neural Networks

Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis

The Exact Sample Complexity Gain from Invariances for Kernel Regression

SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization

Regression with Cost-based Rejection

On the Importance of Feature Separability in Predicting Out-Of-Distribution Error

The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks

$\texttt{TACO}$: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning

CORL: Research-oriented Deep Offline Reinforcement Learning Library

Unpaired Multi-Domain Causal Representation Learning

Does Visual Pretraining Help End-to-End Reasoning?

Scattering Vision Transformer: Spectral Mixing Matters

PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection

How hard are computer vision datasets? Calibrating dataset difficulty to viewing time

A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing

EvoFed: Leveraging Evolutionary Strategies for Communication-Efficient Federated Learning

Train 'n Trade: Foundations of Parameter Markets

Real3D-AD: A Dataset of Point Cloud Anomaly Detection

Gradient-Free Kernel Stein Discrepancy

Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Model

The noise level in linear regression with dependent data

Federated Spectral Clustering via Secure Similarity Reconstruction

Learning and Collusion in Multi-unit Auctions

Meek Separators and Their Applications in Targeted Causal Discovery

The Learnability of In-Context Learning

Reproducibility Study of "Label-Free Explainability for Unsupervised Models"

Bridging RL Theory and Practice with the Effective Horizon

What functions can Graph Neural Networks compute on random graphs? The role of Positional Encoding

On the Overlooked Structure of Stochastic Gradients

CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion

Entropy-dissipation Informed Neural Network for McKean-Vlasov Type PDEs

Non-stationary Experimental Design under Linear Trends

Meta-learning families of plasticity rules in recurrent spiking networks using simulation-based inference

Unbounded Differentially Private Quantile and Maximum Estimation

Sub-optimality of the Naive Mean Field approximation for proportional high-dimensional Linear Regression

Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels

Sheaf Hypergraph Networks

Theoretical Analysis of the Inductive Biases in Deep Convolutional Networks

Improving the Knowledge Gradient Algorithm

Noise-Adaptive Thompson Sampling for Linear Contextual Bandits

Subspace Identification for Multi-Source Domain Adaptation

Sparse Deep Learning for Time Series Data: Theory and Applications

VeriX: Towards Verified Explainability of Deep Neural Networks

Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder

Transfer Learning with Affine Model Transformation

Uni3DETR: Unified 3D Detection Transformer

Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach

Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals

A Finite-Particle Convergence Rate for Stein Variational Gradient Descent

Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations

AQuA: A Benchmarking Tool for Label Quality Assessment

VisAlign: Dataset for Measuring the Alignment between AI and Humans in Visual Perception

Species196: A One-Million Semi-supervised Dataset for Fine-grained Species Recognition

YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus

Consensus and Subjectivity of Skin Tone Annotation for ML Fairness

Scalable 3D Captioning with Pretrained Models

SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model

MedSat: A Public Health Dataset for England Featuring Medical Prescriptions and Satellite Imagery