International Conference on Machine Learning (ICML) - 2023

Conference Proceedings:

Key: PC - Pseudocode, OSC - Open Source Code, OSD - Open Datasets, DS - Dataset Splits, HS - Hardware Specification, SD - Software Dependencies, ES - Experiment Setup

"Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts 5
$H$-Consistency Bounds for Pairwise Misranking Loss Surrogates 2
$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation 5
2D-Shapley: A Framework for Fragmented Data Valuation 5
A Category-theoretical Meta-analysis of Definitions of Disentanglement 0
A Closer Look at Few-shot Classification Again 4
A Closer Look at Self-Supervised Lightweight Vision Transformers 5
A Closer Look at the Intervention Procedure of Concept Bottleneck Models 6
A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests 5
A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imaging 5
A Connection between One-Step RL and Critic Regularization in Reinforcement Learning 3
A Coupled Flow Approach to Imitation Learning 4
A Critical Revisit of Adversarial Robustness in 3D Point Cloud Recognition with Diffusion-Driven Purification 4
A Critical View of Vision-Based Long-Term Dynamics Prediction Under Environment Misalignment 5
A Deep Conjugate Direction Method for Iteratively Solving Linear Systems 5
A Distribution Optimization Framework for Confidence Bounds of Risk Measures 3
A Fast Optimistic Method for Monotone Variational Inequalities 4
A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel 3
A Flexible Diffusion Model 3
A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit Feedback 3
A Fully First-Order Method for Stochastic Bilevel Optimization 4
A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems 5
A General Representation Learning Framework with Generalization Performance Guarantees 6
A Generalization of ViT/MLP-Mixer to Graphs 5
A Gromov-Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening 6
A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining 5
A Hybrid Quantum-Classical Approach based on the Hadamard Transform for the Convolutional Layer 5
A Kernel Stein Test of Goodness of Fit for Sequential Models 3
A Kernel-Based View of Language Model Fine-Tuning 4
A Kernelized Stein Discrepancy for Biological Sequences 3
A Large-Scale Study of Probabilistic Calibration in Neural Network Regression 5
A Law of Robustness beyond Isoperimetry 0
A Mathematical Model for Curriculum Learning for Parities 2
A Model-Based Method for Minimizing CVaR and Beyond 3
A Model-free Closeness-of-influence Test for Features in Supervised Learning 3
A Modern Look at the Relationship between Sharpness and Generalization 4
A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints 3
A Nearly-Optimal Bound for Fast Regression with $\ell_∞$ Guarantee 0
A Neural PDE Solver with Temporal Stencil Modeling 3
A New PHO-rmula for Improved Performance of Semi-Structured Networks 5
A Picture of the Space of Typical Learnable Tasks 3
A Reinforcement Learning Framework for Dynamic Mediation Analysis 4
A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks 7
A Robust Test for the Stationarity Assumption in Sequential Decision Making 4
A Scalable Frank-Wolfe-Based Algorithm for the Max-Cut SDP 5
A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models 5
A Statistical Perspective on Retrieval-Based Models 3
A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs 4
A Study on Transformer Configuration and Training Objective 4
A Theoretical Analysis of the Learning Dynamics under Class Imbalance 6
A Three-regime Model of Network Pruning 5
A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations 3
A Two-Stage Active Learning Algorithm for k-Nearest Neighbors 1
A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition 4
A Unified Optimization Framework of ANN-SNN Conversion: Towards Optimal Mapping from Activation Values to Firing Rates 5
A Unifying Framework to the Analysis of Interaction Methods using Synergy Functions 0
A Universal Unbiased Method for Classification from Aggregate Observations 4
A Watermark for Large Language Models 4
A new near-linear time algorithm for k-nearest neighbor search using a compressed cover tree 1
A theory of continuous generative flow networks 4
A theory of representation learning gives a deep generalisation of kernel methods 3
A/B Testing in Network Data with Covariate-Adaptive Randomization 4
ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging 6
AbODE: Ab initio antibody design using conjoined ODEs 3
Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization 1
Abstracting Imperfect Information Away from Two-Player Zero-Sum Games 1
Accelerated Cyclic Coordinate Dual Averaging with Extrapolation for Composite Convex Optimization 4
Accelerated Infeasibility Detection of Constrained Optimization and Fixed-Point Iterations 2
Accelerated Primal-Dual Methods for Convex-Strongly-Concave Saddle Point Problems 3
Accelerated Stochastic Optimization Methods under Quasar-convexity 4
Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Time 4
Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations 3
Achieving Hierarchy-Free Approximation for Bilevel Programs with Equilibrium Constraints 4
Achieving High Accuracy with PINNs via Energy Natural Gradient Descent 4
Achieving Linear Speedup in Non-IID Federated Bilevel Learning 4
Action Matching: Learning Stochastic Dynamics from Samples 4
Active Learning based Structural Inference 6
Active Policy Improvement from Multiple Black-box Oracles 4
Active Ranking of Experts Based on their Performances in Many Tasks 2
Active causal structure learning with advice 4
Actor-Critic Alignment for Offline-to-Online Reinforcement Learning 4
AdaBoost is not an Optimal Weak to Strong Learner 1
AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation 5
AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners 3
Adapting to game trees in zero-sum imperfect information games 4
Adaptive Annealed Importance Sampling with Constant Rate Progress 4
Adaptive Barrier Smoothing for First-Order Policy Gradient with Contact Dynamics 2
Adaptive Compositional Continual Meta-Learning 6
Adaptive Computation with Elastic Input Sequence 6
Adaptive Coordination in Social Embodied Rearrangement 5
Adaptive Estimation of Graphical Models under Total Positivity 3
Adaptive IMLE for Few-shot Pretraining-free Generative Modelling 5
Adaptive Identification of Populations with Treatment Benefit in Clinical Trials: Machine Learning Challenges and Solutions 2
Adaptive Smoothing Gradient Learning for Spiking Neural Networks 5
Adaptive Whitening in Neural Populations with Gain-modulating Interneurons 4
Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift 5
Additive Causal Bandits with Unknown Graph 3
Addressing Budget Allocation and Revenue Allocation in Data Market Environments Using an Adaptive Sampling Algorithm 5
Adversarial Cheap Talk 5
Adversarial Collaborative Learning on Non-IID Features 4
Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples 5
Adversarial Learning of Distributional Reinforcement Learning 2
Adversarial Parameter Attack on Deep Neural Networks 5
Adversarial Policies Beat Superhuman Go AIs 4
Adversarial robustness of amortized Bayesian inference 5
Adversarially Robust PAC Learnability of Real-Valued Functions 1
Algorithmic Collective Action in Machine Learning 2
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions 0
Algorithms for bounding contribution for histogram estimation under user-level privacy 3
Aligning Language Models with Preferences through $f$-divergence Minimization 4
All in a Row: Compressed Convolution Networks for Graphs 6
Alternately Optimized Graph Neural Networks 6
Alternating Local Enumeration (TnALE): Solving Tensor Network Structure Search with Fewer Evaluations 5
An Adaptive Entropy-Regularization Framework for Multi-Agent Reinforcement Learning 5
An Effective Meaningful Way to Evaluate Survival Models 4
An Information-Theoretic Analysis of Nonstationary Bandit Learning 1
An Instrumental Variable Approach to Confounded Off-Policy Evaluation 2
An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning 3
An SDE for Modeling SAM: Theory and Insights 2
Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression: Fast Convergence and Partial Participation 4
Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels 2
Analyzing Diffusion as Serial Reproduction 4
Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano 3
Anchor Sampling for Federated Learning with Partial Client Participation 6
Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization 6
Anti-Exploration by Random Network Distillation 5
Applied Online Algorithms with Heterogeneous Predictors 4
Approximate Causal Effect Identification under Weak Confounding 1
Approximate Stein Classes for Truncated Density Estimation 3
Approximately Optimal Core Shapes for Tensor Decompositions 5
Approximation Algorithms for Fair Range Clustering 1
Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input 1
Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN 5
Are Diffusion Models Vulnerable to Membership Inference Attacks? 4
Are Equivariant Equilibrium Approximators Beneficial? 2
Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation 4
Are Large Kernels Better Teachers than Transformers for ConvNets? 5
Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations 2
Are Random Decompositions all we need in High Dimensional Bayesian Optimisation? 5
Are labels informative in semi-supervised learning? Estimating and leveraging the missing-data mechanism. 3
Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models 5
Atari-5: Distilling the Arcade Learning Environment down to Five Games 6
Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observability 5
Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise 1
Attributing Image Generative Models using Latent Fingerprints 4
AudioLDM: Text-to-Audio Generation with Latent Diffusion Models 4
Auto-Differentiation of Relational Computations for Very Large Scale Machine Learning 7
AutoCoreset: An Automatic Practical Coreset Construction Framework 5
Automated Search for Conjectures on Mathematical Constants using Analysis of Integer Sequences 2
Automatic Data Augmentation via Invariance-Constrained Learning 5
Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning 5
Automatically Auditing Large Language Models via Discrete Optimization 5
Automatically marginalized MCMC in probabilistic programming 4
Autoregressive Diffusion Model for Graph Generation 4
Auxiliary Learning as an Asymmetric Bargaining Game 5
Auxiliary Modality Learning with Generalized Curriculum Distillation 5
Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity 3
B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding 6
BEATs: Audio Pre-Training with Acoustic Tokenizers 5
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models 5
BNN-DP: Robustness Certification of Bayesian Neural Networks via Dynamic Programming 4
BPipe: Memory-Balanced Pipeline Parallelism for Training Large Language Models 4
Bag of Tricks for Training Data Extraction from Language Models 5
Bandit Multi-linear DR-Submodular Maximization and Its Applications on Adversarial Submodular Bandits 1
Bandit Online Linear Optimization with Hints and Queries 2
Bandits with Knapsacks: Advice on Time-Varying Demands 2
Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning 1
Bayes-optimal Learning of Deep Random Networks of Extensive-width 2
Bayesian Design Principles for Frequentist Sequential Learning 2
Bayesian Estimation of Differential Privacy 4
Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts 3
Bayesian Progressive Deep Topic Model with Knowledge Informed Textual Data Coarsening Process 3
Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models 4
Bayesian online change point detection with Hilbert space approximate Student-t process 3
Beam Tree Recursive Cells 6
Behavior Contrastive Learning for Unsupervised Skill Discovery 5
Benign Overfitting in Deep Neural Networks under Lazy Training 3
Benign Overfitting in Two-layer ReLU Convolutional Neural Networks 2
Best Arm Identification in Multi-Agent Multi-Armed Bandits 4
Best of Both Worlds Policy Optimization 1
Better Diffusion Models Further Improve Adversarial Training 5
Better Training of GFlowNets with Local Credit and Incomplete Trajectories 3
Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic 2
Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering 3
Beyond In-Domain Scenarios: Robust Density-Aware Calibration 5
Beyond Lipschitz Smoothness: A Tighter Analysis for Nonconvex Optimization 4
Beyond Reward: Offline Preference-guided Policy Optimization 5
Beyond Uniform Lipschitz Condition in Differentially Private Optimization 4
Beyond the Edge of Stability via Two-step Gradient Updates 2
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels 2
Bi-directional Masks for Efficient N:M Sparse Training 6
BiBench: Benchmarking and Analyzing Network Binarization 5
BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning 6
Biases in Evaluation of Molecular Optimization Methods and Bias Reduction Strategies 5
Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions 4
Bidirectional Learning for Offline Model-based Biological Sequence Design 5
Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers 5
Bigger, Better, Faster: Human-level Atari with human-level efficiency 5
Bilevel Optimization with Coupled Decision-Dependent Distributions 2
Bit Allocation using Optimization 6
Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces 5
Block Subsampled Randomized Hadamard Transform for Nyström Approximation on Distributed Architectures 6
Blockwise Stochastic Variance-Reduced Methods with Parallel Speedup for Multi-Block Bilevel Optimization 6
Blossom: an Anytime Algorithm for Computing Optimal Decision Trees 7
Boosting Graph Contrastive Learning via Graph Contrastive Saliency 5
Boosting Offline Reinforcement Learning with Action Preference Query 3
Bootstrap in High Dimension with Low Computation 3
Bootstrapped Representations in Reinforcement Learning 2
Brainformers: Trading Simplicity for Efficiency 5
Brauer’s Group Equivariant Neural Networks 0
Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach 3
Buying Information for Stochastic Optimization 1
Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting 4
CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling 4
CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets 5
CLIPood: Generalizing CLIP to Out-of-Distributions 7
CLUSTSEG: Clustering for Universal Segmentation 5
CLUTR: Curriculum Learning via Unsupervised Task Representation Learning 4
CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design 4
COLA: Orchestrating Error Coding and Learning for Robust Neural Network Inference Against Hardware Defects 4
COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models 5
CRISP: Curriculum based Sequential neural decoders for Polar code family 3
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations 4
Calibrating Multimodal Learning 4
Can Forward Gradient Match Backpropagation? 3
Can Large Language Models Reason about Program Invariants? 4
Can Neural Network Memorization Be Localized? 3
Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models? 5
CataBEEM: Integrating Latent Interaction Categories in Node-wise Community Detection Models for Network Data 5
Causal Bounds in Quasi-Markovian Graphs 3
Causal Discovery with Latent Confounders Based on Higher-Order Cumulants 1
Causal Isotonic Calibration for Heterogeneous Treatment Effects 4
Causal Modeling of Policy Interventions From Treatment-Outcome Sequences 4
Causal Proxy Models for Concept-based Model Explanations 4
Causal Strategic Classification: A Tale of Two Shifts 5
Causal Structure Learning for Latent Intervened Non-stationary Data 4
Cell-Free Latent Go-Explore 6
Certified Robust Neural Networks: Generalization and Corruption Resistance 5
Certifying Ensembles: A General Certification Theory with S-Lipschitzness 2
Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning 6
Change is Hard: A Closer Look at Subpopulation Shift 4
Chemically Transferable Generative Backmapping of Coarse-Grained Proteins 6
ChiPFormer: Transferable Chip Placement via Offline Decision Transformer 5
CircuitNet: A Generic Neural Network to Realize Universal Circuit Motif Modeling 3
ClimaX: A foundation model for weather and climate 5
Cluster Explanation via Polyhedral Descriptions 4
ClusterFuG: Clustering Fully connected Graphs by Multicut 6
CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification 3
CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis 6
Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D 4
Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning Using Independent Component Analysis 2
CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks 4
CodeIPPrompt: Intellectual Property Infringement Assessment of Code Language Models 4
Coder Reviewer Reranking for Code Generation 2
Coin Sampling: Gradient-Based Bayesian Inference without Learning Rates 6
Cold Analysis of Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator 7
Collaborative Causal Inference with Fair Incentives 3
Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits 2
Combinatorial Neural Bandits 2
Communication-Constrained Bandits under Additive Gaussian Noise 1
Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation 3
Comparison of meta-learners for estimating multi-valued treatment heterogeneous effects 3
Competing for Shareable Arms in Multi-Player Multi-Armed Bandits 3
Competitive Gradient Optimization 2
Complementary Attention for Multi-Agent Reinforcement Learning 3
Complexity of Block Coordinate Descent with Proximal Regularization and Applications to Wasserstein CP-dictionary Learning 3
Composer: Creative and Controllable Image Synthesis with Composable Conditions 2
Compositional Exemplars for In-context Learning 5
Compositional Score Modeling for Simulation-Based Inference 4
Compressed Decentralized Proximal Stochastic Gradient Method for Nonconvex Composite Problems with Heterogeneous Data 5
Compressing Tabular Data via Latent Variable Estimation 4
Computational Asymmetries in Robust Classification 6
Computational Doob h-transforms for Online Filtering of Discretely Observed Diffusions 3
Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings 3
ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction 3
Concept-based Explanations for Out-of-Distribution Detectors 6
Concurrent Shuffle Differential Privacy Under Continual Observation 1
Conditional Graph Information Bottleneck for Molecular Relational Learning 5
Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models 6
Conditionally Strongly Log-Concave Generative Models 4
Cones: Concept Neurons in Diffusion Models for Customized Generation 3
Confidence and Dispersity Speak: Characterizing Prediction Matrix for Unsupervised Accuracy Estimation 4
Conformal Inference is (almost) Free for Neural Networks Trained with Early Stopping 5
Conformal Prediction Sets for Graph Neural Networks 6
Conformal Prediction for Federated Uncertainty Quantification Under Label Shift 4
Conformal Prediction with Missing Values 5
Conformalization of Sparse Generalized Linear Models 3
Consistency Models 4
Consistency of Multiple Kernel Clustering 3
Constant Matters: Fine-grained Error Bound on Differentially Private Continual Observation 2
Constrained Causal Bayesian Optimization 4
Constrained Decision Transformer for Offline Safe Reinforcement Learning 3
Constrained Efficient Global Optimization of Expensive Black-box Functions 2
Constrained Monotonic Neural Networks 4
Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching 4
Constrained Phi-Equilibria 1
Context Consistency Regularization for Label Sparsity in Time Series 6
Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning 3
Contextual Combinatorial Bandits with Probabilistically Triggered Arms 3
Contextual Conservative Interleaving Bandits 3
Contextual Reliability: When Different Features Matter in Different Contexts 3
Continual Learners are Incremental Model Generalizers 3
Continual Learning in Linear Classification on Separable Data 1
Continual Task Allocation in Meta-Policy Network via Sparse Prompting 4
Continual Vision-Language Representation Learning with Off-Diagonal Information 4
Continuation Path Learning for Homotopy Optimization 5
Continuous Spatiotemporal Transformer 6
Continuously Parameterized Mixture Models 3
ContraBAR: Contrastive Bayes-Adaptive Deep RL 2
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining 4
Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning 4
Contrastive Learning Meets Homophily: Two Birds with One Stone 4
Controllability-Aware Unsupervised Skill Discovery 5
Controllable Neural Symbolic Regression 4
Controlled Differential Equations on Long Sequences via Non-standard Wavelets 5
Controlled Text Generation with Natural Language Instructions 4
Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network 2
Controlling Type Confounding in Ad Hoc Teamwork with Instance-wise Teammate Feedback Rectification 3
Convergence of First-Order Methods for Constrained Nonconvex Optimization with Dependent Data 3
Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity 1
Convex Geometry of ReLU-layers, Injectivity on the Ball and Local Reconstruction 4
Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational Autoencoders 5
Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation 1
Cooperative Open-ended Learning Framework for Zero-Shot Coordination 4
Coordinate Descent Methods for Fractional Minimization 5
Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets 3
Correcting discount-factor mismatch in on-policy policy gradient methods 4
Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes 1
Counterfactual Analysis in Dynamic Latent State Models 5
Counterfactual Identifiability of Bijective Causal Models 3
Coupled Variational Autoencoder 3
Covariate balancing using the integral probability metric for causal inference 6
Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution 2
Cramming: Training a Language Model on a single GPU in one day. 5
Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss 2
Cross-Entropy Loss Functions: Theoretical Analysis and Applications 3
Cross-Modal Fine-Tuning: Align then Refine 6
CrossSplit: Mitigating Label Noise Memorization through Data Splitting 6
Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments 4
Curious Replay for Model-based Adaptation 6
Curriculum Co-disentangled Representation Learning across Multiple Environments for Social Recommendation 4
Cut your Losses with Squentropy 3
Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization 4
D2Match: Leveraging Deep Learning and Degeneracy for Subgraph Matching 4
DADAO: Decoupled Accelerated Decentralized Asynchronous Optimization 2
DDGR: Continual Learning with Deep Diffusion-based Generative Replay 3
DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning 5
DIVISION: Memory Efficient Training via Dual Activation Precision 7
DP-Fast MH: Private, Fast, and Accurate Metropolis-Hastings for Large-Scale Bayesian Inference 4
DRCFS: Doubly Robust Causal Feature Selection 4
DRew: Dynamically Rewired Message Passing with Delay 5
DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation 5
DSGD-CECA: Decentralized SGD with Communication-Optimal Exact Consensus Algorithm 5
DUET: 2D Structured and Approximately Equivariant Representations 4
Data Efficient Neural Scaling Law via Model Reusing 3
Data Feedback Loops: Model-driven Amplification of Dataset Biases 5
Data Poisoning Attacks Against Multimodal Encoders 3
Data Representations’ Study of Latent Image Manifolds 2
Data Structures for Density Estimation 4
Data-Copying in Generative Models: A Formal Framework 3
Data-Driven Subgroup Identification for Linear Regression 6
Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the Least 4
Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value 5
Dataset Distillation with Convexified Implicit Gradients 5
DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models 5
Decentralized SGD and Average-direction SAM are Asymptotically Equivalent 4
Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity 4
Decoding Layer Saliency in Language Transformers 3
DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design 6
Deep Anomaly Detection under Labeling Budget Constraints 4
Deep Clustering with Incomplete Noisy Pairwise Annotations: A Geometric Regularization Approach 4
Deep Generative Symbolic Regression with Monte-Carlo-Tree-Search 3
Deep Graph Representation Learning and Optimization for Influence Maximization 4
Deep Laplacian-based Options for Temporally-Extended Exploration 3
Deep Latent State Space Models for Time-Series Generation 4
Deep Perturbation Learning: Enhancing the Network Performance via Image Perturbations 5
Deep Regression Unlearning 5
Deep Temporal Sets with Evidential Reinforced Attentions for Unique Behavioral Pattern Discovery 4
Defects of Convolutional Decoder Networks in Frequency Representation 2
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time 5
Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback 4
Delay-agnostic Asynchronous Coordinate Update Algorithm 4
Delayed Bandits: When Do Intermediate Observations Help? 2
Delayed Feedback in Kernel Bandits 3
Delving into Noisy Label Detection with Clean Data 5
Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum 4
Demystifying Disagreement-on-the-Line in High Dimensions 3
Demystifying Uneven Vulnerability of Link Stealing Attacks against Graph Neural Networks 2
Denoising MCMC for Accelerating Diffusion-Based Generative Models 5
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature 4
Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score 6
Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions 3
Detecting Out-of-distribution Data through In-distribution Class Prior 4
Deterministic equivalent and error universality of deep random features learning 1
DevFormer: A Symmetric Transformer for Context-Aware Device Placement 5
Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation 3
Difference of submodular minimization via DC programming 4
Difference-in-Differences Meets Tree-based Methods: Heterogeneous Treatment Effects Estimation with Unmeasured Confounding 3
Differentiable Multi-Target Causal Bayesian Experimental Design 4
Differentiable Simulations for Enhanced Sampling of Rare Events 3
Differentiable Tree Operations Promote Compositional Generalization 5
Differentiable and Transportable Structure Learning 3
Differential Privacy has Bounded Impact on Fairness in Classification 3
Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models 6
Differentially Private Distributed Bayesian Linear Regression with MCMC 6
Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards 3
Differentially Private Hierarchical Clustering with Provable Approximation Guarantees 4
Differentially Private Optimization on Large Model at Small Cost 5
Differentially Private Sharpness-Aware Training 6
Differentially Private Stochastic Convex Optimization under a Quantile Loss Function 2
Diffusion Based Representation Learning 4
Diffusion Models are Minimax Optimal Distribution Estimators 0
Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines? 4
Diffusion Models for Black-Box Optimization 5
Dimension-independent Certified Neural Network Watermarks via Mollifier Smoothing 4
Dimensionality Reduction for General KDE Mode Finding 3
Dink-Net: Neural Clustering on Large Graphs 5
Direct Parameterization of Lipschitz-Bounded Deep Networks 5
Directed Chain Generative Adversarial Networks 4
Dirichlet Diffusion Score Model for Biological Sequence Generation 5
DiscoBAX: Discovery of optimal intervention sets in genomic experiment design 4
Discover and Cure: Concept-aware Mitigation of Spurious Correlation 6
Discover-Then-Rank Unlabeled Support Vectors in the Dual Space for Multi-Class Active Learning 4
Discovering Object-Centric Generalized Value Functions From Pixels 5
Discrete Continuous Optimization Framework for Simultaneous Clustering and Training in Mixture Models 6
Discrete Key-Value Bottleneck 4
Disentangled Generative Models for Robust Prediction of System Dynamics 3
Disentangled Multi-Fidelity Deep Bayesian Active Learning 3
Disentangled Multiplex Graph Representation Learning 4
Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning 3
Distance Weighted Supervised Learning for Offline Interaction Data 5
Distilling Internet-Scale Vision-Language Models into Embodied Agents 2
Distortion and Uncertainty Aware Loss for Panoramic Depth Completion 3
Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost 2
Distributed Linear Bandits under Communication Constraints 2
Distribution Free Domain Generalization 5
Distribution Free Prediction Sets for Node Classification 5
Distribution-dependent McDiarmid-type Inequalities for Functions of Unbounded Interaction 0
Distributional Offline Policy Evaluation with Predictive Error Guarantees 3
Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference 6
Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation 6
Divide and Conquer Dynamic Programming: An Almost Linear Time Change Point Detection Methodology in High Dimensions 6
Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat 5
Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling 5
Do Machine Learning Models Learn Statistical Rules Inferred from Data? 5
Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks 6
Do Perceptually Aligned Gradients Imply Robustness? 5
Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection 4
Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark 3
DoCoFL: Downlink Compression for Cross-Device Federated Learning 3
DoG is SGD’s Best Friend: A Parameter-Free Dynamic Step Size Schedule 5
DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm 3
Does Continual Learning Equally Forget All Parameters? 4
Does Sparsity Help in Learning Misspecified Linear Bandits? 1
Does a Neural Network Really Encode Symbolic Concepts? 3
Domain Adaptation for Time Series Under Feature and Label Shifts 6
Double-Weighting for Covariate Shift Adaptation 4
Doubly Adversarial Federated Bandits 5
Doubly Optimal No-Regret Learning in Monotone Games 3
Dropout Reduces Underfitting 4
Drug Discovery under Covariate Shift with Domain-Informed Prior Distributions over Functions 4
Dual Focal Loss for Calibration 5
Dual Propagation: Accelerating Contrastive Hebbian Learning with Dyadic Neurons 6
DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning 6
Dynamic Constrained Submodular Optimization with Polylogarithmic Update Time 1
Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape 6
Dynamical Linear Bandits 4
Dynamics-inspired Neuromorphic Visual Representation Learning 5
E$(n)$ Equivariant Message Passing Simplicial Networks 4
ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines 6
EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compression 3
ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Models 3
EM-Network: Oracle Guided Self-distillation for Sequence Learning 5
ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation 4
Effective Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories 0
Effective Neural Topic Modeling with Embedding Clustering Regularization 4
Effective Structured Prompting by Meta-Learning and Representative Verbalizer 5
Effective and Efficient Structural Inference with Reservoir Computing 7
Effectively Using Public Data in Privacy Preserving Machine Learning 4
Efficient Algorithms for Exact Graph Matching on Correlated Stochastic Block Models with Constant Correlation 4
Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction 5
Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration 5
Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization 3
Efficient Graph Field Integrators Meet Point Clouds 6
Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming 6
Efficient Learning of Mesh-Based Physical Simulation with Bi-Stride Multi-Scale Graph Neural Network 6
Efficient List-Decodable Regression using Batches 1
Efficient Online Reinforcement Learning with Offline Data 4
Efficient Parametric Approximations of Neural Network Function Space Distance 3
Efficient Personalized Federated Learning via Sparse Model-Adaptation 6
Efficient Quantum Algorithms for Quantum Optimal Control 2
Efficient RL via Disentangled Environment and Agent Representations 5
Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation 1
Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language 5
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations 5
Efficient Training of Language Models using Few-Shot Learning 3
Efficient Transformed Gaussian Processes for Non-Stationary Dependent Multi-class Classification 4
Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling 6
Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian 6
Efficient displacement convex optimization with particle gradient descent 2
Efficient preconditioned stochastic gradient descent for estimation in latent variable models 4
Efficiently predicting high resolution mass spectra with graph neural networks 6
Eliminating Adversarial Noise via Information Discard and Robust Representation Restoration 4
Emergence of Adaptive Circadian Rhythms in Deep Reinforcement Learning 3
Emergence of Sparse Representations from Noise 3
Emergent Agentic Transformer from Chain of Hindsight Experience 4
Emergent Asymmetry of Precision and Recall for Measuring Fidelity and Diversity of Generative Models in High Dimensions 3
Enabling First-Order Gradient-Based Learning for Equilibrium Computation in Markets 3
End-to-End Full-Atom Antibody Design 5
End-to-End Learning for Stochastic Optimization: A Bayesian Perspective 4
End-to-End Multi-Object Detection with a Regularized Mixture Model 5
End-to-end Differentiable Clustering with Associative Memories 5
End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization 4
Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments 2
Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language 6
Entity Divider with Language Grounding in Multi-Agent Reinforcement Learning 4
Entropy-driven Unsupervised Keypoint Representation Learning in Videos 4
Equivariance with Learned Canonicalization Functions 6
Equivariant Architectures for Learning in Deep Weight Spaces 4
Equivariant Polynomials for Graph Neural Networks 5
Escaping saddle points in zeroth-order optimization: the power of two-point estimators 4
Estimating Causal Effects using a Multi-task Deep Ensemble 4
Estimating Heterogeneous Treatment Effects: Mutual Information Bounds and Learning Algorithms 4
Estimating Joint Treatment Effects by Combining Multiple Experiments 2
Estimating Possible Causal Effects with Latent Variables via Adjustment 2
Estimating the Contamination Factor’s Distribution in Unsupervised Anomaly Detection 3
Estimation Beyond Data Reweighting: Kernel Method of Moments 4
Evaluating Self-Supervised Learning via Risk Decomposition 6
Evaluating Unsupervised Denoising Requires Unsupervised Metrics 5
Eventual Discounting Temporal Logic Counterfactual Experience Replay 3
Everyone’s Preference Changes Differently: A Weighted Multi-Interest Model For Retrieval 6
Evidential Interactive Learning for Medical Image Captioning 5
Evolving Semantic Prototype Improves Generative Zero-Shot Learning 3
Ewald-based Long-Range Message Passing for Molecular Graphs 4
Exact Inference in High-order Structured Prediction 2
Existence and Estimation of Critical Batch Size for Training Generative Adversarial Networks with Two Time-Scale Update Rule 6
Expectation-Complete Graph Representations with Homomorphisms 6
Expected Gradients of Maxout Networks and Consequences to Parameter Initialization 5
Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making 4
Exphormer: Sparse Transformers for Graphs 5
Explainability as statistical inference 3
Explainable Data-Driven Optimization: From Context to Decision and Back Again 6
Explaining Reinforcement Learning with Shapley Values 3
Explaining the effects of non-convergent MCMC in the training of Energy-Based Models 2
Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization 3
Exploring Chemical Space with Score-based Out-of-distribution Generation 4
Exploring Model Dynamics for Accumulative Poisoning Discovery 5
Exploring the Benefits of Training Expert Language Models over Instruction Tuning 4
Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks 6
Exponential Smoothing for Off-Policy Learning 3
Extending Conformal Prediction to Hidden Markov Models with Exact Validity via de Finetti’s Theorem for Markov Chains 3
Extending Kernel PCA through Dualization: Sparsity, Robustness and Fast Algorithms 5
Extrapolated Random Tree for Regression 6
Extrapolative Controlled Sequence Generation via Iterative Refinement 3
FAENet: Frame Averaging Equivariant GNN for Materials Modeling 6
FAIRER: Fairness as Decision Rationale Alignment 4
FARE: Provably Fair Representation Learning with Practical Certificates 5
FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems 4
FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation 4
FREDIS: A Fusion Framework of Refinement and Disambiguation for Unreliable Partial Label Learning 5
FaDIn: Fast Discretized Inference for Hawkes Processes with General Parametric Kernels 2
Facial Expression Recognition with Adaptive Frame Rate based on Multiple Testing Correction 6
Fair Densities via Boosting the Sufficient Statistics of Exponential Families 6
Fair Neighbor Embedding 3
Fair and Accurate Decision Making through Group-Aware Learning 6
Fair and Optimal Classification via Post-Processing 6
Fair and Robust Estimation of Heterogeneous Treatment Effects for Policy Learning 3
Fair yet Asymptotically Equal Collaborative Learning 5
Fairness in Matching under Uncertainty 2
Fairness in Streaming Submodular Maximization over a Matroid Constraint 4
Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning 5
Fast $(1+\varepsilon)$-Approximation Algorithms for Binary Matrix Factorization 3
Fast Algorithms for Distributed k-Clustering with Outliers 4
Fast Combinatorial Algorithms for Min Max Correlation Clustering 4
Fast Excess Risk Rates via Offset Rademacher Complexity 0
Fast Federated Machine Unlearning with Nonlinear Functional Theory 4
Fast Inference from Transformers via Speculative Decoding 4
Fast Online Node Labeling for Very Large Graphs 4
Fast Online Value-Maximizing Prediction Sets with Conformal Cost Control 5
Fast Private Kernel Density Estimation via Locality Sensitive Quantization 4
Fast Rates for Maximum Entropy Exploration 4
Fast Rates in Time-Varying Strongly Monotone Games 3
Fast Sampling of Diffusion Models via Operator Learning 4
Fast as CHITA: Neural Network Pruning with Combinatorial Optimization 5
Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective 5
Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic Optimization 3
Faster Rates of Convergence to Stationary Points in Differentially Private Optimization 1
FeDXL: Provable Federated Learning for Deep X-Risk Optimization 6
Feature Directions Matter: Long-Tailed Learning via Rotated Balanced Representation 4
Feature Expansion for Graph Neural Networks 5
Feature Programming for Multivariate Time Series Prediction 4
Feature learning in deep classifiers through Intermediate Neural Collapse 4
Featured Graph Coarsening with Similarity Guarantees 4
Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction 3
FedAvg Converges to Zero Training Loss Linearly for Overparameterized Multi-Layer Neural Networks 3
FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction 5
FedCR: Personalized Federated Learning Based on Across-Client Common Representation with Conditional Mutual Information Regularization 7
FedDisco: Federated Learning with Discrepancy-Aware Collaboration 5
FedHPO-Bench: A Benchmark Suite for Federated Hyperparameter Optimization 7
FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models 5
Federated Adversarial Learning: A Framework with Convergence Analysis 2
Federated Conformal Predictors for Distributed Uncertainty Quantification 5
Federated Heavy Hitter Recovery under Linear Sketching 4
Federated Linear Contextual Bandits with User-level Differential Privacy 1
Federated Online and Bandit Convex Optimization 1
Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection 6
Few-Sample Feature Selection via Feature Manifold Learning 6
Few-bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction 6
Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation 4
Finding Generalization Measures by Contrasting Signal and Noise 5
Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs 4
Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron 1
Fisher Information Embedding for Node and Graph Learning 5
Flash: Concept Drift Adaptation in Federated Learning 6
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU 5
FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization 2
Flexible Phase Dynamics for Bio-Plausible Contrastive Learning 3
Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning 5
For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal 4
Forget Unlearning: Towards True Data-Deletion in Machine Learning 2
Formalizing Preferences Over Runtime Distributions 2
Forward-Backward Gaussian Variational Inference via JKO in the Bures-Wasserstein Space 3
Fourmer: An Efficient Global Modeling Paradigm for Image Restoration 3
Fractional Denoising for 3D Molecular Pre-training 5
Free-Form Variational Inference for Gaussian Process State-Space Models 5
From Adaptive Query Release to Machine Unlearning 1
From Hypergraph Energy Functions to Hypergraph Neural Networks 6
From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning 3
From Perception to Programs: Regularize, Overparameterize, and Amortize 3
From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks 4
From Robustness to Privacy and Back 2
From Temporal to Contemporaneous Iterative Causal Discovery in the Presence of Latent Confounders 3
Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes 5
Fully Dynamic Submodular Maximization over Matroids 1
Fully-Adaptive Composition in Differential Privacy 0
Function-Space Regularization in Neural Networks: A Probabilistic Perspective 4
Functional Neural Networks: Shift invariant models for functional data with applications to EEG classification 4
Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods 2
Fundamental Tradeoffs in Learning with Prior Information 1
FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning 7
Future-conditioned Unsupervised Pretraining for Decision Transformer 5
GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks 5
GC-Flow: A Graph-Based Flow Network for Effective Clustering 5
GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models 4
GFlowNet-EM for Learning Compositional Latent Variable Models 7
GFlowOut: Dropout with Generative Flow Networks 6
GLOBE-CE: A Translation Based Approach for Global Counterfactual Explanations 3
GNN&GBDT-Guided Fast Optimizing Framework for Large-scale Integer Programming 5
GNOT: A General Neural Operator Transformer for Operator Learning 5
GOAT: A Global Transformer on Large-scale Graphs 6
GRAFENNE: Learning on Graphs with Heterogeneous and Dynamic Feature Sets 5
GREAD: Graph Neural Reaction-Diffusion Networks 7
Gaussian Process Priors for Systems of Linear Partial Differential Equations with Constant Coefficients 4
Gaussian processes at the Helm(holtz): A more fluid model for ocean currents 3
GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistency 4
General Covariance Data Augmentation for Neural PDE Solvers 3
General Sequential Episodic Memory Model 2
Generalization Analysis for Contrastive Representation Learning 0
Generalization Bounds using Data-Dependent Fractal Dimensions 4
Generalization on the Unseen, Logic Reasoning and Degree Curriculum 4
Generalized Disparate Impact for Configurable Fairness Solutions in ML 6
Generalized Implicit Follow-The-Regularized-Leader 3
Generalized Polyak Step Size for First Order Optimization with Momentum 3
Generalized Reductions: Making any Hierarchical Clustering Fair and Balanced with Low Cost 4
Generalized Teacher Forcing for Learning Chaotic Dynamics 5
Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth Nonconvex Optimization 4
Generalizing Neural Wave Functions 5
Generated Graph Detection 3
Generating Language Corrections for Teaching Physical Control Tasks 7
Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Clouds 4
Generating Private Synthetic Data with Genetic Algorithms 4
Generative Adversarial Symmetry Discovery 3
Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting 4
Generative Decoding of Visual Stimuli 2
Generative Graph Dictionary Learning 5
Generative Pretraining for Black-Box Optimization 5
Geometric Autoencoders - What You See is What You Decode 4
Geometric Clifford Algebra Networks 4
Geometric Latent Diffusion Models for 3D Molecule Generation 5
GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration 5
Gibbsian Polar Slice Sampling 7
Git-Theta: A Git Extension for Collaborative Development of Machine Learning Models 3
Global Context Vision Transformers 6
Global Optimization with Parametric Function Approximation 4
Global Selection of Contrastive Batches via Optimization on Sample Permutations 7
Global optimality for Euclidean CCCP under Riemannian convexity 1
Global optimality of Elman-type RNNs in the mean-field regime 2
Go Beyond Imagination: Maximizing Episodic Reachability with World Models 4
Gradient Descent Converges Linearly for Logistic Regression on Separable Data 3
Gradient Descent Finds the Global Optima of Two-Layer Physics-Informed Neural Networks 1
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond 2
Gradient Descent in Neural Networks as Sequential Learning in Reproducing Kernel Banach Space 0
Gradient-Free Structured Pruning with Unlabeled Data 5
Gradient-based Wang-Landau Algorithm: A Novel Sampler for Output Distribution of Neural Networks over the Input Space 5
Graph Contrastive Backdoor Attacks 3
Graph Generative Model for Benchmarking Graph Neural Networks 5
Graph Inductive Biases in Transformers without Message Passing 5
Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication 6
Graph Mixup with Soft Alignments 5
Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure 4
Graph Neural Networks with Learnable and Optimal Polynomial Bases 5
Graph Neural Tangent Kernel: Convergence on Large Graphs 5
Graph Positional Encoding via Random Feature Propagation 5
Graph Reinforcement Learning for Network Control via Bi-Level Optimization 4
Graph Switching Dynamical Systems 6
GraphCleaner: Detecting Mislabelled Samples in Popular Graph Learning Benchmarks 5
Graphically Structured Diffusion Models 4
Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement 5
Grounding Language Models to Images for Multimodal Inputs and Outputs 5
Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning 4
Group Equivariant Fourier Neural Operators for Partial Differential Equations 5
GuardHFL: Privacy Guardian for Heterogeneous Federated Learning 4
Guiding Pretraining in Reinforcement Learning with Large Language Models 4
H-Likelihood Approach to Deep Neural Networks with Temporal-Spatial Random Effects for High-Cardinality Categorical Features 6
HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption 6
HOPE: High-order Graph ODE For Modeling Interacting Dynamics 4
Half-Hop: A graph upsampling approach for slowing down message passing 5
Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games 1
Hardware-Aware Compression with Random Operation Access Specific Tile (ROAST) Hashing 5
Harmonic Neural Networks 4
HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation 3
Hidden Symmetries of ReLU Networks 1
Hiding Data Helps: On the Benefits of Masking for Sparse Coding 4
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles 6
Hierarchical Diffusion for Offline Decision Making 4
Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction 4
Hierarchical Imitation Learning with Vector Quantized Models 3
Hierarchical Neural Coding for Controllable CAD Model Generation 5
Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs 3
Hierarchies of Reward Machines 5
High Fidelity Image Counterfactuals with Probabilistic Causal Models 4
High Probability Convergence of Stochastic Gradient Methods 1
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance 1
High-dimensional Clustering onto Hamiltonian Cycle 4
High-dimensional Location Estimation via Norm Concentration for Subgamma Vectors 3
Hindsight Learning for MDPs with Exogenous Inputs 5
Homomorphism AutoEncoder -- Learning Group Structured Representations from Observed Transitions 4
Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes 1
Horizon-free Learning for Markov Decision Processes and Games: Stochastically Bounded Rewards and Improved Bounds 1
How Bad is Top-$K$ Recommendation under Competing Content Creators? 3
How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding 3
How Does Information Bottleneck Help Deep Learning? 3
How Jellyfish Characterise Alternating Group Equivariant Neural Networks 1
How Many Perturbations Break This Model? Evaluating Robustness Beyond Adversarial Accuracy 5
How Powerful are Shallow Neural Networks with Bandlimited Random Weights? 2
How much does Initialization Affect Generalization? 2
How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control 6
How to address monotonicity for model risk management? 4
Human-Timescale Adaptation in an Open-Ended Task Space 3
Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection 5
Hyena Hierarchy: Towards Larger Convolutional Language Models 5
HyperTuning: Toward Adapting Large Language Models without Back-propagation 3
Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation Learning 6
Hyperbolic Image-text Representations 4
Hyperbolic Representation Learning: Revisiting and Advancing 4
Hyperparameters in Reinforcement Learning and How To Tune Them 5
Hypervolume Knowledge Gradient: A Lookahead Approach for Multi-Objective Bayesian Optimization with Partial Information 4
Hypothesis Transfer Learning with Surrogate Classification Losses: Generalization Bounds through Algorithmic Stability 1
I$^2$SB: Image-to-Image Schrödinger Bridge 5
ILLUME: Rationalizing Vision-Language Models through Human Interactions 5
IRNeXt: Rethinking Convolutional Network Design for Image Restoration 5
Identifiability and Generalizability in Constrained Inverse Reinforcement Learning 5
Identifiability of Label Noise Transition Matrix 4
Identification of the Adversary from a Single Adversarial Example 4
Identifying Interpretable Subspaces in Image Representations 4
Identifying Useful Learnwares for Heterogeneous Label Spaces 4
Image Restoration with Mean-Reverting Stochastic Differential Equations 4
Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression 3
Image generation with shortest path diffusion 5
Implicit Graph Neural Networks: A Monotone Operator Viewpoint 5
Implicit Jacobian regularization weighted with impurity of probability output 4
Implicit Neural Spatial Representations for Time-dependent PDEs 4
Implicit Regularization Leads to Benign Overfitting for Sparse Linear Regression 1
Importance Weighted Expectation-Maximization for Protein Sequence Design 6
Improved Active Multi-Task Representation Learning via Lasso 3
Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback 2
Improved Algorithms for White-Box Adversarial Streams 1
Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions 0
Improved Learning-Augmented Algorithms for the Multi-Option Ski Rental Problem via Best-Possible Competitive Analysis 1
Improved Online Conformal Prediction via Strongly Adaptive Online Learning 5
Improved Online Learning Algorithms for CTR Prediction in Ad Auctions 1
Improved Policy Evaluation for Randomized Trials of Algorithmic Resource Allocation 3
Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation 1
Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs 4
Improving Adversarial Robustness Through the Contrastive-Guided Diffusion Process 4
Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samples 4
Improving Adversarial Robustness of Deep Equilibrium Models with Explicit Regulations Along the Neural Dynamics 5
Improving Bi-level Optimization Based Methods with Inspiration from Humans’ Classroom Study Techniques 6
Improving Expert Predictions with Conformal Prediction 7
Improving Fair Training under Correlation Shifts 4
Improving Graph Generation by Restricting Graph Bandwidth 5
Improving Graph Neural Networks with Learnable Propagation Operators 4
Improving Hyperparameter Learning under Approximate Inference in Gaussian Process Models 6
Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modeling 5
Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models 5
Improving Visual Prompt Tuning for Self-supervised Vision Transformers 4
Improving l1-Certified Robustness via Randomized Smoothing by Leveraging Box Constraints 5
Improving the Model Consistency of Decentralized Federated Learning 4
In Search for a Generalizable Method for Source Free Domain Adaptation 3
In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect Estimation 4
In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation 4
InGram: Inductive Knowledge Graph Embedding via Relation Graphs 6
IncDSI: Incrementally Updatable Document Retrieval 6
Incentivizing Exploration with Linear Contexts and Combinatorial Actions 1
Individually Fair Learning with One-Sided Feedback 1
Inferring Relational Potentials in Interacting Systems 7
Infinite Action Contextual Bandits with Reusable Data Exhaust 5
Inflow, Outflow, and Reciprocity in Machine Learning 3
InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models 4
InfoOT: Information Maximizing Optimal Transport 4
Information-Theoretic State Space Model for Multi-View Reinforcement Learning 7
Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoning 1
Input Perturbation Reduces Exposure Bias in Diffusion Models 6
Input uncertainty propagation through trained neural networks 6
Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models 4
Instrumental Variable Estimation of Average Partial Causal Effects 4
Integrating Prior Knowledge in Contrastive Learning with Kernel 6
Interactive Object Placement with Reinforcement Learning 3
Internally Rewarded Reinforcement Learning 4
Internet Explorer: Targeted Representation Learning on the Open Web 6
Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics 4
Interpretable Neural-Symbolic Concept Reasoning 6
Interval Bound Interpolation for Few-shot Learning with Few Tasks 6
Interventional Causal Representation Learning 4
Intrinsic Sliced Wasserstein Distances for Comparing Collections of Probability Distributions on Manifolds and Graphs 3
Invariance in Policy Optimisation and Partial Identifiability in Reward Learning 0
Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames 5
Inverse Reinforcement Learning without Reinforcement Learning 4
Investigating the Role of Model-Based Learning in Exploration and Transfer 2
Is Consensus Acceleration Possible in Decentralized Optimization over Slowly Time-Varying Networks? 1
Is Learning Summary Statistics Necessary for Likelihood-free Inference? 3
Is Overfitting Necessary for Implicit Video Representation? 4
Iterative Approximate Cross-Validation 3
JAWS-X: Addressing Efficiency Bottlenecks of Conformal Prediction Under Standard and Feedback Covariate Shift 3
Jump-Start Reinforcement Learning 4
K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs 3
KDEformer: Accelerating Transformers via Kernel Density Estimation 4
Kernel Logistic Regression Approximation of an Understandable ReLU Neural Network 3
Kernel QuantTree 4
Kernel Sufficient Dimension Reduction and Variable Selection for Compositional Data via Amalgamation 4
LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning 3
LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework 4
LEVER: Learning to Verify Language-to-Code Generation with Execution 4
LIV: Language-Image Representations and Rewards for Robotic Control 5
LSDS++ : Dual Sampling for Accelerated k-means++ 3
Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity 6
Label differential privacy and private training data release 4
Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning 2
Language Instructed Reinforcement Learning for Human-AI Coordination 4
Large Language Models Can Be Easily Distracted by Irrelevant Context 2
Large Language Models Struggle to Learn Long-Tail Knowledge 5
Last Switch Dependent Bandits with Monotone Payoff Functions 1
Latent Traversals in Generative Models as Potential Flows 4
Layered State Discovery for Incremental Autonomous Exploration 3
Lazy Agents: A New Perspective on Solving Sparse Reward Problem in Multi-agent Reinforcement Learning 4
LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation 4
LeadFL: Client Self-Defense against Model Poisoning in Federated Learning 4
Learn to Accumulate Evidence from All Training Samples: Theory and Practice 3
Learnability and Algorithm for Continual Learning 4
Learning Affinity with Hyperbolic Representation for Spatial Propagation 5
Learning Antidote Data to Individual Unfairness 5
Learning Belief Representations for Partially Observable Deep RL 3
Learning Compiler Pass Orders using Coreset and Normalized Value Prediction 4
Learning Control by Iterative Inversion 4
Learning Control-Oriented Dynamical Structure from Data 3
Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows 3
Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic 5
Learning Deep Time-index Models for Time Series Forecasting 6
Learning Dense Correspondences between Photos and Sketches 3
Learning Distributions over Quantum Measurement Outcomes 1
Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation 4
Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks 5
Learning Functional Distributions with Private Labels 1
Learning GFlowNets From Partial Episodes For Improved Convergence And Stability 3
Learning Globally Smooth Functions on Manifolds 5
Learning Hidden Markov Models When the Locations of Missing Observations are Unknown 4
Learning Instance-Specific Augmentations by Capturing Local Invariances 6
Learning Intuitive Policies Using Action Features 2
Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation 6
Learning Mixtures of Gaussians with Censored Data 1
Learning Mixtures of Markov Chains and MDPs 3
Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamics 3
Learning Neural PDE Solvers with Parameter-Guided Channel Attention 7
Learning Noisy OR Bayesian Networks with Max-Product Belief Propagation 5
Learning Perturbations to Explain Time Series Predictions 3
Learning Physical Models that Can Respect Conservation Laws 3
Learning Preconditioners for Conjugate Gradient PDE Solvers 4
Learning Prescriptive ReLU Networks 2
Learning Rate Schedules in the Presence of Distribution Shift 4
Learning Regions of Interest for Bayesian Optimization with Adaptive Level-Set Estimation 3
Learning Representations without Compositional Assumptions 5
Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping 4
Learning Subpocket Prototypes for Generalizable Structure-based Drug Design 6
Learning Temporally AbstractWorld Models without Online Experimentation 2
Learning Unforeseen Robustness from Out-of-distribution Data Using Equivariant Domain Translator 5
Learning Unnormalized Statistical Models via Compositional Optimization 4
Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees 4
Learning in POMDPs is Sample-Efficient with Hindsight Observability 1
Learning the Dynamics of Sparsely Observed Interacting Systems 4
Learning the Right Layers a Data-Driven Layer-Aggregation Strategy for Semi-Supervised Learning on Multilayer Graphs 5
Learning to Bid in Repeated First-Price Auctions with Budgets 2
Learning to Boost Training by Periodic Nowcasting Near Future Weights 6
Learning to Decouple Complex Systems 4
Learning to Design Analog Circuits to Meet Threshold Specifications 4
Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Model 1
Learning to Initiate and Reason in Event-Driven Cascading Processes 2
Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling 4
Learning to Learn from APIs: Black-Box Data-Free Meta-Learning 4
Learning to Maximize Mutual Information for Dynamic Feature Selection 5
Learning to Optimize Differentiable Games 5
Learning to Suggest Breaks: Sustainable Optimization of Long-Term User Engagement 5
Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learning 3
Learning useful representations for shifting tasks and distributions 4
Learning-Rate-Free Learning by D-Adaptation 6
Learning-augmented private algorithms for multiple quantile release 5
LegendreTron: Uprising Proper Multiclass Loss Learning 4
Less is More: Task-aware Layer-wise Distillation for Language Model Compression 6
Leveraging Demonstrations to Improve Online Learning: Quality Matters 2
Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks 5
Leveraging Offline Data in Online Reinforcement Learning 1
Leveraging Proxy of Training Data for Test-Time Adaptation 3
Lifelong Language Pretraining with Distribution-Specialized Experts 3
Likelihood Adjusted Semidefinite Programs for Clustering Heterogeneous Data 3
LinSATNet: The Positive Linear Satisfiability Neural Networks 5
Linear CNNs Discover the Statistical Structure of the Dataset Using Only the Most Dominant Frequencies 2
Linear Causal Disentanglement via Interventions 4
Linear Time GPs for Inferring Latent Trajectories from Neural Spike Trains 3
Linear optimal partial transport embedding 4
Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient Approach 4
Linkless Link Prediction via Relational Distillation 5
LipsNet: A Smooth and Robust Neural Network with Adaptive Lipschitz Constant for High Accuracy Optimal Control 5
Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy 5
LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation 6
Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning 3
Local Vertex Colouring Graph Neural Networks 5
Locally Regularized Neural Differential Equations: Some Black Boxes were meant to remain closed! 5
Long Horizon Temperature Scaling 4
Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels 3
Long-Term Rhythmic Video Soundtracker 6
LongCoder: A Long-Range Pre-trained Language Model for Code Completion 5
Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers 3
LookupFFN: Making Transformers Compute-lite for CPU inference 5
Looped Transformers as Programmable Computers 2
Loss Balancing for Fair Supervised Learning 5
Loss-Guided Diffusion Models for Plug-and-Play Controllable Generation 4
Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability 5
Low Complexity Homeomorphic Projection to Ensure Neural-Network Solution Feasibility for Optimization over (Non-)Convex Set 3
Low-Switching Policy Gradient with Exploration via Online Sensitivity Sampling 3
Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single 4
Lower Bounds for Learning in Revealing POMDPs 0
Lowering the Pre-training Tax for Gradient-based Subset Training: A Lightweight Distributed Pre-Training Toolkit 4
MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior 4
MAGANet: Achieving Combinatorial Generalization by Modeling a Group Action 4
MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations 4
MANSA: Learning Fast and Slow in Multi-Agent Systems 2
MEWL: Few-shot multimodal word learning with referential uncertainty 5
MG-GNN: Multigrid Graph Neural Networks for Learning Multilevel Domain Decomposition Methods 3
MODeL: Memory Optimizations for Deep Learning 6
Machine Learning Force Fields with Data Cost Aware Training 4
Magneto: A Foundation Transformer 4
Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models 4
Margin-based Neural Network Watermarking 5
Margin-based sampling in high dimensions: When being active is less efficient than staying passive 3
Marginalization is not Marginal: No Bad VAE Local Minima when Learning Optimal Sparse Representations 2
Markovian Gaussian Process Variational Autoencoders 5
Masked Bayesian Neural Networks : Theoretical Guarantee and its Posterior Inference 5
Masked Trajectory Models for Prediction, Representation, and Control 4
Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning 3
Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels 4
Matrix Estimation for Individual Fairness 3
Maximal Initial Learning Rates in Deep ReLU Networks 4
Maximum Optimality Margin: A Unified Approach for Contextual Linear Programming and Inverse Linear Programming 5
Measuring the Impact of Programming Language Distribution 3
Mechanistic Mode Connectivity 4
Memory-Based Dual Gaussian Processes for Sequential Learning 5
Memory-Based Meta-Learning on Non-Stationary Distributions 3
Men Also Do Laundry: Multi-Attribute Bias Amplification 5
Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks 2
Meta Optimal Transport 5
Meta-Learning the Inductive Bias of Simple Neural Circuits 3
Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optimization 5
Meta-learning Parameterized Skills 5
MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL 3
MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks 3
Metagenomic Binning using Connectivity-constrained Variational Autoencoders 4
MetricGAN-OKD: Multi-Metric Optimization of MetricGAN via Online Knowledge Distillation for Speech Enhancement 6
Mimetic Initialization of Self-Attention Layers 2
Minimalistic Predictions to Schedule Jobs with Online Precedence Constraints 1
Minimax estimation of discontinuous optimal transport maps: The semi-discrete case 1
Minimizing Trajectory Curvature of ODE-based Generative Models 3
Minimum Width of Leaky-ReLU Neural Networks for Uniform Universal Approximation 0
Mirror Sinkhorn: Fast Online Optimization on Transport Polytopes 3
Mitigating Memorization of Noisy Labels by Clipping the Model Prediction 4
Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling 5
Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning 4
MixFlows: principled variational inference via mixed flows 5
Mixing Predictions for Online Metric Algorithms 1
Mixture Proportion Estimation Beyond Irreducibility 4
Moccasin: Efficient Tensor Rematerialization for Neural Networks 3
Modality-Agnostic Variational Compression of Implicit Neural Representations 4
Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization 4
Model Transferability with Responsive Decision Subjects 3
Model-Aware Contrastive Learning: Towards Escaping the Dilemmas 6
Model-Bellman Inconsistency for Model-based Offline Reinforcement Learning 6
Model-Free Robust Average-Reward Reinforcement Learning 2
Model-agnostic Measure of Generalization Difficulty 4
Model-based Offline Reinforcement Learning with Count-based Conservatism 4
Model-based Reinforcement Learning with Scalable Composite Policy Gradient Estimators 3
ModelDiff: A Framework for Comparing Learning Algorithms 5
Modeling Dynamic Environments with Scene Graph Memory 5
Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion 3
Moderately Distributional Exploration for Domain Generalization 5
MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation 4
Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions 3
Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps 3
MonoFlow: Rethinking Divergence GANs via the Perspective of Wasserstein Gradient Flows 3
MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Poses 2
Monotonic Location Attention for Length Generalization 4
Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes 2
Motion Question Answering via Modular Motion Programs 5
Mu$^2$SLAM: Multitask, Multilingual Speech and Language Models 3
Multi-Agent Best Arm Identification with Private Communications 3
Multi-Agent Learning from Learners 4
Multi-Environment Pretraining Enables Transfer to Action Limited Datasets 4
Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning 5
Multi-Fidelity Covariance Estimation in the Log-Euclidean Geometry 3
Multi-Layer Neural Networks as Trainable Ladders of Hilbert Spaces 1
Multi-Modal Classifiers for Open-Vocabulary Object Detection 4
Multi-Objective GFlowNets 4
Multi-Objective Population Based Training 6
Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries 4
Multi-Task Differential Privacy Under Distribution Skew 4
Multi-Task Off-Policy Learning from Bandit Feedback 3
Multi-Task Structural Learning using Local Task Similarity induced Neuron Creation and Removal 6
Multi-User Reinforcement Learning with Low Rank Rewards 1
Multi-View Masked World Models for Visual Robotic Manipulation 4
Multi-agent Online Scheduling: MMS Allocations for Indivisible Items 1
Multi-channel Autobidding with Budget and ROI Constraints 1
Multi-class Graph Clustering via Approximated Effective $p$-Resistance 5
Multi-task Hierarchical Adversarial Inverse Reinforcement Learning 4
Multi-task Representation Learning for Pure Exploration in Linear Bandits 2
MultiAdam: Parameter-wise Scale-invariant Optimizer for Multiscale Training of Physics-informed Neural Networks 4
MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation 3
MultiRobustBench: Benchmarking Robustness Against Multiple Attacks 2
Multicalibration as Boosting for Regression 4
Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation 4
Multiplier Bootstrap-based Exploration 3
Multiply Robust Off-policy Evaluation and Learning under Truncation by Death 2
Multisample Flow Matching: Straightening Flows with Minibatch Couplings 3
Muse: Text-To-Image Generation via Masked Generative Transformers 3
MyoDex: A Generalizable Prior for Dexterous Manipulation 2
N$\text{A}^{\text{2}}$Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning 5
NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscation 5
NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation 5
NTK-approximating MLP Fusion for Efficient Language Model Fine-tuning 5
NUNO: A General Framework for Learning Parametric PDEs with Non-Uniform Data 5
Naive imputation implicitly regularizes high-dimensional linear models 1
NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations 3
Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR 1
Near-Optimal $Φ$-Regret Learning in Extensive-Form Games 3
Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime 1
Near-Optimal Cryptographic Hardness of Agnostically Learning Halfspaces and ReLU Regression under Gaussian Marginals 0
Near-Optimal Quantum Coreset Construction Algorithms for Clustering 1
Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints 2
Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path 2
Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes 1
Nearly Optimal Algorithms with Sublinear Computational Complexity for Online Kernel Regression 5
Nearly Optimal Competitive Ratio for Online Allocation Problems with Two-sided Resource Constraints and Finite Requests 1
Nearly-Linear Time and Streaming Algorithms for Outlier-Robust PCA 1
Nearly-Optimal Hierarchical Clustering for Well-Clustered Graphs 6
Nearly-tight Bounds for Deep Kernel Learning 0
NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion 5
Nested Elimination: A Simple Algorithm for Best-Item Identification From Choice-Based Feedback 5
Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization 2
Network Effects in Performative Prediction Games 3
Neural Algorithmic Reasoning with Causal Regularisation 2
Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data 2
Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series 6
Neural Diffusion Processes 5
Neural FIM for learning Fisher information metrics from point cloud data 4
Neural Inverse Operators for Solving PDE Inverse Problems 5
Neural Latent Aligner: Cross-trial Alignment for Learning Representations of Complex, Naturalistic Neural Data 4
Neural Markov Jump Processes 5
Neural Network Accelerated Implicit Filtering: Integrating Neural Network Surrogates With Provably Convergent Derivative Free Optimization Methods 5
Neural Network Approximations of PDEs Beyond Linearity: A Representational Perspective 0
Neural Prediction Errors enable Analogical Visual Reasoning in Human Standard Intelligence Tests 4
Neural Status Registers 3
Neural Stochastic Differential Games for Time-series Analysis 4
Neural Wasserstein Gradient Flows for Discrepancies with Riesz Kernels 4
Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally Coupled Oscillatory Recurrent Neural Networks 4
Neural networks trained with SGD learn distributions of increasing complexity 3
Neural signature kernels as infinite-width-depth-limits of controlled ResNets 3
NeuralSlice: Neural 3D Triangle Mesh Reconstruction via Slicing 4D Tetrahedral Meshes 6
NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition 2
Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal 5
Never mind the metrics---what about the uncertainty? Visualising binary confusion matrix metric distributions to put performance in perspective 3
New metrics and search algorithms for weighted causal DAGs 4
No One Idles: Efficient Heterogeneous Federated Learning with Parallel Edge and Server Computation 4
Node Embedding from Neural Hamiltonian Orbits in Graph Neural Networks 5
Non-autoregressive Conditional Diffusion Models for Time Series Prediction 5
Non-stationary Reinforcement Learning under General Function Approximation 1
Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think 5
Nonlinear Causal Discovery with Latent Confounders 2
Nonparametric Density Estimation under Distribution Drift 0
Nonparametric Extensions of Randomized Response for Private Confidence Sets 2
Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows 4
Nonparametric Iterative Machine Teaching 5
Normalizing Flows for Interventional Density Estimation 6
Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization 6
Not all Strongly Rayleigh Distributions Have Small Probabilistic Generating Circuits 0
Nugget: Neural Agglomerative Embeddings of Text 3
OCD: Learning to Overfit with Conditional Diffusion Models 5
ODS: Test-Time Adaptation in the Presence of Open-World Data Shift 5
OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models 5
Off-Policy Average Reward Actor-Critic with Deterministic Policy Search 4
Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling 3
Offline Learning in Markov Games with General Function Approximation 1
Offline Meta Reinforcement Learning with In-Distribution Online Adaptation 4
Offline Reinforcement Learning with Closed-Form Policy Improvement Operators 6
Omnipredictors for Constrained Optimization 0
On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation 4
On Bridging the Gap between Mean Field and Finite Width Deep Random Multilayer Perceptron with Batch Normalization 3
On Computing Optimal Tree Ensembles 1
On Coresets for Clustering in Small Dimensional Euclidean spaces 1
On Data Manifolds Entailed by Structural Causal Models 2
On Distribution Dependent Sub-Logarithmic Query Time of Learned Indexing 3
On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network 2
On Excess Mass Behavior in Gaussian Mixture Models with Orlicz-Wasserstein Distances 2
On Heterogeneous Treatment Effects in Heterogeneous Causal Graphs 5
On Investigating the Conservative Property of Score-Based Generative Models 5
On Kinetic Optimal Probability Paths for Generative Models 3
On Many-Actions Policy Gradient 4
On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology 3
On Penalty-based Bilevel Gradient Descent Method 5
On Pitfalls of Test-Time Adaptation 5
On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline 3
On Preemption and Learning in Stochastic Scheduling 4
On Provable Copyright Protection for Generative Models 4
On Regularization and Inference with Label Constraints 0
On Sampling with Approximate Transport Maps 4
On Second-Order Scoring Rules for Epistemic Uncertainty Quantification 0
On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation 6
On Uni-Modal Feature Learning in Supervised Multi-Modal Learning 5
On User-Level Private Convex Optimization 1
On the Complexity of Bayesian Generalization 5
On the Connection Between MPNN and Graph Transformer 4
On the Convergence Rate of Gaussianization with Random Rotations 3
On the Convergence of Federated Averaging with Cyclic Client Participation 7
On the Convergence of Gradient Flow on Multi-layer Linear Models 1
On the Convergence of SARSA with Linear Function Approximation 3
On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters 0
On the Effectiveness of Offline RL for Dialogue Response Generation 4
On the Estimation of Gaussian Mixture Copula Models 4
On the Expressive Power of Geometric Graph Neural Networks 2
On the Forward Invariance of Neural ODEs 5
On the Functional Similarity of Robust and Non-Robust Neural Representations 4
On the Generalization of Multi-modal Contrastive Learning 4
On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization 1
On the Global Convergence of Risk-Averse Policy Gradient Methods with Expected Conditional Risk Measures 3
On the Identifiability and Estimation of Causal Location-Scale Noise Models 3
On the Impact of Algorithmic Recourse on Social Segregation 4
On the Impact of Knowledge Distillation for Model Interpretability 7
On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning 6
On the Initialization of Graph Neural Networks 4
On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits 4
On the Occupancy Measure of Non-Markovian Policies in Continuous MDPs 0
On the Optimality of Misspecified Kernel Ridge Regression 2
On the Power of Foundation Models 0
On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness 1
On the Privacy-Robustness-Utility Trilemma in Distributed Learning 3
On the Relationship Between Explanation and Prediction: A Causal View 2
On the Robustness of Randomized Ensembles to Adversarial Perturbations 4
On the Robustness of Text Vectorizers 3
On the Role of Attention in Prompt-tuning 3
On the Statistical Benefits of Temporal Difference Learning 1
On the Stepwise Nature of Self-Supervised Learning 3
On the Training Instability of Shuffling SGD with Batch Normalization 4
On the Within-Group Fairness of Screening Classifiers 6
On the convergence of the MLE as an estimator of the learning rate in the Exp3 algorithm 3
One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale 5
One-Shot Compression of Large Edge-Exchangeable Graphs using Bits-Back Coding 3
One-Shot Federated Conformal Prediction 5
One-Step Estimator for Permuted Sparse Recovery 3
One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill 4
One-sided Matrix Completion from Two Observations Per Row 3
One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training 5
Online Learning in Stackelberg Games with an Omniscient Follower 1
Online Learning with Feedback Graphs: The True Shape of Regret 1
Online Local Differential Private Quantile Inference via Self-normalization 3
Online Mechanism Design for Information Acquisition 1
Online Nonstochastic Control with Adversarial and Static Constraints 2
Online Platt Scaling with Calibeating 5
Online Prototype Alignment for Few-shot Policy Transfer 4
Online Restless Bandits with Unobserved States 2
Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization 5
Open-Vocabulary Universal Image Segmentation with MaskCLIP 6
OpenFE: Automated Feature Generation with Expert-level Performance 6
Opponent-Limited Online Search for Imperfect Information Games 3
Optimal Arms Identification with Knapsacks 3
Optimal Convergence Rates for Agnostic Nyström Kernel Learning 0
Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning 3
Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs 1
Optimal LP Rounding and Linear-Time Approximation Algorithms for Clustering Edge-Colored Hypergraphs 4
Optimal No-Regret Learning for One-Sided Lipschitz Functions 1
Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Bandits 2
Optimal Rates and Efficient Algorithms for Online Bayesian Persuasion 1
Optimal Sets and Solution Paths of ReLU Networks 6
Optimal Shrinkage for Distributed Second-Order Optimization 5
Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion 1
Optimal randomized multilevel Monte Carlo for repeatedly nested expectations 3
Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits 2
Optimally-weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference 5
Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization 1
Optimistic Planning by Regularized Dynamic Programming 1
Optimization for Amortized Inverse Problems 3
Optimizing DDPM Sampling with Shortcut Fine-Tuning 5
Optimizing Hyperparameters with Conformal Quantile Regression 6
Optimizing Mode Connectivity for Class Incremental Learning 6
Optimizing NOTEARS Objectives via Topological Swaps 3
Optimizing the Collaboration Structure in Cross-Silo Federated Learning 4
Oracles & Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learning 5
Orthogonality-Enforced Latent Space in Autoencoders: An Approach to Learning Disentangled Representations 5
Oscillation-free Quantization for Low-bit Vision Transformers 5
Out-of-Distribution Generalization of Federated Learning via Implicit Invariant Relationships 5
Out-of-Domain Robustness via Targeted Augmentations 5
Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation 4
Over-parametrization via Lifting for Low-rank Matrix Sensing: Conversion of Spurious Solutions to Strict Saddle Points 2
Overcoming Simplicity Bias in Deep Networks using a Feature Sieve 5
PAC Generalization via Invariant Representations 2
PAC Prediction Sets for Large Language Models of Code 4
PAC-Bayesian Generalization Bounds for Adversarial Generative Models 2
PAC-Bayesian Offline Contextual Bandits With Guarantees 3
PAL: Program-aided Language Models 4
PASTA: Pessimistic Assortment Optimization 2
PCA-based Multi-Task Learning: a Random Matrix Approach 5
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models 5
PFNs4BO: In-Context Learning for Bayesian Optimization 6
PINA: Leveraging Side Information in eXtreme Multi-label Classification via Predicted Instance Neighborhood Aggregation 5
PLay: Parametrically Conditioned Layout Generation using Latent Diffusion 3
POUF: Prompt-Oriented Unsupervised Fine-tuning for Large Pre-trained Models 6
PPG Reloaded: An Empirical Study on What Matters in Phasic Policy Gradient 4
PWSHAP: A Path-Wise Explanation Model for Targeted Variables 4
PaLM-E: An Embodied Multimodal Language Model 2
Paging with Succinct Predictions 1
Pairwise Ranking Losses of Click-Through Rates Prediction for Welfare Maximization in Ad Auctions 3
Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation 5
Parallel Neurosymbolic Integration with Concordia 7
Parallel Online Clustering of Bandits via Hedonic Game 3
Parameter-Level Soft-Masking for Continual Learning 5
Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models 5
Pareto Regret Analyses in Multi-objective Multi-armed Bandit 1
Partial Optimality in Cubic Correlation Clustering 4
Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing 3
Patch-level Contrastive Learning via Positional Query for Visual Pre-training 4
Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks 5
Path Neural Networks: Expressive and Accurate Graph Neural Networks 5
Performative Recommendation: Diversifying Content via Strategic Incentives 5
Performative Reinforcement Learning 5
Personalized Federated Learning under Mixture of Distributions 7
Personalized Federated Learning with Inferred Collaboration Graphs 5
Personalized Subgraph Federated Learning 6
Perturbation Analysis of Neural Collapse 2
Phase Transitions in the Detection of Correlated Databases 0
Phase-aware Adversarial Defense for Improving Adversarial Robustness 4
Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding 5
PixelAsParam: A Gradient View on Diffusion Sampling with Guidance 5
Poisoning Generative Replay in Continual Learning to Promote Forgetting 4
Poisoning Language Models During Instruction Tuning 4
Polarity Is All You Need to Learn and Transfer Faster 6
Policy Contrastive Imitation Learning 2
Policy Gradient in Robust MDPs with Global Convergence Guarantee 6
Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games 1
Policy Regularization with Dataset Constraint for Offline Reinforcement Learning 6
Polyhedral Complex Extraction from ReLU Networks using Edge Subdivision 3
Polynomial Preconditioning for Gradient Methods 3
Polynomial Time and Private Learning of Unbounded Gaussian Mixture Models 1
Posterior Sampling for Deep Reinforcement Learning 5
Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference 2
Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute 2
Pre-training for Speech Translation: CTC Meets Optimal Transport 5
PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search 5
Predictable MDP Abstraction for Unsupervised Model-Based RL 5
Predicting Ordinary Differential Equations with Transformers 4
Predicting Rare Events by Shrinking Towards Proportional Odds 6
Predictive Flows for Faster Ford-Fulkerson 5
Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning 5
Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems 5
Pretraining Language Models with Human Preferences 4
Pricing Experimental Design: Causal Effect, Expected Revenue and Tail Risk 1
Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems 2
Principled Acceleration of Iterative Numerical Methods Using Machine Learning 3
Principled Offline RL in the Presence of Rich Exogenous Information 2
Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons 1
Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design 3
Private Federated Learning with Autotuned Compression 4
Private Statistical Estimation of Many Quantiles 1
Probabilistic Attention-to-Influence Neural Models for Event Sequences 5
Probabilistic Categorical Adversarial Attack and Adversarial Training 4
Probabilistic Concept Bottleneck Models 5
Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs 6
Probabilistic Imputation for Time-series Classification with Missing Data 2
Probabilistic Unrolling: Scalable, Inverse-Free Maximum Likelihood Estimation for Latent Gaussian Models 6
Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits 2
Progressive Purification for Instance-Dependent Partial Label Learning 5
Projected Tensor Power Method for Hypergraph Community Recovery 4
Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning 4
PromptBoosting: Black-Box Text Classification with Ten Forward Passes 5
Prompting Large Language Model for Machine Translation: A Case Study 5
Propensity Matters: Measuring and Enhancing Balancing for Recommendation 2
Proper Losses for Discrete Generative Models 1
Proper Scoring Rules for Survival Analysis 6
Properties of the Mallows Model Depending on the Number of Alternatives: A Warning for an Experimentalist 3
ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts 5
Protecting Language Generation Models via Invisible Watermarking 6
Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning 4
Prototype-oriented unsupervised anomaly detection for multivariate time series 5
Provable Benefit of Mixup for Finding Optimal Decision Boundaries 2
Provable Data Subset Selection For Efficient Neural Networks Training 5
Provable Dynamic Fusion for Low-Quality Multimodal Data 5
Provable Multi-instance Deep AUC Maximization with Stochastic Pooling 5
Provable Reset-free Reinforcement Learning by No-Regret Reduction 1
Provably Convergent Schrödinger Bridge with Applications to Probabilistic Time Series Imputation 4
Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources 2
Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP 4
Provably Invariant Learning without Domain Information 5
Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup 4
Provably Learning Object-Centric Representations 4
Provably and Practically Efficient Neural Contextual Bandits 4
Proximal Causal Learning of Conditional Average Treatment Effects 4
Pruning via Sparsity-indexed ODE: a Continuous Sparsity Viewpoint 4
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling 5
Q-Flow: Generative Modeling for Differential Equations of Open Quantum Dynamics with Normalizing Flows 2
Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL 3
QAS-Bench: Rethinking Quantum Architecture Search and A Benchmark 5
QASA: Advanced Question Answering on Scientific Articles 3
Quantifying Human Priors over Social and Navigation Networks 2
Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs 7
Quantifying the Variability Collapse of Neural Networks 3
Quantile Credit Assignment 2
Quantitative Universal Approximation Bounds for Deep Belief Networks 0
Quantized Distributed Training of Large Models with Convergence Guarantees 5
Quantum 3D Graph Learning with Applications to Molecule Embedding 4
Quantum Lower Bounds for Finding Stationary Points of Nonconvex Functions 0
Quantum Policy Gradient Algorithm with Optimized Action Decoding 4
Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation 3
Quantum Speedups for Zero-Sum Games via Improved Dynamic Gibbs Sampling 1
QuantumDARTS: Differentiable Quantum Architecture Search for Variational Quantum Algorithms 5
R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents 4
RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution 5
RGE: A Repulsive Graph Rectification for Node Classification via Influence 5
RLEG: Vision-Language Representation Learning with Diffusion-based Embedding Generation 3
RLSbench: Domain Adaptation Under Relaxed Label Shift 6
RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents 4
RSC: Accelerate Graph Neural Networks Training via Randomized Sparse Computations 7
Raising the Cost of Malicious AI-Powered Image Editing 5
Random Classification Noise does not defeat All Convex Potential Boosters Irrespective of Model Choice 2
Random Grid Neural Processes for Parametric Partial Differential Equations 3
Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption 5
Random Shuffle Transformer for Image Restoration 6
Random Teachers are Good Teachers 4
Randomized Gaussian Process Upper Confidence Bound with Tighter Bayesian Regret Bounds 3
Randomized Schur Complement Views for Graph Contrastive Learning 7
RankMe: Assessing the Downstream Performance of Pretrained Self-Supervised Representations by Their Rank 4
ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval 6
ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs 3
Reachability-Aware Laplacian Representation in Reinforcement Learning 2
Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Quality 3
Recasting Self-Attention with Holographic Reduced Representations 6
Reconstructive Neuron Pruning for Backdoor Defense 5
Recovering Top-Two Answers and Confusion Probability in Multi-Choice Crowdsourcing 6
Recovery Bounds on Class-Based Optimal Transport: A Sum-of-Norms Regularization Framework 3
Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC 4
Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs 4
Refined Regret for Adversarial MDPs with Linear Function Approximation 1
Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models 5
Reflected Diffusion Models 4
Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts 3
Regression with Label Permutation in Generalized Linear Model 2
Regression with Sensor Data Containing Incomplete Observations 5
Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty Equivalents 2
Regret Minimization and Convergence to Equilibria in General-sum Markov Games 1
Regret-Minimizing Double Oracle for Extensive-Form Games 4
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice 4
Regularization-free Diffeomorphic Temporal Alignment Nets 7
Regularizing Towards Soft Equivariance Under Mixed Symmetries 4
Reinforcement Learning Can Be More Efficient with Multiple Rewards 1
Reinforcement Learning from Passive Data via Latent Intentions 5
Reinforcement Learning in Low-rank MDPs with Density Features 1
Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space 3
Reinforcement Learning with History Dependent Dynamic Contexts 3
Relevant Walk Search for Explaining Graph Neural Networks 6
Reliable Measures of Spread in High Dimensional Latent Spaces 1
Reparameterized Policy Learning for Multimodal Trajectory Optimization 4
Repository-Level Prompt Generation for Large Language Models of Code 6
Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL 4
Representation-Driven Reinforcement Learning 3
Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition 2
Representer Point Selection for Explaining Regularized High-dimensional Models 4
Reprogramming Pretrained Language Models for Antibody Sequence Infilling 5
Restoration based Generative Models 5
Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-type Samplers 0
Resurrecting Recurrent Neural Networks for Long Sequences 6
Rethink DARTS Search Space and Renovate a New Benchmark 6
Rethinking Backdoor Attacks 4
Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching 5
Rethinking Visual Reconstruction: Experience-Based Content Completion Guided by Visual Cues 2
Rethinking Warm-Starts with Predictions: Learning Predictions Close to Sets of Optimal Solutions for Faster $\text{L}$-/$\text{L}^\natural$-Convex Function Minimization 3
Rethinking Weak Supervision in Helping Contrastive Learning 4
Retrieval-Augmented Multimodal Language Modeling 4
Retrosynthetic Planning with Dual Value Networks 3
Returning The Favour: When Regression Benefits From Probabilistic Causal Knowledge 5
Revisiting Bellman Errors for Offline Model Selection 7
Revisiting Data-Free Knowledge Distillation with Poisoned Teachers 4
Revisiting Discriminative vs. Generative Classifiers: Theory and Implications 5
Revisiting Domain Randomization via Relaxed State-Adversarial Policy Optimization 4
Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees 2
Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature 7
Revisiting Pseudo-Label for Single-Positive Multi-Label Learning 4
Revisiting Sampling for Combinatorial Optimization 4
Revisiting Simple Regret: Fast Rates for Returning a Good Arm 4
Revisiting Structured Variational Autoencoders 3
Revisiting Weighted Aggregation in Federated Learning with Neural Networks 5
Revisiting the Linear-Programming Framework for Offline RL with General Function Approximation 0
Reward-Mixing MDPs with Few Latent Contexts are Learnable 1
Rigid Body Flows for Sampling Molecular Crystal Structures 3
Robust Budget Pacing with a Single Sample 1
Robust Camera Pose Refinement for Multi-Resolution Hash Encoding 2
Robust Collaborative Learning with Linear Gradient Overhead 6
Robust Consensus in Ranking Data Analysis: Definitions, Properties and Computational Issues 4
Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees 4
Robust Explanation for Free or At the Cost of Faithfulness 2
Robust Non-Linear Feedback Coding via Power-Constrained Deep Learning 3
Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks 5
Robust Perception through Equivariance 5
Robust Satisficing MDPs 6
Robust Situational Reinforcement Learning in Face of Context Disturbances 1
Robust Speech Recognition via Large-Scale Weak Supervision 4
Robust Subtask Learning for Compositional Generalization 3
Robust Weak Supervision with Variational Auto-Encoders 2
Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights? 3
Robust and Scalable Bayesian Online Changepoint Detection 5
Robust and private stochastic linear bandits 1
Robustly Learning a Single Neuron via Sharpness 2
Robustness in Multimodal Learning under Train-Test Modality Mismatch 3
Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch 4
Rotation and Translation Invariant Representation Learning with Implicit Neural Representations 4
Run-off Election: Improved Provable Defense against Data Poisoning Attacks 5
SAAL: Sharpness-Aware Active Learning 4
SAM operates far from home: eigenvalue regularization as a dynamical phenomenon 2
SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation 3
SE(3) diffusion model with application to protein backbone generation 5
SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning 5
SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance 0
SGD with Large Step Sizes Learns Sparse Features 3
SLAMB: Accelerated Large Batch Training with Sparse Communication 5
SMURF-THP: Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process 3
SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning 4
SOM-CPC: Unsupervised Contrastive Learning with Self-Organizing Maps for Structured Representations of High-Rate Time Series 5
SRATTA: Sample Re-ATTribution Attack of Secure Aggregation in Federated Learning. 4
STEERING : Stein Information Directed Exploration for Model-Based Reinforcement Learning 3
STEP: Learning N:M Structured Sparsity Masks from Scratch with Precondition 4
SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient 6
Safe Offline Reinforcement Learning with Real-Time Budget Constraints 4
Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models 3
Sample Complexity Bounds for Learning High-dimensional Simplices in Noisy Regimes 0
Sample Complexity of Probability Divergences under Group Symmetry 1
Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimation 4
Sampling-Based Accuracy Testing of Posterior Estimators for General Inference 4
Sampling-based Nyström Approximation and Kernel Quadrature 3
Scalable Adaptive Computation for Iterative Generation 4
Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation 3
Scalable Safe Policy Improvement via Monte Carlo Tree Search 5
Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation 6
Scaling Laws for Generative Mixed-Modal Language Models 4
Scaling Laws for Multilingual Neural Machine Translation 2
Scaling Laws for Reward Model Overoptimization 3
Scaling Spherical CNNs 5
Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory 4
Scaling Vision Transformers to 22 Billion Parameters 4
Scaling of Class-wise Training Losses for Post-hoc Calibration 5
Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data 0
SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models 6
Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning 6
Second-Order Optimization with Lazy Hessians 3
Second-order regression models exhibit progressive sharpening to the edge of stability 2
Secure Federated Correlation Test and Entropy Estimation 5
SeedGNN: Graph Neural Network for Supervised Seeded Graph Matching 4
SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation 5
Self-Attention Amortized Distributional Projection Optimization for Sliced Wasserstein Point-Cloud Reconstruction 6
Self-Interpretable Time Series Prediction with Counterfactual Explanations 3
Self-Repellent Random Walks on General Graphs - Achieving Minimal Sampling Variance via Nonlinear Markov Chains 2
Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations 3
Self-supervised learning of Split Invariant Equivariant representations 5
SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification 5
Semi Bandit dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees. 3
Semi-Autoregressive Energy Flows: Exploring Likelihood-Free Training of Normalizing Flows 5
Semi-Dual Unbalanced Quadratic Optimal Transport: fast statistical rates and convergent algorithm. 2
Semi-Offline Reinforcement Learning for Optimized Text Generation 5
Semi-Parametric Contextual Pricing Algorithm using Cox Proportional Hazards Model 3
Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories 5
Semiparametrically Efficient Off-Policy Evaluation in Linear Markov Decision Processes 3
Sequence Modeling with Multiresolution Convolutional Memory 5
Sequential Changepoint Detection via Backward Confidence Sequences 2
Sequential Counterfactual Risk Minimization 5
Sequential Kernelized Independence Testing 3
Sequential Monte Carlo Learning for Time Series Structure Discovery 5
Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series 5
Sequential Predictive Conformal Inference for Time Series 5
Sequential Strategic Screening 0
Sequential Underspecified Instrument Selection for Cause-Effect Estimation 3
Set-membership Belief State-based Reinforcement Learning for POMDPs 2
Settling the Reward Hypothesis 1
Shape-Guided Dual-Memory Learning for 3D Anomaly Detection 4
Shapley Based Residual Decomposition for Instance Analysis 4
Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments 1
Sharper Bounds for $\ell_p$ Sensitivity Sampling 0
Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distances 5
Shiftable Context: Addressing Training-Inference Context Mismatch in Simultaneous Speech Translation 5
Short-lived High-volume Bandits 2
Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search 5
Simple Disentanglement of Style and Content in Visual Representations 5
Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning 1
Simple Hardware-Efficient Long Convolutions for Sequence Modeling 6
Simple and Fast Group Robustness by Automatic Feature Reweighting 6
Simplex Random Features 6
Simplified Temporal Consistency Reinforcement Learning 4
Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning 4
SinDDM: A Single Image Denoising Diffusion Model 4
SinFusion: Training Diffusion Models on a Single Image or Video 4
Single Point-Based Distributed Zeroth-Order Optimization with a Non-Convex Stochastic Objective Function 3
Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition 4
Sketch-Flip-Merge: Mergeable Sketches for Private Distinct Counting 2
Sketched Ridgeless Linear Regression: The Role of Downsampling 4
Sketching Meets Differential Privacy: Fast Algorithm for Dynamic Kronecker Projection Maintenance 1
Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability 1
Sliced-Wasserstein on Symmetric Positive Definite Matrices for M/EEG Signals 6
Slot-VAE: Object-Centric Scene Generation with Slot Attention 2
SlotGAT: Slot-based Message Passing for Heterogeneous Graphs 7
Smart Initial Basis Selection for Linear Programs 7
Smooth Non-stationary Bandits 2
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models 5
Social learning spontaneously emerges by searching optimal heuristics with deep reinforcement learning 4
Solving High-Dimensional PDEs with Latent Spectral Models 4
Solving Linear Programs with Fast Online Learning Algorithms 4
SpENCNN: Orchestrating Encoding and Sparsity for Fast Homomorphically Encrypted Neural Network Inference 6
Sparse Learning of Dynamical Systems in RKHS: An Operator-Theoretic Approach 2
SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot 6
SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks at the Edge 5
Spatial Implicit Neural Representations for Global-Scale Species Mapping 5
Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation 6
Special Properties of Gradient Descent with Large Learning Rates 3
Specializing Smaller Language Models towards Multi-Step Reasoning 4
Speed-Oblivious Online Scheduling: Knowing (Precise) Speeds is not Necessary 4
SpeedDETR: Speed-aware Transformers for End-to-end Object Detection 5
Speeding Up Bellman Ford via Minimum Violation Permutations 3
Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere 6
Spherical Inducing Features for Orthogonally-Decoupled Gaussian Processes 5
SpotEM: Efficient Video Search for Episodic Memory 4
Spurious Valleys and Clustering Behavior of Neural Networks 1
Stabilizing GANs’ Training with Brownian Motion Controller 4
Stabilizing Transformer Training by Preventing Attention Entropy Collapse 6
Stable Estimation of Heterogeneous Treatment Effects 7
Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learning 3
State and parameter learning with PARIS particle Gibbs 4
Statistical Foundations of Prior-Data Fitted Networks 3
Statistical Indistinguishability of Learning Algorithms 1
Statistical Inference and A/B Testing for First-Price Pacing Equilibria 2
Statistical Inference on Multi-armed Bandits with Delayed Feedback 2
Statistical Learning under Heterogeneous Distribution Shift 2
Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning 4
Stochastic Gradient Descent under Markovian Sampling Schemes 2
Stochastic Gradient Descent-Induced Drift of Representation in a Two-Layer Neural Network 1
Stochastic Gradient Succeeds for Bandits 2
Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels 5
Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies 3
Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks 4
Strategic Classification with Unknown User Manipulations 1
Stratified Adversarial Robustness with Rejection 6
Streaming Active Learning with Deep Neural Networks 4
Streaming Submodular Maximization with Differential Privacy 5
StriderNet: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes 6
Structural Re-weighting Improves Graph Domain Adaptation 5
Structure Learning of Latent Factors via Clique Search on Correlation Thresholded Graphs 5
Structure-informed Language Models Are Protein Designers 5
Structured Cooperative Learning with Graphical Model Priors 5
StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis 4
Subequivariant Graph Reinforcement Learning in 3D Environments 3
Submodular Order Functions and Assortment Optimization 1
Subsample Ridge Ensembles: Equivalences and Generalized Cross-Validation 3
Subset Selection Based On Multiple Rankings in the Presence of Bias: Effectiveness of Fairness Constraints for Multiwinner Voting Score Functions 4
Subset-Based Instance Optimality in Private Estimation 1
Superhuman Fairness 4
Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimization 5
Supported Trust Region Optimization for Offline Reinforcement Learning 4
SurCo: Learning Linear SURrogates for COmbinatorial Nonlinear Optimization Problems 4
SurProGenes: Survival Risk-Ordered Representation of Cancer Patients and Genes for the Identification of Prognostic Genes 4
Surface Snapping Optimization Layer for Single Image Object Shape Reconstruction 2
Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning 5
Surrogate Module Learning: Reduce the Gradient Error Accumulation in Training Spiking Neural Networks 5
Symmetry-Aware Robot Design with Structured Subgroups 5
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning 4
Synthetic Data, Real Errors: How (Not) to Publish and Use Synthetic Data 5
Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models 3
Synthetic data for model selection 3
System Identification of Neural Systems: If We Got It Right, Would We Know? 4
TAN Without a Burn: Scaling Laws of DP-SGD 4
TGRL: An Algorithm for Teacher Guided Reinforcement Learning 3
TIDE: Time Derivative Diffusion for Deep Learning on Graphs 5
TIPS: Topologically Important Path Sampling for Anytime Neural Networks 4
TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation 6
TRAK: Attributing Model Behavior at Scale 6
TabDDPM: Modelling Tabular Data with Diffusion Models 6
TabLeak: Tabular Data Leakage in Federated Learning 5
Taming graph kernels with random features 3
Target-Aware Generative Augmentations for Single-Shot Adaptation 4
Target-based Surrogates for Stochastic Optimization 5
Task-Specific Skill Localization in Fine-tuned Language Models 4
Task-specific experimental design for treatment effect estimation 5
Taxonomy-Structured Domain Adaptation 5
Team Belief DAG: Generalizing the Sequence Form to Team Games for Fast Computation of Correlated Team Max-Min Equilibria via Regret Minimization 3
Temporal Label Smoothing for Early Event Prediction 6
Temporally Consistent Transformers for Video Generation 3
Tensor Decompositions Meet Control Theory: Learning General Mixtures of Linear Dynamical Systems 1
Tensor Gaussian Process with Contraction for Multi-Channel Imaging Analysis 3
Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalization 4
Test-time Adaptation with Slot-Centric Models 4
Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise 5
Text-To-4D Dynamic Scene Generation 4
Text-To-Concept (and Back) via Cross-Model Alignment 3
The Acquisition of Physical Knowledge in Generative Neural Networks 3
The Benefits of Mixup for Feature Learning 2
The Benefits of Model-Based Generalization in Reinforcement Learning 2
The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond 2
The Catalog Problem: Clustering and Ordering Variable-Sized Sets 7
The Computational Complexity of Concise Hypersphere Classification 0
The Dormant Neuron Phenomenon in Deep Reinforcement Learning 4
The Edge of Orthogonality: A Simple View of What Makes BYOL Tick 5
The Fast Johnson-Lindenstrauss Transform Is Even Faster 0
The Flan Collection: Designing Data and Methods for Effective Instruction Tuning 4
The Hessian perspective into the Nature of Convolutional Neural Networks 3
The Ideal Continual Learner: An Agent That Never Forgets 0
The Impact of Exploration on Convergence and Performance of Multi-Agent Q-Learning Dynamics 1
The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent 1
The Monge Gap: A Regularizer to Learn All Transport Maps 4
The Numerical Stability of Hyperbolic Representation Learning 3
The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation 0
The Persistent Laplacian for Data Science: Evaluating Higher-Order Persistent Spectral Representations of Data 4
The Power of Learned Locally Linear Models for Nonlinear Policy Optimization 2
The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing 2
The Power of Uniform Sampling for k-Median 2
The Price of Differential Privacy under Continual Observation 1
The Regret of Exploration and the Control of Bad Episodes in Reinforcement Learning 2
The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning 5
The SSL Interplay: Augmentations, Inductive Bias, and Generalization 2
The Saddle-Point Method in Differential Privacy 3
The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation 3
The Statistical Scope of Multicalibration 1
The Test of Tests: A Framework for Differentially Private Hypothesis Testing 3
The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning 3
The Unreasonable Effectiveness of Few-shot Learning for Machine Translation 4
The Value of Out-of-Distribution Data 4
The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms 4
The Wisdom of Hindsight Makes Language Models Better Instruction Followers 4
The case for 4-bit precision: k-bit Inference Scaling Laws 3
Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables 0
Theoretical Bounds on the Network Community Profile from Low-rank Semi-definite Programming 4
Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting 4
Theory on Forgetting and Generalization of Continual Learning 2
Thompson Sampling for High-Dimensional Sparse Linear Contextual Bandits 4
Thompson Sampling with Diffusion Generative Prior 5
Thompson Sampling with Less Exploration is Fast and Optimal 3
Tied-Augment: Controlling Representation Similarity Improves Data Augmentation 6
Tight Certification of Adversarially Trained Neural Networks via Nonconvex Low-Rank Semidefinite Relaxations 5
Tight Data Access Bounds for Private Top-$k$ Selection 1
Tight Regret Bounds for Single-pass Streaming Multi-armed Bandits 4
Tight and fast generalization error bound of graph embedding in metric space 0
Tighter Analysis for ProxSkip 2
Tighter Bounds on the Expressivity of Transformer Encoders 0
Tighter Information-Theoretic Generalization Bounds from Supersamples 3
Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond 1
Tilted Sparse Additive Models 4
Topological Point Cloud Clustering 3
Topological Singularity Detection at Multiple Scales 4
Topologically Faithful Image Segmentation via Induced Matching of Persistence Barcodes 6
Total Variation Graph Neural Networks 5
Toward Efficient Gradient-Based Value Estimation 3
Toward Large Kernel Models 5
Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering 5
Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten 4
Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models 6
Towards Constituting Mathematical Structures for Learning to Optimize 5
Towards Controlled Data Augmentations for Active Learning 4
Towards Deep Attention in Graph Neural Networks: Problems and Remedies 4
Towards Explaining Distribution Shifts 4
Towards Learning Geometric Eigen-Lengths Crucial for Fitting Tasks 3
Towards Omni-generalizable Neural Methods for Vehicle Routing Problems 7
Towards Practical Preferential Bayesian Optimization with Skew Gaussian Processes 4
Towards Quantum Machine Learning for Constrained Combinatorial Optimization: a Quantum QAP Solver 2
Towards Reliable Neural Specifications 4
Towards Robust Graph Incremental Learning on Evolving Graphs 6
Towards Robust and Safe Reinforcement Learning with Benign Off-policy Data 3
Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks 6
Towards Sustainable Learning: Coresets for Data-efficient Deep Learning 5
Towards Theoretical Understanding of Inverse Reinforcement Learning 1
Towards Trustworthy Explanation: On Causal Rationalization 6
Towards Unbiased Training in Federated Open-world Semi-supervised Learning 5
Towards Understanding Ensemble Distillation in Federated Learning 3
Towards Understanding Generalization of Graph Neural Networks 3
Towards Understanding Generalization of Macro-AUC in Multi-label Learning 5
Towards Understanding and Improving GFlowNet Training 3
Towards Understanding and Reducing Graph Structural Noise for GNNs 5
Towards a Persistence Diagram that is Robust to Noise and Varied Densities 5
Towards a better understanding of representation dynamics under TD-learning 3
Towards credible visual model interpretation with path attribution 5
Tractable Control for Autoregressive Language Generation 6
Trading-Off Payments and Accuracy in Online Classification with Paid Stochastic Experts 2
Trainability, Expressivity and Interpretability in Gated Neural ODEs 4
Training Deep Surrogate Models with Large Scale Online Learning 5
Training Normalizing Flows from Dependent Data 6
Training-Free Neural Active Learning with Initialization-Robustness Guarantees 4
Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning 3
Transcendental Idealism of Planner: Evaluating Perception from Planning Perspective for Autonomous Driving 5
Transformed Distribution Matching for Missing Value Imputation 5
Transformer-based Stagewise Decomposition for Large-Scale Multistage Stochastic Optimization 4
Transformers Learn In-Context by Gradient Descent 3
Transformers Meet Directed Graphs 6
Transformers as Algorithms: Generalization and Stability in In-context Learning 2
Trapdoor Normalization with Irreversible Ownership Verification 4
Traversing Between Modes in Function Space for Fast Ensembling 7
Trompt: Towards a Better Deep Neural Network for Tabular Data 2
Truncating Trajectories in Monte Carlo Reinforcement Learning 4
Trustworthy Policy Learning under the Counterfactual No-Harm Criterion 3
Tuning Computer Vision Models With Task Rewards 5
Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning 6
Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy 3
Two-Scale Gradient Descent Ascent Dynamics Finds Mixed Nash Equilibria of Continuous Games: A Mean-Field Perspective 0
UMD: Unsupervised Model Detection for X2X Backdoor Attacks 6
UPSCALE: Unconstrained Channel Pruning 6
UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers 4
Uncertain Evidence in Probabilistic Models and Stochastic Simulators 2
Uncertainty Estimation by Fisher Information-based Evidential Deep Learning 5
Uncertainty Estimation for Molecules: Desiderata and Methods 4
Unconstrained Online Learning with Unbounded Losses 1
Uncovering Adversarial Risks of Test-Time Adaptation 4
Under-Counted Tensor Completion with Neural Incorporation of Attributes 5
Understand and Modularize Generator Optimization in ELECTRA-style Pretraining 5
Understanding Backdoor Attacks through the Adaptability Hypothesis 4
Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias 5
Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing 1
Understanding Int4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases 6
Understanding Oversquashing in GNNs through the Lens of Effective Resistance 4
Understanding Plasticity in Neural Networks 2
Understanding Self-Distillation in the Presence of Label Noise 3
Understanding Self-Predictive Learning for Reinforcement Learning 4
Understanding and Defending Patched-based Adversarial Attacks for Vision Transformer 4
Understanding and Generalizing Contrastive Learning from the Inverse Optimal Transport Perspective 5
Understanding the Complexity Gains of Single-Task RL with a Curriculum 3
Understanding the Distillation Process from Deep Generative Models to Tractable Probabilistic Circuits 4
Understanding the Impact of Adversarial Robustness on Accuracy Disparity 5
Understanding the Role of Feedback in Online Learning with Switching Costs 1
Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data 3
Unifying Molecular and Textual Representations via Multi-task Language Modelling 4
Unifying Nesterov’s Accelerated Gradient Methods for Convex and Strongly Convex Objective Functions 2
Unit Scaling: Out-of-the-Box Low-Precision Training 5
Universal Morphology Control via Contextual Modulation 3
Universal Physics-Informed Neural Networks: Symbolic Differential Operator Discovery with Sparse Data 1
Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability 7
Unlocking Slot Attention by Changing Optimal Transport Costs 4
Unscented Autoencoder 5
Unsupervised Out-of-Distribution Detection with Diffusion Inpainting 4
Unsupervised Skill Discovery for Learning Shared Structures across Changing Environments 3
Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features 4
Unveiling the Latent Space Geometry of Push-Forward Generative Models 4
User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems 1
User-level Private Stochastic Convex Optimization with Optimal Rates 1
Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies 3
Using Perturbation to Improve Goodness-of-Fit Tests based on Kernelized Stein Discrepancy 3
VA-learning as a more efficient alternative to Q-learning 3
VIMA: Robot Manipulation with Multimodal Prompts 7
Variance Control for Distributional Reinforcement Learning 4
Variational Autoencoding Neural Operators 3
Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills 3
Variational Mixture of HyperGenerators for Learning Distributions over Functions 5
Variational Open-Domain Question Answering 6
Variational Sparse Inverse Cholesky Approximation for Latent Gaussian Processes via Double Kullback-Leibler Minimization 4
Vector Quantized Wasserstein Auto-Encoder 4
Vector-Valued Control Variates 4
VectorMapNet: End-to-end Vectorized HD Map Learning 5
Vertical Federated Graph Neural Network for Recommender System 6
Von Mises Mixture Distributions for Molecular Conformation Generation 4
WL meet VC 4
Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap 1
Wasserstein Barycenter Matching for Graph Size Generalization of Message Passing Neural Networks 7
Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes 4
Weakly Supervised Regression with Interval Targets 3
Weighted Flow Diffusion for Local Graph Clustering with Node Attributes: an Algorithm and Statistical Guarantees 4
Weighted Sampling without Replacement for Deep Top-$k$ Classification 4
Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality 2
What Can Be Learnt With Wide Convolutional Neural Networks? 5
What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings 6
What can online reinforcement learning with function approximation benefit from general coverage conditions? 1
What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective 2
What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL? 5
When Personalization Harms Performance: Reconsidering the Use of Group Attributes in Prediction 3
When Sparsity Meets Contrastive Models: Less Graph Data Can Bring Better Class-Balanced Representations 4
When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis 4
When do Minimax-fair Learning and Empirical Risk Minimization Coincide? 4
When does Privileged information Explain Away Label Noise? 4
When is Realizability Sufficient for Off-Policy Reinforcement Learning? 0
Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression 2
Which Invariance Should We Transfer? A Causal Minimax Learning Approach 7
Which Tricks are Important for Learning to Rank? 3
Which is Better for Learning with Noisy Labels: The Semi-supervised Method or Modeling Label Noise? 5
Who Needs to Know? Minimal Knowledge for Optimal Coordination 3
Whose Opinions Do Language Models Reflect? 3
Why Is Public Pretraining Necessary for Private Model Training? 3
Why Random Pruning Is All We Need to Start Sparse 5
Why Target Networks Stabilise Temporal Difference Methods 2
Why do Nearest Neighbor Language Models Work? 4
Why does Throwing Away Data Improve Worst-Group Error? 3
Width and Depth Limits Commute in Residual Networks 1
Wrapped Cauchy Distributed Angular Softmax for Long-Tailed Visual Recognition 4
X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion 4
XTab: Cross-table Pretraining for Tabular Transformers 5
dugMatting: Decomposed-Uncertainty-Guided Matting 5
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video 5
simple diffusion: End-to-end diffusion for high resolution images 4
spred: Solving L1 Penalty with SGD 5