# Downloads 2023

Number of events: 3664

- $H$-Consistency Bounds: Characterization and Extensions
- $k$-Means Clustering with Distance-Based Privacy
- $L_2$-Uniform Stability of Randomized Learning Algorithms: Sharper Generalization Bounds and Confidence Boosting
- $\mathbf{\mathbb{E}^{FWI}}$: Multiparameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties
- $\mathcal{M}^4$: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities and Models
- $p$-Poisson surface reconstruction in curl-free flow from point clouds
- $p$-value Adjustment for Monotonous, Unbiased, and Fast Clustering Comparison
- $S^3$: Increasing GPU Utilization during Generative Inference for Higher Throughput
- $SE(3)$ Equivariant Convolution and Transformer in Ray Space
- $\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning
- $\texttt{TACO}$: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
- $\varepsilon$-fractional core stability in Hedonic Games.
- 2Direction: Theoretically Faster Distributed Training with Bidirectional Communication Compression
- 3D-Aware Visual Question Answering about Parts, Poses and Occlusions
- 3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection
- 3D Indoor Instance Segmentation in an Open-World
- 3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes
- 3D-LLM: Injecting the 3D World into Large Language Models
- 3D molecule generation by denoising voxel grids
- 4D Panoptic Scene Graph Generation
- 4M: Massively Multimodal Masked Modeling
- 4th Workshop on Self-Supervised Learning: Theory and Practice
- 6th Robot Learning Workshop: Pretraining, Fine-Tuning, and Generalization with Large Scale Models
- 6th Workshop on Artificial Intelligence for Humanitarian Assistance and Disaster Response
- A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning
- A Batch-to-Online Transformation under Random-Order Model
- A Bayesian Approach To Analysing Training Data Attribution In Deep Learning
- A Bayesian Take on Gaussian Process Networks
- AbDiffuser: full-atom generation of in-vitro functioning antibodies
- AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weeks
- A benchmark of categorical encoders for binary classification
- Abide by the law and follow the flow: conservation laws for gradient flows
- A Bounded Ability Estimation for Computerized Adaptive Testing
- A case for reframing automated medical image classification as segmentation
- A Causal Framework for Decomposing Spurious Variations
- Accelerated On-Device Forward Neural Network Training with Module-Wise Descending Asynchronism
- Accelerated Quasi-Newton Proximal Extragradient: Faster Rate for Smooth Convex Optimization
- Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation
- Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance
- Accelerating Exploration with Unlabeled Prior Data
- Accelerating Molecular Graph Neural Networks via Knowledge Distillation
- Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction
- Accelerating Motion Planning via Optimal Transport
- Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration
- Accelerating Value Iteration with Anchoring
- Accessing Higher Dimensions for Unsupervised Word Translation
- Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples
- Accurate Interpolation for Scattered Data through Hierarchical Residual Refinement
- Achieving $\mathcal{O}(\epsilon^{-1.5})$ Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization
- Achieving Cross Modal Generalization with Multimodal Unified Representation
- A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)
- A Combinatorial Algorithm for Approximating the Optimal Transport in the Parallel and MPC Settings
- A Competitive Algorithm for Agnostic Active Learning
- A Comprehensive Benchmark for Neural Human Radiance Fields
- A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking
- A Computationally Efficient Sparsified Online Newton Method
- A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting
- A Cross-Moment Approach for Causal Effect Estimation
- Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs
- Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models
- Active Bipartite Ranking
- Active Learning-Based Species Range Estimation
- Active Learning for Semantic Segmentation with Multi-class Label Query
- Actively Testing Your Model While It Learns: Realizing Label-Efficient Learning in Practice
- Active Negative Loss Functions for Learning with Noisy Labels
- Active Observing in Continuous-time Control
- Active Reasoning in an Open-World Environment
- Active representation learning for general task space with applications in robotics
- Active Vision Reinforcement Learning under Limited Visual Observability
- Activity Grammars for Temporal Action Segmentation
- AdANNS: A Framework for Adaptive Semantic Search
- AdaPlanner: Adaptive Planning from Feedback with Language Models
- Adapting Fairness Interventions to Missing Values
- Adapting Neural Link Predictors for Data-Efficient Complex Query Answering
- Adapting to Continuous Covariate Shift via Online Density Ratio Estimation
- Adaptive Algorithms for Relaxed Pareto Set Identification
- Adaptive Contextual Perception: How To Generalize To New Backgrounds and Ambiguous Objects
- Adaptive Data Analysis in a Balanced Adversarial Model
- Adaptive Experimental Design and Active Learning in the Real World
- Adaptive Linear Estimating Equations
- Adaptive Normalization for Non-stationary Time Series Forecasting: A Temporal Slice Perspective
- Adaptive Online Replanning with Diffusion Models
- Adaptive Principal Component Regression with Applications to Panel Data
- Adaptive Privacy Composition for Accuracy-first Mechanisms
- Adaptive recurrent vision performs zero-shot computation scaling to unseen difficulty levels
- Adaptive Selective Sampling for Online Prediction with Experts
- Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction
- Adaptive Test-Time Personalization for Federated Learning
- Adaptive Topological Feature via Persistent Homology: Filtration Learning for Point Clouds
- Adaptive Uncertainty Estimation via High-Dimensional Testing on Latent Representations
- Adaptive whitening with fast gain modulation and slow synaptic plasticity
- AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking
- A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks
- A Dataset for Analyzing Streaming Media Performance over HTTP/3 Browsers
- A Dataset of Relighted 3D Interacting Hands
- AdaVAE: Bayesian Structural Adaptation for Variational Autoencoders
- Add and Thin: Diffusion for Temporal Point Processes
- Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation
- Addressing Negative Transfer in Diffusion Models
- Addressing the speed-accuracy simulation trade-off for adaptive spiking neurons
- A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability
- A Definition of Continual Reinforcement Learning
- ADGym: Design Choices for Deep Anomaly Detection
- A Diffusion-Model of Joint Interactive Navigation
- Adjustable Robust Reinforcement Learning for Online 3D Bin Packing
- AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset
- A Dual-Stream Neural Network Explains the Functional Segregation of Dorsal and Ventral Visual Pathways in Human Brains
- Advancing Bayesian Optimization via Learning Correlated Latent Space
- Adversarial Attacks on Online Learning to Rank with Click Feedback
- Adversarial Counterfactual Environment Model Learning
- Adversarial Examples Are Not Real Features
- Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces
- Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness
- Adversarial Learning for Feature Shift Detection and Correction
- Adversarially Robust Distributed Count Tracking via Partial Differential Privacy
- Adversarially Robust Learning with Uncertain Perturbation Sets
- Adversarial Model for Offline Reinforcement Learning
- Adversarial Resilience in Sequential Prediction via Abstention
- Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach
- Adversarial Robustness through Random Weight Sampling
- Adversarial Self-Training Improves Robustness and Generalization for Gradual Domain Adaptation
- Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions
- Adversarial Training from Mean Field Perspective
- Advice Querying under Budget Constraint for Online Algorithms
- A Dynamical System View of Langevin-Based Non-Convex Sampling
- A Fast and Accurate Estimator for Large Scale Linear Model via Data Averaging
- A fast heuristic to optimize time-space tradeoff for large models
- Affinity-Aware Graph Networks
- A Finite-Particle Convergence Rate for Stein Variational Gradient Descent
- A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games
- A Fractional Graph Laplacian Approach to Oversmoothing
- A Framework for Fast and Stable Representations of Multiparameter Persistent Homology Decompositions
- AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix
- A General Framework for Equivariant Neural Networks on Reductive Lie Groups
- A General Framework for Robust G-Invariance in G-Equivariant Networks
- A General Theory of Correct, Incorrect, and Extrinsic Equivariance
- A generative model of the hippocampal formation trained with theta driven local learning rules
- Agent Learning in Open-Endedness Workshop
- Aggregating Capacity in FL through Successive Layer Training for Computationally-Constrained Devices
- Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
- Agnostically Learning Single-Index Models using Omnipredictors
- Agnostic Multi-Group Active Learning
- A graphon-signal analysis of graph neural networks
- A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning
- A Guide Through the Zoo of Biased SGD
- A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction
- A Heavy-Tailed Algebra for Probabilistic Programming
- A Hierarchical Spatial Transformer for Massive Point Samples in Continuous Space
- A Hierarchical Training Paradigm for Antibody Structure-sequence Co-design
- A High-Resolution Dataset for Instance Detection with Multi-View Object Capture
- A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
- AI for Accelerated Materials Design (AI4Mat-2023)
- AI for Interpretable Chemistry: Predicting Radical Mechanistic Pathways via Contrastive Learning
- AI for Science: from Theory to Practice
- AiluRus: A Scalable ViT Framework for Dense Prediction
- AI meets Moral Philosophy and Moral Psychology: An Interdisciplinary Dialogue about Computational Ethics
- Aiming towards the minimizers: fast convergence of SGD for overparametrized problems
- AIMS: All-Inclusive Multi-Level Segmentation for Anything
- AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs
- AirDelhi: Fine-Grained Spatio-Temporal Particulate Matter Dataset From Delhi For ML based Modeling
- AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation
- Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions
- Alexa Arena: A User-Centric Interactive Platform for Embodied AI
- Algorithmic Fairness through the Lens of Time
- Algorithmic Regularization in Tensor Optimization: Towards a Lifted Approach in Matrix Sensing
- Algorithm Selection for Deep Active Learning with Imbalanced Datasets
- ALGO: Synthesizing Algorithmic Programs with Generated Oracle Verifiers
- Aligning Gradient and Hessian for Neural Signed Distance Function
- Aligning Language Models with Human Preferences via a Bayesian Approach
- Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation
- Aligning Synthetic Medical Images with Clinical Knowledge using Human Feedback
- Alignment with human representations supports robust few-shot learning
- Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization
- ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning
- Alleviating the Semantic Gap for Generalized fMRI-to-Image Reconstruction
- All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation
- AllSim: Simulating and Benchmarking Resource Allocation Policies in Multi-User Systems
- (Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy
- A Logic for Expressing Log-Precision Transformers
- A Long $N$-step Surrogate Stage Reward for Deep Reinforcement Learning
- AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback
- Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics
- Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
- Alternating Updates for Efficient Transformers
- Alternation makes the adversary weaker in two-player games
- AmadeusGPT: a natural language interface for interactive animal behavioral analysis
- AMAG: Additive, Multiplicative and Adaptive Graph Neural Network For Forecasting Neuron Activity
- A Massive Scale Semantic Similarity Dataset of Historical English
- Amazon-M2: A Multilingual Multi-locale Shopping Session Dataset for Recommendation and Text Generation
- Ambient Diffusion: Learning Clean Distributions from Corrupted Data
- AMDP: An Adaptive Detection Procedure for False Discovery Rate Control in High-Dimensional Mediation Analysis
- A Measure-Theoretic Axiomatisation of Causality
- American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers
- A Metadata-Driven Approach to Understand Graph Neural Networks
- Amortized Reparametrization: Efficient and Scalable Variational Inference for Latent SDEs
- (Amplified) Banded Matrix Factorization: A unified approach to private training
- A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Causal Relationship
- An $\varepsilon$-Best-Arm Identification Algorithm for Fixed-Confidence and Beyond
- An active learning framework for multi-group mean estimation
- An Adaptive Algorithm for Learning with Unknown Distribution Drift
- An Alternating Optimization Method for Bilevel Problems under the Polyak-Łojasiewicz Condition
- An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient
- Analysis of Variance of Multiple Causal Networks
- Analyzing Generalization of Neural Networks through Loss Path Kernels
- Analyzing the Sample Complexity of Self-Supervised Image Reconstruction Methods
- Analyzing Vision Transformers for Image Classification in Class Embedding Space
- Anchor Data Augmentation
- AND: Adversarial Neural Degradation for Learning Blind Image Super-Resolution
- AndroidInTheWild: A Large-Scale Dataset For Android Device Control
- An Efficient and Robust Framework for Approximate Nearest Neighbor Search with Attribute Constraint
- An Efficient Dataset Condensation Plugin and Its Application to Continual Learning
- An Efficient Doubly-Robust Test for the Kernel Treatment Effect
- An Efficient End-to-End Training Approach for Zero-Shot Human-AI Coordination
- An Empirical Investigation of the Role of Pre-training in Lifelong Learning
- An Empirical Study Towards Prompt-Tuning for Graph Contrastive Pre-Training in Recommendations
- A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference
- A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs
- A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks
- A new perspective on building efficient and expressive 3D equivariant graph neural networks
- An Exploration-by-Optimization Approach to Best of Both Worlds in Linear Bandits
- An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits
- An Inductive Bias for Tabular Deep Learning
- An Information-Theoretic Evaluation of Generative Models in Learning Multi-modal Distributions
- An information-theoretic quantification of the content of communication between brain regions
- An Information Theory Perspective on Variance-Invariance-Covariance Regularization
- An Inverse Scaling Law for CLIP Training
- An Iterative Self-Learning Framework for Medical Domain Generalization
- An NLP Benchmark Dataset for Assessing Corporate Climate Policy Engagement
- Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation
- Anonymous and Copy-Robust Delegations for Liquid Democracy
- Anonymous Learning via Look-Alike Clustering: A Precise Analysis of Model Generalization
- An Optimal and Scalable Matrix Mechanism for Noisy Marginals under Convex Loss Functions
- An Optimal Structured Zeroth-order Algorithm for Non-smooth Optimization
- An Optimization-based Approach To Node Role Discovery in Networks: Approximating Equitable Partitions
- A normative theory of social conflict
- A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspective
- A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence
- ANPL: Towards Natural Programming with Interactive Decomposition
- ANTN: Bridging Autoregressive Neural Networks and Tensor Networks for Quantum Many-Body Simulation
- Anytime-Competitive Reinforcement Learning with Policy Prior
- Anytime Model Selection in Linear Bandits
- Any-to-Any Generation via Composable Diffusion
- A One-Size-Fits-All Approach to Improving Randomness in Paper Assignment
- A Partially-Supervised Reinforcement Learning Framework for Visual Active Search
- A Path to Simpler Models Starts With Noise
- A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning
- A polar prediction model for learning to represent visual transformations
- Application Development using Large Language Models
- Approximate Allocation Matching for Structural Causal Bandits with Unobserved Confounders
- Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent
- Approximate inference of marginals using the IBIA framework
- Approximately Equivariant Graph Networks
- Approximation-Generalization Trade-offs under (Approximate) Group Equivariance
- A Privacy-Friendly Approach to Data Valuation
- A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints
- AQuA: A Benchmarking Tool for Label Quality Assessment
- A Randomized Approach to Tight Privacy Accounting
- Arbitrarily Scalable Environment Generators via Neural Cellular Automata
- Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning
- AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation
- Are aligned neural networks adversarially aligned?
- A Recurrent Neural Circuit Mechanism of Temporal-scaling Equivariant Representation
- Are Diffusion Models Vision-And-Language Reasoners?
- A Reduction-based Framework for Sequential Decision Making with Delayed Feedback
- Are Emergent Abilities of Large Language Models a Mirage?
- Are GATs Out of Balance?
- A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems
- Are These the Same Apple? Comparing Images Based on Object Intrinsics
- Are Vision Transformers More Data Hungry Than Newborn Visual Systems?
- A Riemannian Exponential Augmented Lagrangian Method for Computing the Projection Robust Wasserstein Distance
- A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods
- A Robust and Opponent-Aware League Training Method for StarCraft II
- A Robust Exact Algorithm for the Euclidean Bipartite Matching Problem
- ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections
- ARTree: A Deep Autoregressive Model for Phylogenetic Inference
- A Scalable Neural Network for DSIC Affine Maximizer Auction Design
- A Scale-Invariant Sorting Criterion to Find a Causal Order in Additive Noise Models
- ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training
- A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories
- A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm
- A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation
- A Single-Loop Accelerated Extra-Gradient Difference Algorithm with Improved Complexity Bounds for Constrained Minimax Optimization
- ASL Citizen: A Community-Sourced Dataset for Advancing Isolated Sign Language Recognition
- A Smooth Binary Mechanism for Efficient Private Continual Observation
- A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm
- A Spectral Theory of Neural Prediction and Alignment
- ASPEN: Breaking Operator Barriers for Efficient Parallelization of Deep Neural Networks
- Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment
- Associative Memory & Hopfield Networks in 2023
- Assumption violations in causal discovery and the robustness of score matching
- A State Representation for Diminishing Rewards
- A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset
- A Sublinear-Time Spectral Clustering Oracle with Improved Preprocessing Time
- Asymmetric Certified Robustness via Feature-Convex Neural Networks
- Asymptotically Optimal Quantile Pure Exploration for Infinite-Armed Bandits
- Asymptotics of Bayesian Uncertainty Estimation in Random Features Regression
- Asynchronous Proportional Response Dynamics: Convergence in Markets with Adversarial Scheduling
- Asynchrony-Robust Collaborative Perception via Bird's Eye View Flow
- A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence
- A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes
- A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression
- A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs
- A Theory of Multimodal Learning
- A Theory of Transfer-Based Black-Box Attacks: Explanation and Implications
- A Theory of Unsupervised Translation Motivated by Understanding Animal Communication
- ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation
- A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning
- A Trichotomy for Transductive Online Learning
- ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation
- Attacks on Online Learners: a Teacher-Student Analysis
- Attention as Implicit Structural Inference
- Attentive Transfer Entropy to Exploit Transient Emergence of Coupling Effect
- Attributing Model Behavior at Scale (ATTRIB)
- AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation
- AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models
- Auditing Fairness by Betting
- Auditing for Human Expertise
- Augmentation-Aware Self-Supervision for Data-Efficient GAN Training
- Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic Segmentation
- Augmented Memory Replay-based Continual Learning Approaches for Network Intrusion Detection
- Augmenting Language Models with Long-Term Memory
- A Unified Algorithm Framework for Unsupervised Discovery of Skills based on Determinantal Point Process
- A Unified Approach for Maximizing Continuous DR-submodular Functions
- A Unified Approach to Count-Based Weakly Supervised Learning
- A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm
- A Unified Conditional Framework for Diffusion-based Image Restoration
- A Unified Detection Framework for Inference-Stage Backdoor Defenses
- A Unified Discretization Framework for Differential Equation Approach with Lyapunov Arguments for Convex Optimization
- A Unified Fast Gradient Clipping Framework for DP-SGD
- A unified framework for information-theoretic generalization bounds
- A Unified Framework for Rank-based Loss Minimization
- A Unified Framework for U-Net Design and Analysis
- A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing
- A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning
- A Unified Model and Dimension for Interactive Estimation
- A Unified, Scalable Framework for Neural Population Decoding
- A Unified Solution for Privacy and Communication Efficiency in Vertical Federated Learning
- A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning
- Auslan-Daily: Australian Sign Language Translation for Daily Communication and News
- Autodecoding Latent 3D Diffusion Models
- AutoGO: Automated Computation Graph Optimization for Neural Network Evolution
- Automated Classification of Model Errors on ImageNet
- Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger
- Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement Learning
- Automatic Integration for Spatiotemporal Neural Point Processes
- Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings
- A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning
- Auxiliary Losses for Learning Generalizable Concept-based Models
- A Variational Perspective on High-Resolution ODEs
- AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web
- AVIDa-hIL6: A Large-Scale VHH Dataset Produced from an Immunized Alpaca for Predicting Antigen-Antibody Interactions
- AVIS: Autonomous Visual Information Seeking with Large Language Model Agent
- AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis
- AVOIDDS: Aircraft Vision-based Intruder Detection Dataset and Simulator
- Backdoors in Deep Learning: The Good, the Bad, and the Ugly
- Back-Modality: Leveraging Modal Transformation for Data Augmentation
- BadTrack: A Poison-Only Backdoor Attack on Visual Object Tracking
- Balanced Training for Sparse GANs
- Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective
- Balancing memorization and generalization in RNNs for high performance brain-machine Interfaces
- Balancing Risk and Reward: A Batched-Bandit Strategy for Automated Phased Release
- Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance
- BanditPAM++: Faster $k$-medoids Clustering
- Bandit Social Learning under Myopic Behavior
- Bandit Task Assignment with Unknown Processing Time
- BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis
- Batch Bayesian Optimization For Replicable Experimental Design
- Batchnorm Allows Unsupervised Radial Attacks
- Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks
- Bayes beats Cross Validation: Efficient and Accurate Ridge Regression via Expectation Maximization
- BayesDAG: Gradient-Based Posterior Inference for Causal Discovery
- Bayesian Active Causal Discovery with Multi-Fidelity Experiments
- Bayesian Extensive-Rank Matrix Factorization with Rotational Invariant Priors
- Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space
- Bayesian Learning via Q-Exponential Process
- Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval
- Bayesian nonparametric (non-)renewal processes for analyzing neural spike train variability
- Bayesian Optimisation of Functions on Graphs
- Bayesian Optimization with Cost-varying Variable Subsets
- Bayesian Risk-Averse Q-Learning with Streaming Observations
- Bayesian target optimisation for high-precision holographic optogenetics
- BayesTune: Bayesian Sparse Deep Model Fine-tuning
- BCDiff: Bidirectional Consistent Diffusion for Instantaneous Trajectory Prediction
- BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset
- BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks
- Behavior Alignment via Reward Function Optimization
- Belief Projection-Based Reinforcement Learning for Environments with Delayed Feedback
- BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing
- Benchmarking and Analyzing 3D-aware Image Synthesis with a Modularized Codebase
- Benchmarking Distribution Shift in Tabular Data with TableShift
- Benchmarking Encoder-Decoder Architectures for Biplanar X-ray to 3D Bone Shape Reconstruction
- Benchmarking Foundation Models with Language-Model-as-an-Examiner
- Benchmarking Large Language Models on CMExam - A comprehensive Chinese Medical Exam Dataset
- Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models
- Benchmarking Robustness to Adversarial Image Obfuscations
- Benchmark of Machine Learning Force Fields for Semiconductor Simulations: Datasets, Metrics, and Comparative Analysis
- BERT Lost Patience Won't Be Robust to Adversarial Slowdown
- Best Arm Identification with Fixed Budget: A Large Deviation Perspective
- Beta Diffusion
- Better Correlation and Robustness: A Distribution-Balanced Self-Supervised Learning Framework for Automatic Dialogue Evaluation
- Better Private Linear Regression Through Better Private Feature Selection
- Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks
- Beyond Average Return in Markov Decision Processes
- Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions
- Beyond Confidence: Reliable Models Should Also Consider Atypicality
- Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift
- Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence
- Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysis
- Beyond Invariance: Test-Time Label-Shift Adaptation for Addressing "Spurious" Correlations
- Beyond MLE: Convex Learning for Text Generation
- Beyond Myopia: Learning from Positive and Unlabeled Data through Holistic Predictive Trends
- Beyond Normal: On the Evaluation of Mutual Information Estimators
- Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time
- Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense
- Beyond probability partitions: Calibrating neural networks with semantic aware grouping
- Beyond Scaling Panel
- Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets
- Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation
- Bias in Evaluation Processes: An Optimization-Based Model
- Bicriteria Approximation Algorithms for the Submodular Cover Problem
- Bicriteria Multidimensional Mechanism Design with Side Information
- Bifurcations and loss jumps in RNN training
- Bilevel Coreset Selection in Continual Learning: A New Formulation and Algorithm
- Bi-Level Offline Policy Optimization with Limited Exploration
- Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-Start
- BiMatting: Efficient Video Matting via Binarization
- Binarized Neural Machine Translation
- Binarized Spectral Compressive Imaging
- Binary Classification with Confidence Difference
- Binary Radiance Fields
- BioMassters: A Benchmark Dataset for Forest Biomass Estimation using Multi-modal Satellite Time-series
- BIOT: Biosignal Transformer for Cross-data Learning in the Wild
- Birder: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN Training
- BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning
- Birth of a Transformer: A Memory Viewpoint
- BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization
- Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method
- Black-box Backdoor Defense via Zero-shot Image Purification
- Black-Box Differential Privacy for Interactive ML
- BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing
- Block Broyden's Methods for Solving Nonlinear Equations
- Block-Coordinate Methods and Restarting for Solving Extensive-Form Games
- Block Coordinate Plug-and-Play Methods for Blind Inverse Problems
- Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraints
- Block Low-Rank Preconditioner with Shared Basis for Stochastic Optimization
- Block-State Transformers
- Blockwise Parallel Transformers for Large Context Models
- Blurred-Dilated Method for Adversarial Attacks
- BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information
- Boosting Adversarial Transferability by Achieving Flat Local Maxima
- Boosting Learning for LDPC Codes to Improve the Error-Floor Performance
- Boosting Spectral Clustering on Incomplete Data via Kernel Correction and Affinity Learning
- Boosting Verification of Deep Reinforcement Learning via Piece-Wise Linear Decision Neural Networks
- Boosting with Tempered Exponential Measures
- Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences
- Bootstrapping Vision-Language Learning with Decoupled Language Pre-training
- Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff
- Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces
- Boundary Guided Learning-Free Semantic Control with Diffusion Models
- Bounded rationality in structured density estimation
- Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information
- Bounding training data reconstruction in DP-SGD
- BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimization
- Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models
- Brain Dissection: fMRI-trained Networks Reveal Spatial Selectivity in the Processing of Natural Images
- Brain encoding models based on multimodal transformers can transfer across language and vision
- Brain-like Flexible Visual Inference by Harnessing Feedback Feedforward Alignment
- Brant: Foundation Model for Intracranial Neural Signal
- Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback
- Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy
- Break It Down: Evidence for Structural Compositionality in Neural Networks
- Bridging Discrete and Backpropagation: Straight-Through and Beyond
- Bridging RL Theory and Practice with the Effective Horizon
- Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models
- Bringing regularized optimal transport to lightspeed: a splitting method adapted for GPUs
- BubbleML: A Multiphase Multiphysics Dataset and Benchmarks for Machine Learning
- Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders
- Budgeting Counterfactual for Offline RL
- BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting
- Building Socio-culturally Inclusive Stereotype Resources with Community Engagement
- Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark
- Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition
- Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing
- Bypassing spike sorting: Density-based decoding using spike localization from dense multielectrode probes
- Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits
- Byzantine-Tolerant Methods for Distributed Variational Inequalities
- CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning
- Cal-DETR: Calibrated Detection Transformer
- Calibrate and Boost Logical Expressiveness of GNN Over Multi-Relational and Temporal Graphs
- Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents
- Calibrating “Cheap Signals” in Peer Review without a Prior
- Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability
- Calibration by Distribution Matching: Trainable Kernel Calibration Metrics
- Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
- CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
- CamoPatch: An Evolutionary Strategy for Generating Camoflauged Adversarial Patches
- CaMP: Causal Multi-policy Planning for Interactive Navigation in Multi-room Scenes
- Can Language Models Solve Graph Problems in Natural Language?
- Can Language Models Teach? Teacher Explanations Improve Student Performance via Personalization
- Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
- Canonical normalizing flows for manifold learning
- Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?
- Can semi-supervised learning use all the data effectively? A lower bound perspective
- Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data
- CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models
- CAPP-130: A Corpus of Chinese Application Privacy Policy Summarization and Interpretation
- Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer
- CAPro: Webly Supervised Learning with Cross-modality Aligned Prototypes
- CARE-MI: Chinese Benchmark for Misinformation Evaluation in Maternity and Infant Care
- CARE: Modeling Interacting Dynamics Under Temporal Environmental Variation
- Cascading Bandits: Optimizing Recommendation Frequency in Delayed Feedback Environments
- Cascading Contextual Assortment Bandits
- CAST: Cross-Attention in Space and Time for Video Action Recognition
- Category-Extensible Out-of-Distribution Detection via Hierarchical Context Descriptions
- CAT-Walk: Inductive Hypergraph Learning via Set Walks
- Causal Component Analysis
- Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairness
- Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data
- Causal discovery from observational and interventional data across multiple environments
- Causal Discovery from Subsampled Time Series with Proxy Variables
- Causal Discovery in Semi-Stationary Time Series
- Causal Effect Identification in Uncertain Causal Networks
- Causal Effect Regularization: Automated Detection and Removal of Spurious Correlations
- Causal Fairness for Outcome Control
- Causal Imitability Under Context-Specific Independence Relations
- Causal Interpretation of Self-Attention in Pre-Trained Transformers
- Causal normalizing flows: from theory to practice
- Causal Representation Learning
- Cause-Effect Inference in Location-Scale Noise Models: Maximum Likelihood vs. Independence Testing
- Causes and Effects of Unanticipated Numerical Deviations in Neural Network Inference Frameworks
- CBD: A Certified Backdoor Detector Based on Local Dominant Probability
- C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder
- CEIL: Generalized Contextual Imitation Learning
- CELLE-2: Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transformer
- Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback
- Certifiably Robust Graph Contrastive Learning
- Certification of Distributional Individual Fairness
- Certified Minimax Unlearning with Generalization Rates and Deletion Capacity
- Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization
- C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models
- Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models
- CHAMMI: A benchmark for channel-adaptive models in microscopy imaging
- Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception
- Change point detection and inference in multivariate non-parametric models under mixing conditions
- Characteristic Circuits
- Characterization and Learning of Causal Graphs with Small Conditioning Sets
- Characterization of Overfitting in Robust Multiclass Classification
- Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond
- Characterizing Out-of-Distribution Error via Optimal Transport
- Characterizing the Impacts of Semi-supervised Learning for Weak Supervision
- Characterizing the Optimal $0-1$ Loss for Multi-class Classification with a Test-time Attacker
- Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach
- ChatGPT-Powered Hierarchical Comparisons for Image Classification
- Chatting Makes Perfect: Chat-based Image Retrieval
- Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models
- Cheaply Estimating Inference Efficiency Metrics for Autoregressive Transformer Models
- ChessGPT: Bridging Policy Learning and Language Modeling
- ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors
- Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity
- Circuit as Set of Points
- CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data
- CLadder: Assessing Causal Reasoning in Language Models
- Class-Conditional Conformal Prediction with Many Classes
- Class-Distribution-Aware Pseudo-Labeling for Semi-Supervised Multi-Label Learning
- Classical Simulation of Quantum Circuits: Parallel Environments and Benchmark
- Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach
- CLeAR: Continual Learning on Algorithmic Reasoning for Human-like Intelligence
- Clifford Group Equivariant Neural Networks
- ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling
- ClimateSet: A Large-Scale Climate Model Dataset for Machine Learning
- ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation
- CLIP4HOI: Towards Adapting CLIP for Practical Zero-Shot HOI Detection
- CLIP-OGD: An Experimental Design for Adaptive Neyman Allocation in Sequential Experiments
- CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation
- Closing the Computational-Statistical Gap in Best Arm Identification for Combinatorial Semi-bandits
- Closing the gap between the upper bound and lower bound of Adam's iteration complexity
- CluB: Cluster Meets BEV for LiDAR-Based 3D Object Detection
- Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering
- ClusterFomer: Clustering As A Universal Visual Learner
- Clustering the Sketch: Dynamic Compression for Embedding Tables
- CMMA: Benchmarking Multi-Affection Detection in Chinese Multi-Modal Conversations
- Cocktail: Mixing Multi-Modality Control for Text-Conditional Image Generation
- COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs
- CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection
- CODA: Generalizing to Open and Unseen Domains with Compaction and Disambiguation
- CoDet: Co-occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection
- CoDrug: Conformal Drug Property Prediction with Density Estimation under Covariate Shift
- Cognitive Model Discovery via Disentangled RNNs
- Cognitive Steering in Deep Neural Networks via Long-Range Modulatory Feedback Connections
- Coherence statistics, self-generated experience and why young humans are much smarter than current AI.
- Coherent Soft Imitation Learning
- Cola: A Benchmark for Compositional Text-to-image Retrieval
- CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
- Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
- Collaborative Alignment of NLP Models
- Collaborative Learning via Prediction Consensus
- Collaboratively Learning Linear Models with Structured Missing Data
- Collaborative Score Distillation for Consistent Visual Editing
- Collapsed Inference for Bayesian Deep Learning
- CoLLAT: On Adding Fine-grained Audio Understanding to Language Models using Token-Level Locked-Language Tuning
- Color Equivariant Convolutional Networks
- Combating Bilateral Edge Noise for Robust Link Prediction
- Combating Representation Learning Disparity with Geometric Harmonization
- Combinatorial Group Testing with Selfish Agents
- Combinatorial Optimization with Policy Adaptation using Latent Space Search
- Combining Behaviors with the Successor Features Keyboard
- Common Ground in Cooperative Communication
- CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion
- Communication-Efficient Federated Bilevel Optimization with Global and Local Lower Level Problems
- Compact Neural Volumetric Video Representations with Dynamic Codebooks
- Comparing Apples to Oranges: Learning Similarity Functions for Data Produced by Different Distributions
- Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions
- Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift
- Complexity Matters: Rethinking the Latent Space for Generative Modeling
- Complexity of Derivative-Free Policy Optimization for Structured $\mathcal{H}_\infty$ Control
- Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints
- Complex-valued Neurons Can Learn More but Slower than Real-valued Neurons via Gradient Descent
- Composable Coresets for Determinant Maximization: Greedy is Almost Optimal
- Composing Parameter-Efficient Modules with Arithmetic Operation
- Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task
- Compositional Foundation Models for Hierarchical Planning
- Compositional Generalization from First Principles
- Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees
- Compositional Sculpting of Iterative Generative Processes
- Compressed Video Prompt Tuning
- Compression with Bayesian Implicit Neural Representations
- Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy
- Computational Guarantees for Doubly Entropic Wasserstein Barycenters
- Computational Sustainability: Promises and Pitfalls from Theory to Deployment
- Computing a human-like reaction time metric from stable recurrent vision models
- Computing Approximate $\ell_p$ Sensitivities
- Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games
- Computing Optimal Nash Equilibria in Multiplayer Games
- ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation
- Concentration analysis of multivariate elliptic diffusions
- Concept Algebra for (Score-Based) Text-Controlled Generative Models
- Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement
- ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding
- Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference
- Conditional Distribution Function Estimation Using Neural Networks for Censored and Uncensored Data
- Conditional independence testing under misspecified inductive biases
- Conditional Matrix Flows for Gaussian Graphical Models
- Conditional Mutual Information for Disentangled Representations in Reinforcement Learning
- Conditional score-based diffusion models for Bayesian inference in infinite dimensions
- Conditional Score Guidance for Text-Driven Image-to-Image Translation
- Coneheads: Hierarchy Aware Attention
- Conformalized matrix completion
- Conformal Meta-learners for Predictive Inference of Individual Treatment Effects
- Conformal PID Control for Time Series Prediction
- Conformal Prediction for Time Series with Modern Hopfield Networks
- Conformal Prediction for Uncertainty-Aware Planning with Diffusion Dynamics Model
- Conformal Prediction Sets for Ordinal Classification
- Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems
- Connecting Certified and Adversarial Training
- Connecting Multi-modal Contrastive Representations
- Connecting Pre-trained Language Model and Downstream Task via Properties of Representation
- ConRad: Image Constrained Radiance Fields for 3D Generation from a Single Image
- Consensus and Subjectivity of Skin Tone Annotation for ML Fairness
- Conservative Offline Policy Adaptation in Multi-Agent Games
- Conservative State Value Estimation for Offline Reinforcement Learning
- Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards
- Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent
- Constant Approximation for Individual Preference Stable Clustering
- Constrained Policy Optimization with Explicit Behavior Density For Offline Reinforcement Learning
- Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning
- Constructing Non-isotropic Gaussian Diffusion Model Using Isotropic Gaussian Diffusion Model for Image Editing
- Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars
- Content-based Unrestricted Adversarial Attack
- Context-guided Embedding Adaptation for Effective Topic Modeling in Low-Resource Regimes
- Context-lumpable stochastic bandits
- Context-PIPs: Persistent Independent Particles Demands Spatial Context Features
- Context Shift Reduction for Offline Meta-Reinforcement Learning
- Contextual Bandits and Imitation Learning with Preference-Based Active Queries
- Contextual Gaussian Process Bandits with Neural Networks
- Contextually Affinitive Neighborhood Refinery for Deep Clustering
- Contextual Stochastic Bilevel Optimization
- ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling
- Continual Learning for Instruction Following from Realtime Feedback
- ContinuAR: Continuous Autoregression For Infinite-Fidelity Fusion
- Continuous Parametric Optical Flow
- Continuous-time Analysis of Anchor Acceleration
- Continuous-Time Functional Diffusion Processes
- Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities
- Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series
- Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion
- Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning
- Contrastive Moments: Unsupervised Halfspace Learning in Polynomial Time
- Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL
- Contrastive Sampling Chains in Diffusion Models
- Contrastive Training of Complex-Valued Autoencoders for Object Discovery
- Contributing to an Efficient and Democratized Large Model Era
- Controlling Text-to-Image Diffusion by Orthogonal Finetuning
- Convergence analysis of ODE models for accelerated first-order methods via positive semidefinite kernels
- Convergence Analysis of Sequential Federated Learning on Heterogeneous Data
- Convergence of Actor-Critic with Multi-Layer Neural Networks
- Convergence of Adam Under Relaxed Assumptions
- Convergence of Alternating Gradient Descent for Matrix Factorization
- Convergence of mean-field Langevin dynamics: time-space discretization, stochastic gradient, and variance reduction
- Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems
- Convex and Non-convex Optimization Under Generalized Smoothness
- Convex-Concave Zero-Sum Markov Stackelberg Games
- Convolutional Neural Operators for robust and accurate learning of PDEs
- Convolutional State Space Models for Long-Range Spatiotemporal Modeling
- Convolutional Visual Prompt for Robust Visual Perception
- Convolution Monge Mapping Normalization for learning on sleep data
- Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP
- Cookie Consent Has Disparate Impact on Estimation Accuracy
- COOM: A Game Benchmark for Continual Reinforcement Learning
- Coop: Memory is not a Commodity
- Coordinating Distributed Example Orders for Provably Accelerated Training
- CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inference
- Core-sets for Fair and Diverse Data Summarization
- CORL: Research-oriented Deep Offline Reinforcement Learning Library
- CORNN: Convex optimization of recurrent neural networks for rapid inference of neural dynamics
- Correlation Aware Sparsified Mean Estimation Using Random Projection
- Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neural Networks without Weight Symmetry
- CorresNeRF: Image Correspondence Priors for Neural Radiance Fields
- Corruption-Robust Offline Reinforcement Learning with General Function Approximation
- CosNet: A Generalized Spectral Kernel Network
- Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation
- Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning
- Counterfactual Evaluation of Peer-Review Assignment Policies
- Counterfactual Generation with Identifiability Guarantees
- Counterfactually Comparing Abstaining Classifiers
- Counterfactually Fair Representation
- Counterfactual Memorization in Neural Language Models
- Counting Distinct Elements in the Turnstile Model with Differential Privacy under Continual Observation
- Counting Distinct Elements Under Person-Level Differential Privacy
- Coupled Reconstruction of Cortical Surfaces by Diffeomorphic Mesh Deformation
- Covariance-adaptive best arm identification
- CP-SLAM: Collaborative Neural Point-based SLAM System
- CQM: Curriculum Reinforcement Learning with a Quantized World Model
- Creating a Public Repository for Joining Private Data
- Creating Multi-Level Skill Hierarchies in Reinforcement Learning
- Credal Marginal MAP
- Critical Initialization of Wide and Deep Neural Networks using Partial Jacobians: General Theory and Applications
- CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders
- CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion
- CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography
- Cross-Domain Policy Adaptation via Value-Guided Data Filtering
- Cross-Episodic Curriculum for Transformer Agents
- CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement
- Cross-links Matter for Link Prediction: Rethinking the Debiased GNN from a Data Perspective
- Cross-modal Active Complementary Learning with Self-refining Correspondence
- Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks
- Cross-Scale MAE: A Tale of Multiscale Exploitation in Remote Sensing
- Crystal Structure Prediction by Joint Equivariant Diffusion
- CS4ML: A general framework for active learning with arbitrary data based on Christoffel functions
- CS-Isolate: Extracting Hard Confident Examples by Content and Style Isolation
- CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion
- CSMeD: Bridging the Dataset Gap in Automated Citation Screening for Systematic Literature Reviews
- CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labels
- Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First
- Curriculum Learning With Infant Egocentric Videos
- Curvature Filtrations for Graph Generative Model Evaluation
- Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models
- Customizable Image Synthesis with Multiple Subjects
- CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss
- CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation
- D$^2$CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts
- D4Explainer: In-distribution Explanations of Graph Neural Network via Discrete Denoising Diffusion
- D4: Improving LLM Pretraining via Document De-Duplication and Diversification
- DAC-DETR: Divide the Attention Layers and Conquer
- DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets
- DäRF: Boosting Radiance Fields from Sparse Input Views with Monocular Depth Adaptation
- DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation
- Data Augmentations for Improved (Large) Language Model Generalization
- Data-Centric AI for reliable and responsible AI: from theory to practice
- Data-Centric Learning from Unlabeled Graphs with Diffusion Model
- DataComp: In search of the next generation of multimodal datasets
- Data Contribution Estimation for Machine Learning
- Data-Dependent Bounds for Online Portfolio Selection Without Lipschitzness and Smoothness
- Data-Driven Network Neuroscience: On Data Collection and Benchmark
- Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances
- Data-Informed Geometric Space Selection
- Data Market Design through Deep Learning
- Data Minimization at Inference Time
- DataPerf: Benchmarks for Data-Centric AI Development
- Data Portraits: Recording Foundation Model Training Data
- Data Pruning via Moving-one-Sample-out
- Data Quality in Imitation Learning
- DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model
- Data Selection for Language Models via Importance Resampling
- Dataset Diffusion: Diffusion-based Synthetic Data Generation for Pixel-Level Semantic Segmentation
- DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models
- Datasets and Benchmarks for Nanophotonic Structure and Parametric Design Simulations
- DAW: Exploring the Better Weighting Function for Semi-supervised Semantic Segmentation
- D-CIPHER: Discovery of Closed-form Partial Differential Equations
- DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models
- DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Field
- Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models
- Debiased and Denoised Entity Recognition from Distant Supervision
- Debiasing Conditional Stochastic Optimization
- Debiasing Pretrained Generative Models by Uniformly Sampling Semantic Attributes
- Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation
- Decentralized Matrix Sensing: Statistical Guarantees and Fast Convergence
- Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards
- Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment
- Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees
- Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models
- Decision Tree for Locally Private Estimation with Public Data
- Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory
- DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
- Decompose a Task into Generalizable Subtasks in Multi-Agent Reinforcement Learning
- Decompose Novel into Known: Part Concept Learning For 3D Novel Class Discovery
- Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses
- Decorate3D: Text-Driven High-Quality Texture Generation for Mesh Decoration in the Wild
- Deductive Verification of Chain-of-Thought Reasoning
- DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization
- Deep Contract Design via Discontinuous Networks
- Deep Equilibrium Based Neural Operators for Steady-State PDEs
- DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection
- Deep Fractional Fourier Transform
- Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems
- Deep Generative Models for Health
- Deep Insights into Noisy Pseudo Labeling on Graph Data
- Deep learning with kernels through RKHM and the Perron-Frobenius operator
- Deep Momentum Multi-Marginal Schrödinger Bridge
- Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model
- Deep Non-line-of-sight Imaging from Under-scanning Measurements
- Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image Restoration
- Deep Patch Visual Odometry
- DeepPCR: Parallelizing Sequential Operations in Neural Networks
- Deep Recurrent Optimal Stopping
- Deep Reinforcement Learning with Plasticity Injection
- DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation
- Deep Stochastic Processes via Functional Markov Transition Operators
- Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training
- Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks
- Degraded Polygons Raise Fundamental Questions of Neural Network Perception
- Delayed Algorithms for Distributed Stochastic Weakly Convex Optimization
- Delegated Classification
- DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis
- DELTA: Diverse Client Sampling for Fasting Federated Learning
- Demo2Code: From Summarizing Demonstrations to Synthesizing Code via Extended Chain-of-Thought
- Demographic Parity Constrained Minimax Optimal Regression under Linear Model
- Demystifying Oversmoothing in Attention-Based Graph Neural Networks
- Demystifying Softmax Gating Function in Gaussian Mixture of Experts
- Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?
- Demystifying the Optimal Performance of Multi-Class Classification
- De novo Drug Design using Reinforcement Learning with Multiple GPT Agents
- Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models
- Dense-Exponential Random Features: Sharp Positive Estimators of the Gaussian Kernel
- Density of States Prediction of Crystalline Materials via Prompt-guided Multi-Modal Transformer
- Depth-discriminative Metric Learning for Monocular 3D Object Detection
- Derandomized novelty detection with FDR control via conformal e-values
- DesCo: Learning Object Recognition with Rich Language Descriptions
- Described Object Detection: Liberating Object Detection with Flexible Expressions
- Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents
- Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization
- Designing Robust Transformers using Robust Kernel Density Estimation
- DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries
- Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models
- Detecting hidden confounding in observational data using multiple environments
- Detection Based Part-level Articulated Object Reconstruction from Single RGBD Image
- DeWave: Discrete Encoding of EEG Waves for EEG to Text Translation
- DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning
- DICES Dataset: Diversity in Conversational AI Evaluation for Safety
- DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
- DiffComplete: Diffusion-based Generative 3D Shape Completion
- DIFFER:Decomposing Individual Reward for Fair Experience Replay in Multi-Agent Reinforcement Learning
- Differentiable and Stable Long-Range Tracking of Multiple Posterior Modes
- Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives
- Differentiable Clustering with Perturbed Spanning Forests
- Differentiable Neuro-Symbolic Reasoning on Large-Scale Knowledge Graphs
- Differentiable Random Partition Models
- Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching
- Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick
- Differentiable sorting for censored time-to-event data.
- Differentially Private Approximate Near Neighbor Counting in High Dimensions
- Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection
- Differentially Private Image Classification by Learning Priors from Random Processes
- Differentially Private Statistical Inference through $\beta$-Divergence One Posterior Sampling
- Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models
- DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology
- Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models
- DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation
- DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing
- DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models
- DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model
- DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models
- Diffused Redundancy in Pre-trained Representations
- Diffused Task-Agnostic Milestone Planner
- Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
- Diffusion-Based Probabilistic Uncertainty Estimation for Active Domain Adaptation
- Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence
- Diffusion Model for Graph Inverse Problems: Towards Effective Source Localization on Complex Networks
- Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
- Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels
- Diffusion Probabilistic Models for Structured Node Classification
- Diffusion Representation for Asymmetric Kernels via Magnetic Transform
- Diffusion Schrödinger Bridge Matching
- Diffusion Self-Guidance for Controllable Image Generation
- Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection
- Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback
- Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
- DiffUTE: Universal Text Editing Diffusion Model
- DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics
- DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimization
- Digital Typhoon: Long-term Satellite Image Dataset for the Spatio-Temporal Modeling of Tropical Cyclones
- DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning
- DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
- Diplomat: A Dialogue Dataset for Situated PragMATic Reasoning
- Direct Diffusion Bridge using Data Consistency for Inverse Problems
- Directed Cyclic Graph for Causal Discovery from Multivariate Functional Data
- Directional diffusion models for graph representation learning
- Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms
- Direct Preference-based Policy Optimization without Reward Modeling
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- Direct Training of SNN using Local Zeroth Order Method
- Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning
- DISCO-10M: A Large-Scale Music Dataset
- Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning
- Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design
- Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning
- Discovering Intrinsic Spatial-Temporal Logic Rules to Explain Human Actions
- DISCOVER: Making Vision Networks Interpretable via Competition and Dissection
- Discrete-Smoothness in Online Algorithms with Predictions
- Discriminative Calibration: Check Bayesian Computation from Simulations and Flexible Classifier
- Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability
- DISCS: A Benchmark for Discrete Sampling
- DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models
- Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning
- Disentangled Wasserstein Autoencoder for T-Cell Receptor Engineering
- Disentanglement via Latent Quantization
- Disentangling Cognitive Diagnosis with Limited Exercise Labels
- Disentangling Voice and Content with Self-Supervision for Speaker Recognition
- Dis-inhibitory neuronal circuits can control the sign of synaptic plasticity
- Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning
- Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power
- Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models
- Distributed Inference and Fine-tuning of Large Language Models Over The Internet
- Distributed Personalized Empirical Risk Minimization
- Distributional Learning of Variational AutoEncoder: Application to Synthetic Data Generation
- Distributionally Robust Bayesian Optimization with $\varphi$-divergences
- Distributionally Robust Ensemble of Lottery Tickets Towards Calibrated Sparse Network Training
- Distributionally Robust Linear Quadratic Control
- Distributionally Robust Skeleton Learning of Discrete Bayesian Networks
- Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning
- Distributional Pareto-Optimal Multi-Objective Reinforcement Learning
- Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning
- Distribution-Free Model-Agnostic Regression Calibration via Nonparametric Methods
- Distribution-Free Statistical Dispersion Control for Societal Applications
- Distribution Learnability and Robustness
- DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation
- Diverse Community Data for Benchmarking Data Privacy Algorithms
- Diverse Conventions for Human-AI Collaboration
- Diverse Shape Completion via Style Modulated Generative Adversarial Networks
- Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation
- Diversify \& Conquer: Outcome-directed Curriculum RL via Out-of-Distribution Disagreement
- Diversifying Spatial-Temporal Perception for Video Domain Generalization
- Diversify Your Vision Datasets with Automatic Diffusion-based Augmentation
- Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback
- DiViNeT: 3D Reconstruction from Disparate Views using Neural Template Regularization
- Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration
- Does a sparse ReLU network training problem always admit an optimum ?
- Does Continual Learning Meet Compositionality? New Benchmarks and An Evaluation Framework
- Does Graph Distillation See Like Vision Dataset Counterpart?
- Does Invariant Graph Learning via Environment Augmentation Learn Invariance?
- Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
- Does progress on ImageNet transfer to real-world datasets?
- Does Visual Pretraining Help End-to-End Reasoning?
- Domain Adaptive Imitation Learning with Visual Observation
- Domain Agnostic Fourier Neural Operators
- Domain Re-Modulation for Few-Shot Generative Domain Adaptation
- Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand
- Do Not Marginalize Mechanisms, Rather Consolidate!
- Don't be so Monotone: Relaxing Stochastic Line Search in Over-Parameterized Models
- Don’t blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy
- Don’t just prune by magnitude! Your mask topology is a secret weapon
- Don’t Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner
- DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining
- DOSE: Diffusion Dropout with Adaptive Prior for Speech Enhancement
- Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning
- Double and Single Descent in Causal Inference with an Application to High-Dimensional Synthetic Control
- Double Auctions with Two-sided Bandit Feedback
- Double Gumbel Q-Learning
- Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage
- Double Randomized Underdamped Langevin with Dimension-Independent Convergence Guarantee
- Doubly Constrained Fair Clustering
- Doubly Robust Augmented Transfer for Meta-Reinforcement Learning
- Doubly-Robust Self-Training
- DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
- Do You Prefer Learning with Preferences?
- DP-HyPO: An Adaptive Private Framework for Hyperparameter Optimization
- DP-Mix: Mixup-based Data Augmentation for Differentially Private Learning
- DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics
- DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models
- DRAUC: An Instance-wise Distributionally Robust AUC Optimization Framework
- DreamHuman: Animatable 3D Avatars from Text
- DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data
- DreamSparse: Escaping from Plato’s Cave with 2D Diffusion Model Given Sparse Views
- Dream the Impossible: Outlier Imagination with Diffusion Models
- DreamWaltz: Make a Scene with Complex 3D Animatable Avatars
- Drift doesn't Matter: Dynamic Decomposition with Diffusion Reconstruction for Unstable Multivariate Time Series Anomaly Detection
- DropCompute: simple and more robust distributed synchronous training via compute variance reduction
- DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions
- DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening
- D-Separation for Causal Self-Explanation
- DSR: Dynamical Surface Representation as Implicit Neural Networks for Protein
- Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization
- Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative MARL
- DVSOD: RGB-D Video Salient Object Detection
- DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting
- DynaDojo: An Extensible Platform for Benchmarking Scaling in Dynamical System Identification
- Dynamically Masked Discriminator for GANs
- Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers
- Dynamic Non-monotone Submodular Maximization
- Dynamic Personalized Federated Learning with Adaptive Differential Privacy
- Dynamic Pricing and Learning with Bayesian Persuasion
- Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing
- Dynamic Regret of Adversarial Linear Mixture MDPs
- Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies
- Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks
- Dynamic Sparsity Is Channel-Level Sparsity Learner
- Dynamic Tensor Decomposition via Neural Diffusion-Reaction Processes
- Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes
- DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets
- DynPoint: Dynamic Neural Point For View Synthesis
- E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning
- Easy Bayesian Transfer Learning with Informative Priors
- Easy Learning from Label Proportions
- ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram
- Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusion
- Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes
- EDGI: Equivariant Diffusion for Planning with Embodied Agents
- Effective Bayesian Heteroscedastic Regression with Deep Neural Networks
- Effective Human-AI Teams via Learned Natural Language Rules and Onboarding
- Effectively Learning Initiation Sets in Hierarchical Reinforcement Learning
- Effective Robustness against Natural Distribution Shifts for Models with Different Training Data
- Effective Targeted Attacks for Adversarial Self-Supervised Learning
- Efficient Activation Function Optimization through Surrogate Modeling
- Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing
- Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning
- Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection
- Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards
- Efficient Batched Algorithm for Contextual Linear Bandits with Large Action Space via Soft Elimination
- Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks
- Efficient Beam Tree Recursion
- Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks
- Efficient Diffusion Policies For Offline Reinforcement Learning
- Efficient Equivariant Transfer Learning from Pretrained Models
- Efficient Exploration in Continuous-time Model-based Reinforcement Learning
- Efficient Hyper-parameter Optimization with Cubic Regularization
- Efficient Learning of Linear Graph Neural Networks via Node Subsampling
- Efficient Low-rank Backpropagation for Vision Transformer Adaptation
- Efficiently incorporating quintuple interactions into geometric deep learning force fields
- Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimization
- Efficient Model-Free Exploration in Low-Rank MDPs
- Efficient Neural Music Generation
- Efficient Online Clustering with Moving Costs
- Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents
- Efficient Potential-based Exploration in Reinforcement Learning using Inverse Dynamic Bisimulation Metric
- Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations
- Efficient Robust Bayesian Optimization for Arbitrary Uncertain inputs
- Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models
- Efficient Subgame Refinement for Extensive-form Games
- Efficient Symbolic Policy Learning with Differentiable Symbolic Expression
- Efficient Testable Learning of Halfspaces with Adversarial Label Noise
- Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction
- Efficient Training of Energy-Based Models Using Jarzynski Equality
- Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks
- Ego4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities
- Egocentric Planning for Scalable Embodied Task Achievement
- EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding
- EgoEnv: Human-centric environment representations from egocentric video
- EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding
- EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset
- EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models
- EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images
- EICIL: Joint Excitatory Inhibitory Cycle Iteration Learning for Deep Spiking Neural Networks
- Elastic Decision Transformer
- ELDEN: Exploration via Local Dependencies
- Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback
- Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization
- Eliminating Domain Bias for Federated Learning in Representation Space
- Embedding Space Interpolation Beyond Mini-Batch, Beyond Pairs and Beyond Examples
- EMBERSim: A Large-Scale Databank for Boosting Similarity Search in Malware Analysis
- EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought
- Embracing the chaos: analysis and diagnosis of numerical instability in variational flows
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification
- Emergence of Shape Bias in Convolutional Neural Networks through Activation Sparsity
- Emergent and Predictable Memorization in Large Language Models
- Emergent Communication for Rules Reasoning
- Emergent Communication in Interactive Sketch Question Answering
- Emergent Correspondence from Image Diffusion
- EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learning
- Empowering Collaborative Filtering with Principled Adversarial Contrastive Loss
- Empowering Convolutional Neural Nets with MetaSin Activation
- Encoding Human Behavior in Information Design through Deep Learning
- Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency
- End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics
- End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes
- Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models
- Energy-based learning algorithms for analog computing: a comparative study
- Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach
- Energy-Based Sliced Wasserstein Distance
- Energy Discrepancies: A Score-Independent Loss for Energy-Based Models
- Energy-Efficient Scheduling with Predictions
- Energy Guided Diffusion for Generating Neurally Exciting Images
- Energy Transformer
- Enhancing Adaptive History Reserving by Spiking Convolutional Block Attention Module in Recurrent Neural Networks
- Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization
- Enhancing Adversarial Robustness via Score-Based Optimization
- Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning
- Enhancing Knowledge Transfer for Task Incremental Learning with Data-free Subnetwork
- Enhancing Minority Classes by Mixing: An Adaptative Optimal Transport Approach for Long-tailed Classification
- Enhancing Motion Deblurring in High-Speed Scenes with Spike Streams
- Enhancing Robot Program Synthesis Through Environmental Context
- Enhancing Sharpness-Aware Optimization Through Variance Suppression
- Enhancing User Intent Capture in Session-Based Recommendation with Attribute Patterns
- Ensemble-based Deep Reinforcement Learning for Vehicle Routing Problems under Distribution Shift
- Entropic Neural Optimal Transport via Diffusion Processes
- Entropy-based Training Methods for Scalable Neural Implicit Samplers
- Entropy-dissipation Informed Neural Network for McKean-Vlasov Type PDEs
- Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization
- EPIC Fields: Marrying 3D Geometry and Video Understanding
- Epidemic Learning: Boosting Decentralized Learning with Randomized Communication
- Episodic Multi-Task Learning with Heterogeneous Neural Processes
- Epistemic Neural Networks
- Equal Opportunity of Coverage in Fair Regression
- Equivariant Adaptation of Large Pretrained Models
- Equivariant flow matching
- Equivariant Flow Matching with Hybrid Probability Transport for 3D Molecule Generation
- Equivariant Neural Operator Learning with Graphon Convolution
- Equivariant Neural Simulators for Stochastic Spatiotemporal Dynamics
- Equivariant Single View Pose Prediction Via Induced and Restriction Representations
- Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics
- Error Bounds for Learning with Vector-Valued Random Features
- Error Discovery By Clustering Influence Embeddings
- Errors-in-variables Fr\'echet Regression with Low-rank Covariate Approximation
- ESSEN: Improving Evolution State Estimation for Temporal Networks using Von Neumann Entropy
- Ess-InfoGAIL: Semi-supervised Imitation Learning from Imbalanced Demonstrations
- Estimating and Controlling for Equalized Odds via Sensitive Attribute Predictors
- Estimating Causal Effects Identifiable from a Combination of Observations and Experiments
- Estimating Generic 3D Room Structures from 2D Annotations
- Estimating Koopman operators with sketching to provably learn large scale dynamical systems
- Estimating Noise Correlations Across Continuous Conditions With Wishart Processes
- Estimating Propensity for Causality-based Recommendation without Exposure Data
- Estimating Riemannian Metric with Noise-Contaminated Intrinsic Distance
- Estimating the Rate-Distortion Function by Wasserstein Gradient Descent
- Ethical Considerations for Responsible Data Curation
- Euler-Lagrange Analysis of Generative Adversarial Networks
- Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning
- Evaluating and Inducing Personality in Pre-trained Language Models
- Evaluating Cognitive Maps and Planning in Large Language Models with CogEval
- Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking
- Evaluating Neuron Interpretation Methods of NLP Models
- Evaluating Open-QA Evaluation
- Evaluating Post-hoc Explanations for Graph Neural Networks via Robustness Analysis
- Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts
- Evaluating Self-Supervised Learning for Molecular Graph Embeddings
- Evaluating the Moral Beliefs Encoded in LLMs
- Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance
- Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Events
- Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction
- EV-Eye: Rethinking High-frequency Eye Tracking through the Lenses of Event Cameras
- EvoFed: Leveraging Evolutionary Strategies for Communication-Efficient Federated Learning
- Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing
- Evolving Connectivity for Recurrent Spiking Neural Networks
- Evolving Standardization for Continual Domain Generalization over Temporal Drift
- EvoPrompting: Language Models for Code-Level Neural Architecture Search
- Exact Bayesian Inference on Discrete Models via Probability Generating Functions: A Probabilistic Programming Approach
- Exact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Models
- Exact Optimality of Communication-Privacy-Utility Tradeoffs in Distributed Mean Estimation
- Exact recovery and Bregman hard clustering of node-attributed Stochastic Block Model
- Exact Representation of Sparse Networks with Symmetric Nonnegative Embeddings
- Exact Verification of ReLU Neural Control Barrier Functions
- Expanding Small-Scale Datasets with Guided Imagination
- Experimental Designs for Heteroskedastic Variance
- Experiment Planning with Function Approximation
- Expert load matters: operating networks at high accuracy and low manual effort
- Explainable and Efficient Randomized Voting Rules
- Explainable Brain Age Prediction using coVariance Neural Networks
- Explain Any Concept: Segment Anything Meets Concept-Based Explanation
- Explaining Predictive Uncertainty with Information Theoretic Shapley Values
- Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Models
- Explaining V1 Properties with a Biologically Constrained Deep Learning Architecture
- Exploiting Connections between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models
- Exploiting Contextual Objects and Relations for 3D Visual Grounding
- Exploiting Correlated Auxiliary Feedback in Parameterized Bandits
- Exploiting hidden structures in non-convex games for convergence to Nash equilibrium
- Explore In-Context Learning for 3D Point Cloud Understanding
- Explore to Generalize in Zero-Shot RL
- Exploring and Interacting with the Set of Good Sparse Generalized Additive Models
- Exploring Diverse In-Context Configurations for Image Captioning
- Exploring Geometry of Blind Spots in Vision models
- Exploring Loss Functions for Time-based Training Strategy in Spiking Neural Networks
- Exploring Question Decomposition for Zero-Shot VQA
- Exploring the Optimal Choice for Generative Processes in Diffusion Models: Ordinary vs Stochastic Differential Equations
- Exploring Why Object Recognition Performance Degrades Across Income Levels and Geographies with Factor Annotations
- Exponential Lower Bounds for Fictitious Play in Potential Games
- Exponentially Convergent Algorithms for Supervised Matrix Factorization
- Exposing Attention Glitches with Flip-Flop Language Modeling
- Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
- Expressive probabilistic sampling in recurrent neural networks
- Expressive Sign Equivariant Networks for Spectral Geometric Learning
- Expressivity-Preserving GNN Simulation
- ExPT: Synthetic Pretraining for Few-Shot Experimental Design
- Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman
- Extensible Prompts for Language Models on Zero-shot Language Style Customization
- Extracting Reward Functions from Diffusion Models
- Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion Models
- Extremal Domain Translation with Neural Optimal Transport
- FABind: Fast and Accurate Protein-Ligand Binding
- FaceComposer: A Unified Model for Versatile Facial Content Creation
- FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models
- FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy
- Face Reconstruction from Facial Templates by Learning Latent Space of a Generator Network
- Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes
- Facing Off World Model Backbones: RNNs, Transformers, and S4
- Factorized Contrastive Learning: Going Beyond Multi-view Redundancy
- Failure-Aware Gaussian Process Optimization with Regret Bounds
- Fair Adaptive Experiments
- Fair Allocation of Indivisible Chores: Beyond Additive Costs
- Fair Canonical Correlation Analysis
- Fair Graph Distillation
- FairLISA: Fair User Modeling with Limited Sensitive Attributes Information
- Fairly Recommending with Social Attributes: A Flexible and Controllable Optimization Approach
- Fairness Aware Counterfactuals for Subgroups
- Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments
- Fairness-guided Few-shot Prompting for Large Language Models
- Fair, Polylog-Approximate Low-Cost Hierarchical Clustering
- Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint
- Faith and Fate: Limits of Transformers on Compositionality
- False Discovery Proportion control for aggregated Knockoffs
- FAMO: Fast Adaptive Multitask Optimization
- Fantastic Robustness Measures: The Secrets of Robust Generalization
- Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training
- FAST: a Fused and Accurate Shrinkage Tree for Heterogeneous Treatment Effects Estimation
- Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms
- Fast and Simple Spectral Clustering in Theory and Practice
- Fast Approximation of Similarity Graphs with Kernel Density Estimation
- Fast Asymptotically Optimal Algorithms for Non-Parametric Stochastic Bandits
- Fast Attention Over Long Sequences With Dynamic Sparse Flash Attention
- Fast Attention Requires Bounded Entries
- Fast Bellman Updates for Wasserstein Distributionally Robust MDPs
- Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions
- Faster approximate subgraph counts with privacy
- Faster Differentially Private Convex Optimization via Second-Order Methods
- Faster Discrete Convex Function Minimization with Predictions: The M-Convex Case
- Faster Margin Maximization Rates for Generic Optimization Methods
- Faster Query Times for Fully Dynamic $k$-Center Clustering with Outliers
- Faster Relative Entropy Coding with Greedy Rejection Coding
- Fast Exact Leverage Score Sampling from Khatri-Rao Products with Applications to Tensor Decomposition
- Fast Model DeBias with Machine Unlearning
- Fast Online Changepoint Detection via Functional Pruning CUSUM Statistics
- Fast Optimal Locally Private Mean Estimation via Random Projections
- Fast Optimal Transport through Sliced Generalized Wasserstein Geodesics
- Fast Partitioned Learned Bloom Filter
- Fast Projected Newton-like Method for Precision Matrix Estimation under Total Positivity
- Fast Rank-1 Lattice Targeted Sampling for Black-box Optimization
- Fast Scalable and Accurate Discovery of DAGs Using the Best Order Score Search and Grow Shrink Trees
- Fast Trainable Projection for Robust Fine-tuning
- FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning
- Feature Adaptation for Sparse Linear Regression
- Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning
- Feature Learning for Interpretable, Performant Decision Trees
- Feature-Learning Networks Are Consistent Across Widths At Realistic Scales
- Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond
- Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples
- Feature Selection in the Contrastive Analysis Setting
- FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
- Fed-CO$_{2}$: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning
- Federated Compositional Deep AUC Maximization
- Federated Conditional Stochastic Optimization
- Federated Learning via Meta-Variational Dropout
- Federated Learning with Bilateral Curation for Partially Class-Disjoint Data
- Federated Learning with Client Subsampling, Data Heterogeneity, and Unbounded Smoothness: A New Algorithm and Lower Bounds
- Federated Learning with Manifold Regularization and Normalized Update Reaggregation
- Federated Linear Bandits with Finite Adversarial Actions
- Federated Multi-Objective Learning
- Federated Spectral Clustering via Secure Similarity Reconstruction
- Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense
- FedFed: Feature Distillation against Data Heterogeneity in Federated Learning
- FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning
- FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networks
- Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer
- FedL2P: Federated Learning to Personalize
- FedNAR: Federated Optimization with Normalized Annealing Regularization
- FELM: Benchmarking Factuality Evaluation of Large Language Models
- FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation
- Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration
- Few-shot Generation via Recalling Brain-Inspired Episodic-Semantic Memory
- FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation
- FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations
- FIND: A Function Description Benchmark for Evaluating Interpretability Methods
- Finding Counterfactually Optimal Action Sequences in Continuous State Spaces
- Finding Local Minima Efficiently in Decentralized Optimization
- Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning
- Finding Safe Zones of Markov Decision Processes Policies
- Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation
- Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator
- Fine-grained Expressivity of Graph Neural Networks
- Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
- Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering
- Fine-Grained Theoretical Analysis of Federated Zeroth-Order Optimization
- Fine-Grained Visual Prompting
- FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing
- Fine-Tuning Language Models with Just Forward Passes
- Finite Population Regression Adjustment and Non-asymptotic Guarantees for Treatment Effect Estimation
- Finite-Time Analysis of Single-Timescale Actor-Critic
- Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation
- Finite-Time Logarithmic Bayes Regret Upper Bounds
- FIRAL: An Active Learning Algorithm for Multinomial Logistic Regression
- First- and Second-Order Bounds for Adversarial Linear Contextual Bandits
- First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities
- First Order Stochastic Optimization with Oblivious Noise
- Fitting trees to $\ell_1$-hyperbolic distances
- Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs
- FLAIR : a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery
- FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning
- Flat Seeking Bayesian Neural Networks
- Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning
- Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models
- Flow-Attention-based Spatio-Temporal Aggregation Network for 3D Mask Detection
- Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection
- FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow
- Flow Factorized Representation Learning
- Flow Matching for Scalable Simulation-Based Inference
- Flow: Per-instance Personalized Federated Learning
- FlowPG: Action-constrained Policy Gradient with Normalizing Flows
- FLSL: Feature-level Self-supervised Learning
- FLuID: Mitigating Stragglers in Federated Learning using Invariant Dropout
- FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space
- Focused Transformer: Contrastive Training for Context Scaling
- Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation
- Focus Your Attention when Few-Shot Classification
- Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts
- FORB: A Flat Object Retrieval Benchmark for Universal Image Embedding
- ForecastPFN: Synthetically-Trained Zero-Shot Forecasting
- ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning
- Formalizing locality for normative synaptic plasticity models
- Formulating Discrete Probability Flow Through Optimal Transport
- For SALE: State-Action Representation Learning for Deep Reinforcement Learning
- Foundation Model is Efficient Multimodal Multitask Model Selector
- Foundation Models for Decision Making
- FouriDown: Factoring Down-Sampling into Shuffling and Superposing
- FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective
- FourierHandFlow: Neural 4D Hand Representation Using Fourier Query Flow
- f-Policy Gradients: A General Framework for Goal-Conditioned RL using f-Divergences
- Fractal Landscapes in Policy Optimization
- Fragment-based Pretraining and Finetuning on Molecular Graphs
- Framework and Benchmarks for Combinatorial and Mixed-variable Bayesian Optimization
- Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator
- FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models
- Frequency Domain-Based Dataset Distillation
- Frequency-domain MLPs are More Effective Learners in Time Series Forecasting
- Frequency-Enhanced Data Augmentation for Vision-and-Language Navigation
- From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Models to Pre-trained Machine Reader
- From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion
- From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces
- From Tempered to Benign Overfitting in ReLU Neural Networks
- From Trainable Negative Depth to Edge Heterophily in Graphs
- From ViT Features to Training-free Video Object Segmentation via Streaming-data Mixture Models
- Front-door Adjustment Beyond Markov Equivalence with Limited Graph Knowledge
- Full-Atom Protein Pocket Design via Iterative Refinement
- Fully Dynamic $k$-Clustering in $\tilde O(k)$ Update Time
- Functional Equivalence and Path Connectivity of Reducible Hyperbolic Tangent Networks
- Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration
- Functional Renyi Differential Privacy for Generative Modeling
- Function Space Bayesian Pseudocoreset for Bayesian Neural Networks
- Fundamental Limits and Tradeoffs in Invariant Representation Learning
- Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications
- Future-Dependent Value-Based Off-Policy Evaluation in POMDPs
- Gacs-Korner Common Information Variational Autoencoder
- GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection
- GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection
- GALOPA: Graph Transport Learning with Optimal Plan Alignment
- Game Solving with Online Fine-Tuning
- GAN You See Me? Enhanced Data Reconstruction Attacks against Split Inference
- GAUCHE: A Library for Gaussian Processes in Chemistry
- Gaussian Differential Privacy on Riemannian Manifolds
- Gaussian Membership Inference Privacy
- Gaussian Mixture Solvers for Diffusion Models
- Gaussian Partial Information Decomposition: Bias Correction and Application to High-dimensional Data
- Gaussian Process Probes (GPP) for Uncertainty-Aware Probing
- Gaze Meets ML
- Generalised f-Mean Aggregation for Graph Neural Networks
- Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations
- Generalizable One-shot 3D Neural Head Avatar
- Generalization bounds for neural ordinary differential equations and deep residual networks
- Generalization in Planning (GenPlan '23)
- Generalization in the Face of Adaptivity: A Bayesian Perspective
- Generalized Bayesian Inference for Scientific Simulators via Amortized Cost Estimation
- Generalized Belief Transport
- Generalized equivalences between subsampling and ridge regularization
- Generalized Information-theoretic Multi-view Clustering
- Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models
- Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation
- Generalized test utilities for long-tail performance in extreme multi-label classification
- Generalized Weighted Path Consistency for Mastering Atari Games
- Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems
- Generalizing Nonlinear ICA Beyond Structural Sparsity
- General Munchausen Reinforcement Learning with Tsallis Kullback-Leibler Divergence
- Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion
- Generating Behaviorally Diverse Policies with Latent Diffusion Models
- Generating Images with Multimodal Language Models
- Generating QM1B with PySCF$_{\text{IPU}}$
- Generative AI and Biology (GenBio@NeurIPS2023)
- Generative AI for Education (GAIED): Advances, Opportunities, and Challenges
- Generative Category-level Object Pose Estimation via Diffusion Models
- Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transport
- Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning
- Generative Neural Fields by Mixtures of Neural Implicit Functions
- Generator Born from Classifier
- Generator Identification for Linear SDEs with Additive and Multiplicative Noise
- GenEval: An object-focused framework for evaluating text-to-image alignment
- GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image
- GenS: Generalizable Neural Surface Reconstruction from Multi-View Images
- GEO-Bench: Toward Foundation Models for Earth Monitoring
- GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization
- GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition
- Geodesic Multi-Modal Mixup for Robust Fine-Tuning
- Geometric Algebra Transformer
- Geometric Analysis of Matrix Sensing over Graphs
- Geometric Neural Diffusion Processes
- Geometric Transformer with Interatomic Positional Encoding
- Geometry-Aware Adaptation for Pretrained Models
- Geometry-Informed Neural Operator for Large-Scale 3D PDEs
- GeoPhy: Differentiable Phylogenetic Inference via Geometric Gradients of Tree Topologies
- GeoTMI: Predicting Quantum Chemical Property with Easy-to-Obtain Geometry via Positional Denoising
- GEQ: Gaussian Kernel Inspired Equilibrium Models
- Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design
- GEX: A flexible method for approximating influence via Geometric Ensemble
- Gigastep - One Billion Steps per Second Multi-agent Reinforcement Learning
- GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
- Glance and Focus: Memory Prompting for Multi-Event Video Question Answering
- GLEMOS: Benchmark for Instantaneous Graph Learning Model Selection
- GLIME: General, Stable and Local LIME Explanation
- Global Convergence Analysis of Local SGD for Two-layer Neural Network without Overparameterization
- Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
- Global Identifiability of $\ell_1$-based Dictionary Learning via Matrix Volume Optimization
- Globally injective and bijective neural operators
- Globally solving the Gromov-Wasserstein problem for point clouds in low dimensional Euclidean spaces
- Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch
- Global Optimality in Bivariate Gradient-based DAG Learning
- Global Structure-Aware Diffusion Process for Low-light Image Enhancement
- Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data
- GLOBER: Coherent Non-autoregressive Video Generation via GLOBal Guided Video DecodER
- GloptiNets: Scalable Non-Convex Optimization with Certificates
- GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces
- GlyphControl: Glyph Conditional Control for Visual Text Generation
- GMSF: Global Matching Scene Flow
- GNeSF: Generalizable Neural Semantic Fields
- GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels
- Goal-conditioned Offline Planning from Curious Exploration
- Goal-Conditioned Predictive Coding for Offline Reinforcement Learning
- Goal-Conditioned Reinforcement Learning
- Goal Driven Discovery of Distributional Differences via Language Descriptions
- Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity
- Going beyond persistent homology using persistent homology
- Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism
- Governance & Accountability for ML: Existing Tools, Ongoing Efforts, & Future Directions
- GPEX, A Framework For Interpreting Artificial Neural Networks
- GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction
- GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks
- Gradient-Based Feature Learning under Structured Data
- Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy
- Gradient Flossing: Improving Gradient Descent through Dynamic Control of Jacobians
- Gradient-Free Kernel Stein Discrepancy
- Gradient Informed Proximal Policy Optimization
- GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients
- Grammar Prompting for Domain-Specific Language Generation with Large Language Models
- GRAND-SLAMIN’ Interpretable Additive Modeling with Structural Constraints
- Granger Components Analysis: Unsupervised learning of latent temporal dependencies
- GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph
- Graph Clustering with Graph Neural Networks
- Graph Contrastive Learning with Stable and Scalable Spectral Encoding
- Graph Convolutional Kernel Machine versus Graph Convolutional Networks
- Graph Denoising Diffusion for Inverse Protein Folding
- Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling
- GraphMP: Graph Neural Network-based Motion Planning with Efficient Graph Search
- Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis
- Graph of Circuits with GNN for Exploring the Optimal Design Space
- GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation
- Graph-Structured Gaussian Processes for Transferable Graph Learning
- Grassmann Manifold Flows for Stable Shape Generation
- Greatness in Simplicity: Unified Self-Cycle Consistency for Parser-Free Virtual Try-On
- Greedy Poisson Rejection Sampling
- Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing
- Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents
- Grounding Neural Inference with Satisfiability Modulo Theories
- Group Fairness in Peer Review
- Group Robust Classification Without Any Group Information
- GSLB: The Graph Structure Learning Benchmark
- Guarantees for Self-Play in Multiplayer Games via Polymatrix Decomposability
- Guide Your Agent with Adaptive Multimodal Rewards
- Guiding Large Language Models via Directional Stimulus Prompting
- Guiding The Last Layer in Federated Learning with Pre-Trained Models
- GUST: Combinatorial Generalization by Unsupervised Grouping with Neuronal Coherence
- H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
- H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection
- H3T: Efficient Integration of Memory Optimization and Parallelism for Large-scale Transformer Training
- Handling Data Heterogeneity via Architectural Design for Federated Visual Recognition
- HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
- Hardness of Low Rank Approximation of Entrywise Transformed Matrix Products
- Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
- Hardware Resilience Properties of Text-Guided Image Classifiers
- Harnessing Hard Mixed Samples with Decoupled Regularizer
- Harnessing the power of choices in decision tree learning
- HASSOD: Hierarchical Adaptive Self-Supervised Object Detection
- Have it your way: Individualized Privacy Assignment for DP-SGD
- HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding
- HeadSculpt: Crafting 3D Head Avatars with Text
- Heavy Tails in ML: Structure, Stability, Dynamics
- HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds
- HiBug: On Human-Interpretable Model Debug
- Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
- Hierarchical Adaptive Value Estimation for Multi-modal Visual Reinforcement Learning
- Hierarchical clustering with dot products recovers hidden tree structure
- Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality
- Hierarchical Gaussian Mixture based Task Generative Model for Robust Meta-Learning
- Hierarchical Integration Diffusion Model for Realistic Image Deblurring
- Hierarchically Gated Recurrent Neural Network for Sequence Modeling
- Hierarchical Multi-Agent Skill Discovery
- Hierarchical Open-vocabulary Universal Image Segmentation
- Hierarchical Randomized Smoothing
- Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration
- Hierarchical VAEs provide a normative account of motion processing in the primate brain
- Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection
- High-dimensional Asymptotics of Denoising Autoencoders
- High-dimensional Contextual Bandit Problem without Sparsity
- High dimensional, tabular deep learning with an auxiliary knowledge graph
- Higher-Order Uncoupled Dynamics Do Not Lead to Nash Equilibrium - Except When They Do
- High-Fidelity Audio Compression with Improved RVQGAN
- High Precision Causal Model Evaluation with Conditional Randomization
- H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation
- HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation
- HIQL: Offline Goal-Conditioned RL with Latent States as Actions
- History Filtering in Imperfect Information Games: Algorithms and Complexity
- H-nobs: Achieving Certified Fairness and Robustness in Distributed Learning on Heterogeneous Datasets
- HOH: Markerless Multimodal Human-Object-Human Handover Dataset with Large Object Count
- Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks
- Holistic Evaluation of Text-to-Image Models
- Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data
- Homotopy-based training of NeuralODEs for accurate dynamics discovery
- Honesty Is the Best Policy: Defining and Mitigating AI Deception
- Horospherical Decision Boundaries for Large Margin Classification in Hyperbolic Space
- HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception
- How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception
- How a Student becomes a Teacher: learning and forgetting through Spectral methods
- How Does Adaptive Optimization Impact Local Neural Network Geometry?
- How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model
- How do Minimum-Norm Shallow Denoisers Look in Function Space?
- How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources
- How hard are computer vision datasets? Calibrating dataset difficulty to viewing time
- How many samples are needed to leverage smoothness?
- How Re-sampling Helps for Long-Tail Learning?
- How to Data in Datathons
- How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization
- How to Scale Your EMA
- How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budget
- How to Turn Your Knowledge Graph Embeddings into Generative Models
- How to Work With Real Humans in Human-AI Systems
- HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text
- HT-Step: Aligning Instructional Articles with How-To Videos
- HubRouter: Learning Global Routing via Hub Generation and Pin-hub Connection
- HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
- Human-Aligned Calibration for AI-Assisted Decision Making
- Human-Guided Complexity-Controlled Abstractions
- Human-in-the-Loop Optimization for Deep Stimulus Encoding in Visual Prostheses
- Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language
- Humans in Kitchens: A Dataset for Multi-Person Human Motion Forecasting with Scene Context
- Human spatiotemporal pattern learning as probabilistic program synthesis
- Hybrid Policy Optimization from Imperfect Demonstrations
- Hybrid Search for Efficient Planning with Completeness Guarantees
- HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution
- Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approach
- Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels
- Hyperbolic VAE via Latent Gaussian Distributions
- Hyper-HMM: aligning human brains and semantic features in a common latent event space
- Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks
- Hyper-Skin: A Hyperspectral Dataset for Reconstructing Facial Skin-Spectra from RGB Images
- Hypervolume Maximization: A Geometric View of Pareto Set Learning
- HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork
- HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models
- Hypothesis Selection with Memory Constraints
- HyTrel: Hypergraph-enhanced Tabular Data Representation Learning
- IBA: Towards Irreversible Backdoor Attacks in Federated Learning
- I Can’t Believe It’s Not Better (ICBINB): Failure Modes in the Age of Foundation Models
- ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets
- IDEA: An Invariant Perspective for Efficient Domain Adaptive Image Retrieval
- Idempotent Learned Image Compression with Right-Inverse
- Identifiability Guarantees for Causal Disentanglement from Soft Interventions
- Identifiable Contrastive Learning with Automatic Feature Importance Discovery
- Identification of Nonlinear Latent Hierarchical Models
- IDRNet: Intervention-Driven Relation Network for Semantic Segmentation
- IEBins: Iterative Elastic Bins for Monocular Depth Estimation
- Ignorance is Bliss: Robust Control via Information Gating
- ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation
- Image Captioners Are Scalable Vision Learners Too
- ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification
- ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
- Imagine That! Abstract-to-Intricate Text-to-Image Synthesis with Scene Graph Hallucination Diffusion
- Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models
- Imbalanced Mixed Linear Regression
- Imitation Learning from Imperfection: Theoretical Justifications and Algorithms
- Imitation Learning from Vague Feedback
- Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability
- Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data
- Implicit Bias of (Stochastic) Gradient Descent for Rank-1 Linear Neural Network
- Implicit Contrastive Representation Learning with Guided Stop-gradient
- Implicit Convolutional Kernels for Steerable CNNs
- Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis
- Implicit Manifold Gaussian Process Regression
- Implicit Regularization in Over-Parameterized Support Vector Machine
- Implicit Transfer Operator Learning: Multiple Time-Resolution Models for Molecular Dynamics
- Implicit variance regularization in non-contrastive SSL
- Implicit Variational Inference for High-Dimensional Posteriors
- IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL
- Importance-aware Co-teaching for Offline Model-based Optimization
- Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning
- IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI
- Im-Promptu: In-Context Composition from Image Prompts
- Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
- Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning
- Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition
- Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms
- Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates
- Improved Convergence in High Probability of Clipped Gradient Methods with Heavy Tailed Noise
- Improved Frequency Estimation Algorithms with and without Predictions
- Improvements on Uncertainty Quantification for Node Classification via Distance Based Regularization
- Improving Adversarial Robustness via Information Bottleneck Distillation
- Improving Adversarial Transferability via Intermediate-level Perturbation Decay
- Improving CLIP Training with Language Rewrites
- Improving Compositional Generalization using Iterated Learning and Simplicial Embeddings
- Improving *day-ahead* Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context
- Improving Diffusion-Based Image Synthesis with Context Prediction
- Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data
- Improving Graph Matching with Positional Reconstruction Encoder-Decoder Network
- Improving Language Plasticity via Pretraining with Active Forgetting
- Improving multimodal datasets with image captioning
- Improving neural network representations using human similarity judgments
- Improving Robustness with Adaptive Weight Decay
- Improving Self-supervised Molecular Representation Learning using Persistent Homology
- Improving the Knowledge Gradient Algorithm
- Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners
- Incentives in Federated Learning: Equilibria, Dynamics, and Mechanisms for Welfare Maximization
- Incentives in Private Collaborative Machine Learning
- Incentivized Communication for Federated Bandits
- Incentivizing Honesty among Competitors in Collaborative Learning and Optimization
- Incomplete Multimodality-Diffused Emotion Recognition
- Inconsistency, Instability, and Generalization Gap of Deep Neural Network Training
- In-Context Impersonation Reveals Large Language Models' Strengths and Biases
- In-Context Learning Unlocked for Diffusion Models
- In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer
- Individual Arbitrariness and Group Fairness
- Individualized Dosing Dynamics via Neural Eigen Decomposition
- Inference for Gaussian Processes with Matern Covariogram on Compact Riemannian Manifolds
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
- Inferring Hybrid Neural Fluid Fields from Videos
- Inferring the Future by Imagining the Past
- InfoCD: A Contrastive Chamfer Distance Loss for Point Cloud Completion
- InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding
- Information Design in Multi-Agent Reinforcement Learning
- Information Geometry of the Retinal Representation Manifold
- Information-guided Planning: An Online Approach for Partially Observable Problems
- Information Maximization Perspective of Orthogonal Matching Pursuit with Applications to Explainable AI
- Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills
- Information Theoretic Lower Bounds for Information Theoretic Upper Bounds
- Information-Theoretic Principles in Cognitive Systems (InfoCog)
- Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks
- Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks
- Injecting Multimodal Information into Rigid Protein Docking via Bi-level Optimization
- Inner-Outer Aware Reconstruction Model for Monocular 3D Scene Reconstruction
- Inner Product-based Neural Network Similarity
- InsActor: Instruction-driven Physics-based Characters
- Inserting Anybody in Diffusion Models via Celeb Basis
- INSPECT: A Multimodal Dataset for Patient Outcome Prediction of Pulmonary Embolisms
- InstanT: Semi-supervised Learning with Instance-dependent Thresholds
- InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
- Instructing Goal-Conditioned Reinforcement Learning Agents with Temporal Logic Objectives
- Instruction Tuning and Instruction Following
- Integration-free Training for Spatio-temporal Multimodal Covariate Deep Kernel Point Processes
- Intelligent Knee Sleeves: A Real-time Multimodal Dataset for 3D Lower Body Motion Estimation Using Smart Textile
- Intensity Profile Projection: A Framework for Continuous-Time Representation Learning for Dynamic Networks
- Interaction Measures, Partition Lattices and Kernel Tests for High-Order Interactions
- Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision
- Interactive Visual Reasoning under Uncertainty
- InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback
- Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
- Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction
- Interpretable Graph Networks Formulate Universal Algebra Conjectures
- Interpretable Prototype-based Graph Information Bottleneck
- Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach
- Interpreting Unsupervised Anomaly Detection in Security via Rule Extraction
- Intervention Generalization: A View from Factor Graph Models
- Into the LAION’s Den: Investigating Hate in Multimodal Datasets
- Into the Single Cell Multiverse: an End-to-End Dataset for Procedural Knowledge Extraction in Biomedical Texts
- Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP
- Intriguing Properties of Quantization at Scale
- Intrinsically Motivated Open-ended Learning (IMOL) Workshop
- Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts
- Intrinsic Gaussian Process on Unknown Manifolds with Probabilistic Metrics
- Invariant Anomaly Detection under Distribution Shifts: A Causal Perspective
- Invariant Learning via Probability of Sufficient and Necessary Causes
- Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation
- Inverse Preference Learning: Preference-based RL without a Reward Function
- Inverse Reinforcement Learning with the Average Reward Criterion
- Investigating how ReLU-networks encode symmetries
- IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers
- iSCAN: Identifying Causal Mechanism Shifts among Nonlinear Additive Noise Models
- Is Distance Matrix Enough for Geometric Deep Learning?
- Is Heterogeneity Notorious? Taming Heterogeneity to Handle Test-Time Shift in Federated Learning
- Is Learning in Games Good for the Learners?
- Isometric Quotient Variational Auto-Encoders for Structure-Preserving Representation Learning
- ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns
- Is RLHF More Difficult than Standard RL? A Theoretical Perspective
- Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics
- Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
- Iteratively Learn Diverse Strategies with State Distance Information
- Iterative Reachability Estimation for Safe Reinforcement Learning
- Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels
- Jailbroken: How Does LLM Safety Training Fail?
- Jigsaw: Learning to Assemble Multiple Fractured Objects
- Joint Attribute and Model Generalization Learning for Privacy-Preserving Action Recognition
- Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network
- Joint Data-Task Generation for Auxiliary Learning
- Joint Feature and Differentiable $ k $-NN Graph Learning using Dirichlet Energy
- Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization
- Joint processing of linguistic properties in brains and language models
- Joint Prompt Optimization of Stacked LLMs using Variational Inference
- Joint Training of Deep Ensembles Fails Due to Learner Collusion
- JourneyDB: A Benchmark for Generative Image Understanding
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
- KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training
- Katakomba: Tools and Benchmarks for Data-Driven NetHack
- KD-Zero: Evolving Knowledge Distiller for Any Teacher-Student Pairs
- Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control
- Kernel-Based Tests for Likelihood-Free Hypothesis Testing
- Kernelized Cumulants: Beyond Kernel Mean Embeddings
- Kernelized Reinforcement Learning with Order Optimal Regret Bounds
- Kernel Quadrature with Randomly Pivoted Cholesky
- Kernel Stein Discrepancy thinning: a theoretical perspective of pathologies and a practical fix with regularization
- Keypoint-Augmented Self-Supervised Learning for Medical Image Segmentation with Limited Annotation
- Kiki or Bouba? Sound Symbolism in Vision-and-Language Models
- Kissing to Find a Match: Efficient Low-Rank Permutation Representation
- k-Median Clustering via Metric Embedding: Towards Better Initialization with Differential Privacy
- K-Nearest-Neighbor Local Sampling Based Conditional Independence Testing
- Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks
- Knowledge-based in silico models and dataset for the comparative evaluation of mammography AI for a range of breast characteristics, lesion conspicuities and doses
- Knowledge Diffusion for Distillation
- Knowledge Distillation for High Dimensional Search Index
- Knowledge Distillation Performs Partial Variance Reduction
- Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors
- Koopman Kernel Regression
- Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures
- KuaiSim: A Comprehensive Simulator for Recommender Systems
- Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards
- L2T-DLN: Learning to Teach with Dynamic Loss Network
- Label Correction of Crowdsourced Noisy Annotations with an Instance-Dependent Noise Transition Model
- Label-efficient Segmentation via Affinity Propagation
- Labeling Neural Representations with Inverse Recognition
- Label-Only Model Inversion Attacks via Knowledge Transfer
- Label Poisoning is All You Need
- Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels
- Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency
- LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections
- LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite
- LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas
- LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark
- LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images
- Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information
- Langevin Quasi-Monte Carlo
- Language-based Action Concept Spaces Improve Video Self-Supervised Learning
- Language-driven Scene Synthesis using Multi-conditional Diffusion Model
- Language Is Not All You Need: Aligning Perception with Language Models
- Language Model Alignment with Elastic Reset
- Language Models are Weak Learners
- Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning
- Language Models can Solve Computer Tasks
- Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
- Language Models Meet World Models
- Language Models Meet World Models: Embodied Experiences Enhance Language Models
- Language Model Tokenizers Introduce Unfairness Between Languages
- Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment
- Language Semantic Graph Guided Data-Efficient Learning
- Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding
- Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias
- Large Language Models are Fixated by Red Herrings: Exploring Creative Problem Solving and Einstellung Effect using the Only Connect Wall Dataset
- Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning
- Large Language Models Are Semi-Parametric Reinforcement Learning Agents
- Large Language Models are Visual Reasoning Coordinators
- Large Language Models Are Zero-Shot Time Series Forecasters
- Large Language Models as Commonsense Knowledge for Large-Scale Task Planning
- Large Language Models can Implement Policy Iteration
- Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering
- Large language models implicitly learn to straighten neural sentence trajectories to construct a predictive representation of natural language.
- Large Language Models of Code Fail at Completing Code with Potential Bugs
- Large language models transition from integrating across position-yoked, exponential windows to structure-yoked, power-law windows
- Large sample spectral analysis of graph-based multi-manifold clustering
- Large-Scale Distributed Learning via Private On-Device LSH
- LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting
- LART: Neural Correspondence Learning with Latent Regularization Transformer for 3D Motion Transfer
- Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
- Latent Diffusion for Language Generation
- Latent Diffusion Models: Is the Generative AI Revolution Happening in Latent Space?
- Latent exploration for Reinforcement Learning
- Latent Field Discovery in Interacting Dynamical Systems with Neural Fields
- Latent Graph Inference with Limited Supervision
- Latent SDEs on Homogeneous Spaces
- Latent Space Translation via Semantic Alignment
- Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions
- Layer-Neighbor Sampling --- Defusing Neighborhood Explosion in GNNs
- LayoutGPT: Compositional Visual Planning and Generation with Large Language Models
- LayoutPrompter: Awaken the Design Ability of Large Language Models
- L-C2ST: Local Diagnostics for Posterior Approximations in Simulation-Based Inference
- L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priors
- LD2: Scalable Heterophilous Graph Neural Network with Decoupled Embeddings
- LEACE: Perfect linear concept erasure in closed form
- LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
- Learning a 1-layer conditional generative model in total variation
- Learning Adaptive Tensorial Density Fields for Clean Cryo-ET Reconstruction
- Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback
- Learning and Collusion in Multi-unit Auctions
- Learning and processing the ordinal information of temporal sequences in recurrent neural circuits
- Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs
- Learning-Based Solutions for Inverse Problems
- Learning better with Dale’s Law: A Spectral Perspective
- Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning
- Learning Causal Models under Independent Changes
- Learning Curves for Deep Structured Gaussian Feature Models
- Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge Ensembles
- Learning Cuts via Enumeration Oracles
- Learning DAGs from Data with Few Root Causes
- Learning Dense Flow Field for Highly-accurate Cross-view Camera Localization
- Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation
- Learning Dictionary for Visual Attention
- Learning Domain-Aware Detection Head with Prompt Tuning
- Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning
- Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations
- Learning Efficient Surrogate Dynamic Models with Graph Spline Networks
- Learning Energy-based Model via Dual-MCMC Teaching
- Learning Energy-Based Prior Model with Diffusion-Amortized MCMC
- Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions
- Learning Exponential Families from Truncated Samples
- Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment
- Learning from Active Human Involvement through Proxy Value Propagation
- Learning From Biased Soft Labels
- Learning from Both Structural and Textual Knowledge for Inductive Knowledge Graph Completion
- Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection
- Learning from Visual Observation via Offline Pretrained State-to-Go Transformer
- Learning Functional Transduction
- Learning Generalizable Agents via Saliency-guided Features Decorrelation
- Learning Human Action Recognition Representations Without Real Humans
- Learning Interpretable Low-dimensional Representation via Physical Symmetry
- Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective
- Learning Invariant Molecular Representation in Latent Discrete Space
- Learning Invariant Representations of Graph Neural Networks via Cluster Generalization
- Learning Invariant Representations with a Nonparametric Nadaraya-Watson Head
- Learning Large Graph Property Prediction via Graph Segment Training
- Learning Large-Scale MTP$_2$ Gaussian Graphical Models via Bridge-Block Decomposition
- Learning Large-scale Neural Fields via Context Pruned Meta-Learning
- Learning Layer-wise Equivariances Automatically using Gradients
- Learning Linear Causal Representations from Interventions under General Nonlinear Mixing
- Learning List-Level Domain-Invariant Representations for Ranking
- Learning Mask-aware CLIP Representations for Zero-Shot Segmentation
- Learning Mixtures of Gaussians Using the DDPM Objective
- Learning Modulated Transformation in GANs
- Learning Motion Refinement for Unsupervised Face Animation
- Learning Multi-agent Behaviors from Distributed and Streaming Demonstrations
- Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priors
- Learning non-Markovian Decision-Making from State-only Sequences
- Learning Nonparametric Latent Causal Graphs with Unknown Interventions
- Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance
- Learning Provably Robust Estimators for Inverse Problems via Jittering
- Learning Rate Free Sampling in Constrained Domains
- Learning Regularized Monotone Graphon Mean-Field Games
- Learning Reliable Logical Rules with SATNet
- Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer
- Learning Re-sampling Methods with Parameter Attribution for Image Super-resolution
- Learning Robust Statistics for Simulation-based Inference under Model Misspecification
- Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction
- Learning Sample Difficulty from Pre-trained Models for Reliable Prediction
- Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping
- Learning Shared Safety Constraints from Multi-task Demonstrations
- Learning Space-Time Continuous Latent Neural PDEs from Partially Observed States
- Learning the Efficient Frontier
- Learning threshold neurons via edge of stability
- Learning Time-Invariant Representations for Individual Neurons from Population Dynamics
- Learning to Augment Distributions for Out-of-distribution Detection
- Learning to Compress Prompts with Gist Tokens
- Learning to Configure Separators in Branch-and-Cut
- Learning to Discover Skills through Guidance
- Learning To Dive In Branch And Bound
- Learning to Group Auxiliary Datasets for Molecule
- Learning to Influence Human Behavior with Offline Reinforcement Learning
- Learning to Modulate pre-trained Models in RL
- Learning to Parameterize Visual Attributes for Open-set Fine-grained Retrieval
- Learning Topology-Agnostic EEG Representations with Geometry-Aware Modeling
- Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification
- Learning to Reason and Memorize with Self-Notes
- Learning to Receive Help: Intervention-Aware Concept Embedding Models
- Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt
- Learning to Taste: A Multimodal Wine Dataset
- Learning to Tokenize for Generative Retrieval
- Learning Trajectories are Generalization Indicators
- Learning Transformer Programs
- Learning Universal Policies via Text-Guided Video Generation
- Learning Unseen Modality Interaction
- Learning via Wasserstein-Based High Probability Generalisation Bounds
- Learning Visual Prior via Generative Pre-Training
- Learning with Explanation Constraints
- Learning World Models with Identifiable Factorization
- Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery
- Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition
- LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models
- Lending Interaction Wings to Recommender Systems with Conversational Agents
- LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction
- Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets
- Leveraging Early-Stage Robustness in Diffusion Models for Efficient and High-Quality Image Synthesis
- Leveraging Locality and Robustness to Achieve Massively Scalable Gaussian Process Regression
- Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning
- Leveraging sparse and shared feature activations for disentangled representation learning
- Leveraging the two-timescale regime to demonstrate convergence of neural networks
- Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection
- Lexinvariant Language Models
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
- LICO: Explainable Models with Language-Image COnsistency
- Lie Point Symmetry and Physics-Informed Networks
- Lift Yourself Up: Retrieval-augmented Text Generation with Self-Memory
- LightSpeed: Light and Fast Neural Light Fields on Mobile Devices
- Lightweight Vision Transformer with Bidirectional Interaction
- LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios
- Likelihood-Based Diffusion Language Models
- Likelihood Ratio Confidence Sets for Sequential Decision Making
- LIMA: Less Is More for Alignment
- Limits, approximation and size transferability for GNNs on sparse graphs via graphops
- Linear Time Algorithms for k-means with Multi-Swap Local Search
- LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference
- Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment
- LinkerNet: Fragment Poses and Linker Co-Design with 3D Equivariant Diffusion
- List and Certificate Complexities in Replicable Learning
- LithoBench: Benchmarking AI Computational Lithography for Semiconductor Manufacturing
- Live Graph Lab: Towards Open, Dynamic and Real Transaction Graphs with NFT
- LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day
- LLM-Pruner: On the Structural Pruning of Large Language Models
- LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation
- LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition
- Local Convergence of Gradient Methods for Min-Max Games: Partial Curvature Generically Suffices
- Locality-Aware Generalizable Implicit Neural Representation
- Locality Sensitive Hashing in Fourier Frequency Domain For Soft Set Containment Search
- Localized Symbolic Knowledge Distillation for Visual Commonsense Models
- Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning
- Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training
- LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning
- Logarithmic-Regret Quantum Learning Algorithms for Zero-Sum Games
- LogSpecT: Feasible Graph Learning Model from Stationary Signals with Recovery Guarantees
- Lo-Hi: Practical ML Drug Discovery Benchmark
- Long Sequence Hopfield Memory
- Long-Term Fairness with Unknown Dynamics
- Lookaround Optimizer: $k$ steps around, 1 step average
- Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL
- Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videos
- Lookup Table meets Local Laplacian Filter: Pyramid Reconstruction Network for Tone Mapping
- LoRA: A Logical Reasoning Augmented Dataset for Visual Question Answering
- Loss Decoupling for Task-Agnostic Continual Learning
- Loss Dynamics of Temporal Difference Reinforcement Learning
- Lossy Image Compression with Conditional Diffusion Models
- Lovász Principle for Unsupervised Graph Representation Learning
- LOVM: Language-Only Vision Model Selection
- Lower Bounds on Adaptive Sensing for Matrix Recovery
- Low-shot Object Learning with Mutual Exclusivity Bias
- Low Tensor Rank Learning of Neural Dynamics
- LuminAIRe: Illumination-Aware Conditional Image Repainting for Lighting-Realistic Generation
- Lung250M-4B: A Combined 3D Dataset for CT- and Point Cloud-Based Intra-Patient Lung Registration
- LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching
- M$^2$Hub: Unlocking the Potential of Machine Learning for Materials Discovery
- M$^{2}$SODAI: Multi-Modal Maritime Object Detection Dataset With RGB and Hyperspectral Image Sensors
- M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models
- M5HisDoc: A Large-scale Multi-style Chinese Historical Document Analysis Benchmark
- Machine learning detects terminal singularities
- Machine Learning for Audio
- Machine Learning for Systems
- Machine Learning for Theorem Proving
- Machine Learning in Structural Biology Workshop
- Machine Learning with New Compute Paradigms
- Macro Placement by Wire-Mask-Guided Black-Box Optimization
- MADG: Margin-based Adversarial Learning for Domain Generalization
- MADLAD-400: A Multilingual And Document-Level Large Audited Dataset
- MAG-GNN: Reinforcement Learning Boosted Graph Neural Network
- MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing
- Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning
- Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation
- Making Scalable Meta Learning Practical
- Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off
- Many-body Approximation for Non-negative Tensors
- MARBLE: Music Audio Representation Benchmark for Universal Evaluation
- Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits
- Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack
- MarioGPT: Open-Ended Text2Level Generation through Large Language Models
- Markovian Sliced Wasserstein Distances: Beyond Independent Projections
- Masked Image Residual Learning for Scaling Deeper Vision Transformers
- Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction
- Masked Two-channel Decoupling Framework for Incomplete Multi-view Weak Multi-label Learning
- Mask Propagation for Efficient Video Semantic Segmentation
- Massively Multilingual Corpus of Sentiment Datasets and Multi-faceted Sentiment Classification Benchmark
- Mass-Producing Failures of Multimodal Systems with Language Models
- MATH-AI: The 3rd Workshop on Mathematical Reasoning and AI
- Mathematical Capabilities of ChatGPT
- Mathematics of Modern Machine Learning (M3L)
- MathNAS: If Blocks Have a Role in Mathematical Architecture Design
- Matrix Compression via Randomized Low Rank and Low Precision Factorization
- MAViL: Masked Audio-Video Learners
- Maximization of Average Precision for Deep Learning with Adversarial Ranking Robustness
- Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration
- Maximum Average Randomly Sampled: A Scale Free and Non-parametric Algorithm for Stochastic Bandits
- Maximum Independent Set: Self-Training through Dynamic Programming
- Maximum State Entropy Exploration using Predecessor and Successor Representations
- Max-Margin Token Selection in Attention Mechanism
- Max-Sliced Mutual Information
- May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations
- MCUFormer: Deploying Vision Tranformers on Microcontrollers with Limited Memory
- Mechanic: A Learning Rate Tuner
- Mechanism Design for Collaborative Normal Mean Estimation
- MeCo: Zero-Shot NAS with One Data and Single Forward Pass via Minimum Eigenvalue of Correlation
- Medical Imaging meets NeurIPS
- MedSat: A Public Health Dataset for England Featuring Medical Prescriptions and Satellite Imagery
- Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias
- Meek Separators and Their Applications in Targeted Causal Discovery
- Meet in the Middle: A New Pre-training Paradigm
- MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers
- MeGraph: Capturing Long-Range Interactions by Alternating Local and Hierarchical Aggregation on Multi-Scaled Graph Hierarchy
- Memory-Constrained Algorithms for Convex Optimization
- Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization
- Memory Efficient Optimizers with 4-bit States
- MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detection
- Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean
- Meta-AdaM: An Meta-Learned Adaptive Optimizer with Momentum for Few-Shot Learning
- Meta-Adapter: An Online Few-shot Learner for Vision-Language Model
- MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning
- Meta-in-context learning in large language models
- Meta-Learning Adversarial Bandit Algorithms
- Meta-learning families of plasticity rules in recurrent spiking networks using simulation-based inference
- Meta-Learning with Neural Bandit Scheduler
- Metis: Understanding and Enhancing In-Network Regular Expressions
- Metropolis Sampling for Constrained Diffusion Models
- MGDD: A Meta Generator for Fast Dataset Distillation
- MG-ViT: A Multi-Granularity Method for Compact and Efficient Vision Transformers
- Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation
- MiliPoint: A Point Cloud Dataset for mmWave Radar
- MIM4DD: Mutual Information Maximization for Dataset Distillation
- MIMEx: Intrinsic Rewards from Masked Input Modeling
- MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition
- Mind2Web: Towards a Generalist Agent for the Web
- Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
- Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks
- Minimax Forward and Backward Learning of Evolving Tasks with Performance Guarantees
- Minimax-Optimal Location Estimation
- Minimax Optimal Rate for Parameter Estimation in Multivariate Deviated Models
- Minimax Risks and Optimal Procedures for Estimation under Functional Local Differential Privacy
- Minimum Description Length and Generalization Guarantees for Representation Learning
- Minimum norm interpolation by perceptra: Explicit regularization and implicit bias
- Minimum-Risk Recalibration of Classifiers
- Mip-Grid: Anti-aliased Grid Representations for Neural Radiance Fields
- Mirror Diffusion Models for Constrained and Watermarked Generation
- Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals
- Mitigating Source Bias for Fairer Weak Supervision
- Mitigating Test-Time Bias for Fair Image Retrieval
- Mitigating the Effect of Incidental Correlations on Part-based Learning
- Mitigating the Popularity Bias of Graph Collaborative Filtering: A Dimensional Collapse Perspective
- Mixed-Initiative Multiagent Apprenticeship Learning for Human Training of Robot Teams
- Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation
- MixFormerV2: Efficient Fully Transformer Tracking
- Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
- Mixture Weight Estimation and Model Prediction in Multi-source Multi-target Domain Adaptation
- MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates
- MLFMF: Data Sets for Machine Learning for Mathematical Formalization
- MMD Aggregated Two-Sample Test
- MMD-Fuse: Learning and Combining Kernels for Two-Sample Testing Without Data Splitting
- MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing
- MMGP: a Mesh Morphing Gaussian Process-based machine learning method for regression of physical problems under nonparametrized geometrical variability
- Mnemosyne: Learning to Train Transformers with Transformers
- Mobilizing Personalized Federated Learning in Infrastructure-Less and Heterogeneous Environments via Random Walk Stochastic ADMM
- MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks
- Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder
- Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser
- Mode Connectivity in Auction Design
- Model and Feature Diversity for Bayesian Neural Networks in Mutual Learning
- Model-Based Control with Sparse Neural Dynamics
- Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms
- Model-enhanced Vector Index
- Model-Free Active Exploration in Reinforcement Learning
- Model-free Posterior Sampling via Learning Rate Randomization
- Model-Free Reinforcement Learning with the Decision-Estimation Coefficient
- Modeling and Exploiting Data Heterogeneity under Distribution Shifts
- Modeling Dynamics over Meshes with Gauge Equivariant Nonlinear Message Passing
- Modeling Human Visual Motion Processing with Trainable Motion Energy Sensing and a Self-attention Network
- Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder
- Model Shapley: Equitable Model Valuation with Black-box Access
- Model Sparsity Can Simplify Machine Unlearning
- Model Spider: Learning to Rank Pre-Trained Models Efficiently
- Modulated Neural ODEs
- Module-wise Adaptive Distillation for Multimodality Foundation Models
- Module-wise Training of Neural Networks via the Minimizing Movement Scheme
- Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion
- MomentDiff: Generative Video Moment Retrieval from Random to Real
- Moment Matching Denoising Gibbs Sampling
- Momentum Provably Improves Error Feedback!
- Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture
- Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context
- MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues
- Monte Carlo Tree Search with Boltzmann Exploration
- Moral Responsibility for AI Systems
- MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining
- Most Neural Networks Are Almost Learnable
- MotionGPT: Human Motion as a Foreign Language
- Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset
- MoVie: Visual Model-Based Policy Adaptation for View Generalization
- Mr. HiSum: A Large-scale Dataset for Video Highlight Detection and Summarization
- Multi-Agent First Order Constrained Optimization in Policy Space
- Multi-Agent Learning with Heterogeneous Linear Contextual Bandits
- Multi-Agent Meta-Reinforcement Learning: Sharper Convergence Rates with Task Similarity
- Multi-Agent Security: Security as Key to AI Safety
- Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation
- Multiclass Boosting: Simple and Intuitive Weak Learning Criteria
- Multi-Fidelity Multi-Armed Bandits Revisited
- MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation
- Multi-Head Adapter Routing for Cross-Task Generalization
- Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text
- Multimodal Clinical Benchmark for Emergency Care (MC-BEC): A Comprehensive Benchmark for Evaluating Foundation Models in Emergency Medicine
- Multimodal Deep Learning Model Unveils Behavioral Dynamics of V1 Activity in Freely Moving Mice
- Multi-Modal Inverse Constrained Reinforcement Learning from a Mixture of Demonstrations
- Multi-modal Queried Object Detection in the Wild
- MultiMoDN—Multimodal, Multi-Task, Interpretable Modular Networks
- Multinomial Logistic Regression: Asymptotic Normality on Null Covariates in High-Dimensions
- Multi-Objective Intrinsic Reward Learning for Conversational Recommender Systems
- Multi-Object Representation Learning via Feature Connectivity and Object-Centric Regularization
- Multi-Player Zero-Sum Markov Games with Networked Separable Interactions
- Multiplication-Free Transformer Training via Piecewise Affine Operations
- Multiply Robust Federated Estimation of Targeted Average Treatment Effects
- Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation
- Multi-resolution Spectral Coherence for Graph Generation with Score-based Diffusion
- Multi-scale Diffusion Denoised Smoothing
- Multi-Step Generalized Policy Improvement by Leveraging Approximate Models
- Multi-Swap k-Means++
- Multi-task Graph Neural Architecture Search with Task-aware Collaboration and Curriculum
- Multitask Learning with No Regret: from Improved Confidence Bounds to Active Learning
- Multi-task learning with summary statistics
- Multi-task Representation Learning for Pure Exploration in Bilinear Bandits
- Multi Time Scale World Models
- MultiVENT: Multilingual Videos of Events and Aligned Natural Text
- MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data
- Mutual-Information Regularized Multi-Agent Policy Iteration
- Mutual Information Regularized Offline Reinforcement Learning
- MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion
- MVDoppler: Unleashing the Power of Multi-View Doppler for MicroMotion-based Gait Classification
- NAP: Neural 3D Articulated Object Prior
- NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning
- Nash Regret Guarantees for Linear Bandits
- NAS-X: Neural Adaptive Smoothing via Twisting
- Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation
- Natural Language Instruction-following with Task-related Language Development and Translation
- NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations
- Navigating Data Heterogeneity in Federated Learning: A Semi-Supervised Federated Object Detection
- Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment
- NCDL: A Framework for Deep Learning on non-Cartesian Lattices
- Nearest Neighbour with Bandit Feedback
- Near-Linear Time Algorithm for the Chamfer Distance
- Nearly Optimal Bounds for Cyclic Forgetting
- Nearly Optimal VC-Dimension and Pseudo-Dimension Bounds for Deep Neural Network Derivatives
- Nearly Tight Bounds For Differentially Private Multiway Cut
- Near-Optimal $k$-Clustering in the Sliding Window Model
- Near-Optimal Algorithms for Gaussians with Huber Contamination: Mean Estimation and Linear Regression
- Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise
- Near-optimal learning with average Hölder smoothness
- Near Optimal Reconstruction of Spherical Harmonic Expansions
- Necessary and Sufficient Conditions for Optimal Decision Trees using Dynamic Programming
- NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks
- NeRF-IBVS: Visual Servo Based on NeRF for Visual Localization and Navigation
- NeRF Revisited: Fixing Quadrature Instability in Volume Rendering
- NetHack is Hard to Hack
- Network Regression with Graph Laplacians
- Networks are Slacking Off: Understanding Generalization Problem in Image Deraining
- Neural Algorithmic Reasoning Without Intermediate Supervision
- Neural approximation of Wasserstein distance via a universal architecture for symmetric and factorwise group invariant functions
- Neural Circuits for Fast Poisson Compressed Sensing in the Olfactory Bulb
- Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalization
- Neural Data Transformer 2: Multi-context Pretraining for Neural Spiking Activity
- Neural Fields with Hard Constraints of Arbitrary Differential Order
- Neural Foundations of Mental Simulation: Future Prediction of Latent Representations on Dynamic Scenes
- Neural Frailty Machine: Beyond proportional hazard assumption in neural survival regressions
- Neural Functional Transformers
- NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function
- Neural Graph Generation from Graph Statistics
- Neural Harmonics: Bridging Spectral Embedding and Matrix Completion in Self-Supervised Learning
- Neural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential Equations
- Neural Image Compression: Generalization, Robustness, and Spectral Biases
- Neural Injective Functions for Multisets, Measures and Graphs via a Finite Witness Theorem
- Neural Lad: A Neural Latent Dynamics Framework for Times Series Modeling
- Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization
- Neural Lighting Simulation for Urban Scenes
- Neural-Logic Human-Object Interaction Detection
- Neural Lyapunov Control for Discrete-Time Systems
- Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning
- Neural Modulation for Flash Memory: An Unsupervised Learning Framework for Improved Reliability
- Neural Multi-Objective Combinatorial Optimization with Diversity Enhancement
- Neural Oscillators are Universal
- Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features
- Neural Priming for Sample-Efficient Adaptation
- Neural Processes with Stability
- Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data
- Neural Sampling in Hierarchical Exponential-family Energy-based Models
- Neural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysis
- Neural (Tangent Kernel) Collapse
- NeurIPS 2023 Workshop: Machine Learning and the Physical Sciences
- NeurIPS 2023 Workshop on Diffusion Models
- NeurIPS 2023 Workshop on Machine Learning for Creativity and Design
- NeurIPS 2023 Workshop on Tackling Climate Change with Machine Learning: Blending New and Existing Knowledge Systems
- NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications
- NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries
- NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics
- Neuro-symbolic Learning Yielding Logical Constraints
- New Bounds for Hyperparameter Tuning of Regression Problems Across Instances
- New Complexity-Theoretic Frontiers of Tractability for Neural Network Training
- New Frontiers in Graph Learning (GLFrontiers)
- New Frontiers of AI for Drug Discovery and Development
- Newton–Cotes Graph Neural Networks: On the Time Evolution of Dynamic Systems
- NextGenAI: The Delusion of Scaling and the Future of Generative AI
- NICE: NoIse-modulated Consistency rEgularization for Data-Efficient GANs
- NIS3D: A Completely Annotated Benchmark for Dense 3D Nuclei Image Segmentation
- No Change, No Gain: Empowering Graph Neural Networks with Expected Model Change Maximization for Active Learning
- Noether Embedding: Efficient Learning of Temporal Regularities
- Noise-Adaptive Thompson Sampling for Linear Contextual Bandits
- Nominality Score Conditioned Time Series Anomaly Detection by Point/Sequential Reconstruction
- Non-adversarial training of Neural SDEs with signature kernel scores
- Non-Asymptotic Analysis of a UCB-based Top Two Algorithm
- Non-autoregressive Machine Translation with Probabilistic Context-free Grammar
- Non-Convex Bilevel Optimization with Time-Varying Objective Functions
- Nonparametric Boundary Geometry in Physics Informed Deep Learning
- Nonparametric Identifiability of Causal Representations from Unknown Interventions
- Nonparametric Teaching for Multiple Learners
- Non-Rigid Shape Registration via Deep Functional Maps Prior
- Non-Smooth Weakly-Convex Finite-sum Coupled Compositional Optimization
- Non-Stationary Bandits with Auto-Regressive Temporal Dependency
- Non-stationary Experimental Design under Linear Trends
- No-regret Algorithms for Fair Resource Allocation
- No-Regret Learning in Dynamic Competition with Reference Effects Under Logit Demand
- No-Regret Learning with Unbounded Losses: The Case of Logarithmic Pooling
- No-Regret Online Prediction with Strategic Experts
- No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions
- No Representation Rules Them All in Category Discovery
- Normalization-Equivariant Neural Networks with Application to Image Denoising
- Normalization Layers Are All That Sharpness-Aware Minimization Needs
- Normalizing flow neural networks by JKO scheme
- Norm-based Generalization Bounds for Sparse Neural Networks
- Norm-guided latent space exploration for text-to-image generation
- Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts
- Not All Out-of-Distribution Data Are Harmful to Open-Set Active Learning
- No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models
- NPCL: Neural Processes for Uncertainty-Aware Continual Learning
- NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF
- NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding
- NuTrea: Neural Tree Search for Context-guided Multi-hop KGQA
- NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videos
- OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents
- Objaverse-XL: A Universe of 10M+ 3D Objects
- OBJECT 3DIT: Language-guided 3D-aware Image Editing
- Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities
- Object-centric Learning with Cyclic Walks between Parts and Whole
- Object-Centric Slot Diffusion
- Object Reprojection Error (ORE): Camera pose benchmarks from lightweight tracking annotations
- Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving
- OceanBench: The Sea Surface Height Edition
- ODE-based Recurrent Model-free Reinforcement Learning for POMDPs
- OFCOURSE: A Multi-Agent Reinforcement Learning Environment for Order Fulfillment
- Offline Imitation Learning with Variational Counterfactual Reasoning
- Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage
- Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization
- Offline Reinforcement Learning for Mixture-of-Expert Dialogue Management
- Offline Reinforcement Learning with Differential Privacy
- Offline RL with Discrete Proxy Representations for Generalizability in POMDPs
- Off-Policy Evaluation for Human Feedback
- OKRidge: Scalable Optimal k-Sparse Ridge Regression
- On Calibrating Diffusion Probabilistic Models
- On Certified Generalization in Structured Prediction
- On Class Distributions Induced by Nearest Neighbor Graphs for Node Classification of Tabular Data
- On Computing Pairwise Statistics with Local Differential Privacy
- On Convergence of Polynomial Approximations to the Gaussian Mixture Entropy
- On Differentially Private Sampling from Gaussian and Product Distributions
- On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes
- One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization
- One Fits All: Power General Time Series Analysis by Pretrained LM
- One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation
- One Less Reason for Filter Pruning: Gaining Free Adversarial Robustness with Structured Grouped Kernel Pruning
- One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models
- OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling
- One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated Learning
- One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning
- One-step differentiation of iterative algorithms
- One-Step Diffusion Distillation via Deep Equilibrium Models
- On Evaluating Adversarial Robustness of Large Vision-Language Models
- On Generalization Bounds for Projective Clustering
- On Imitation in Mean-field Games
- On kernel-based statistical learning theory in the mean field limit
- On Learning Latent Models with Multi-Instance Weak Supervision
- On Learning Necessary and Sufficient Causal Graphs
- Online Ad Allocation with Predictions
- Online Adaptive Policy Selection in Time-Varying Systems: No-Regret via Contractive Perturbations
- Online Ad Procurement in Non-stationary Autobidding Worlds
- Online Clustering of Bandits with Misspecified User Models
- Online Constrained Meta-Learning: Provable Guarantees for Generalization
- Online Control for Meta-optimization
- Online Convex Optimization with Unbounded Memory
- Online Corrupted User Detection and Regret Minimization
- Online Inventory Problems: Beyond the i.i.d. Setting with Online Convex Optimization
- Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms
- Online learning of long-range dependencies
- Online Learning under Adversarial Nonlinear Constraints
- Online List Labeling with Predictions
- Online Map Vectorization for Autonomous Driving: A Rasterization Perspective
- Online (Multinomial) Logistic Bandit: Improved Regret and Constant Computation Cost
- Online Nonstochastic Model-Free Reinforcement Learning
- Online PCA in Converging Self-consistent Field Equations
- Online Performative Gradient Descent for Learning Nash Equilibria in Decision-Dependent Games
- Online POMDP Planning with Anytime Deterministic Guarantees
- Online Pricing for Multi-User Multi-Item Markets
- Online Reinforcement Learning in Digital Health Interventions
- Online RL in Linearly $q^\pi$-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore
- Online robust non-stationary estimation
- On Masked Pre-training and the Marginal Likelihood
- On Measuring Fairness in Generative Models
- On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
- On permutation symmetries in Bayesian neural network posteriors: a variational perspective
- On Private and Robust Bandits
- On Proper Learnability between Average- and Worst-case Robustness
- On quantum backpropagation, information reuse, and cheating measurement collapse
- On Robust Streaming for Learning with Experts: Algorithms and Lower Bounds
- On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling and Beyond
- On Separate Normalization in Self-supervised Transformers
- On Single-Index Models beyond Gaussian Data
- On skip connections and normalisation layers in deep optimisation
- On Slicing Optimality for Mutual Information
- On Sparse Modern Hopfield Model
- On student-teacher deviations in distillation: does it pay to disobey?
- On the Ability of Graph Neural Networks to Model Interactions Between Vertices
- On the Adversarial Robustness of Out-of-distribution Generalization Models
- On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay
- On the choice of Perception Loss Function for Learned Video Compression
- On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence
- On the Connection between Pre-training Data Diversity and Fine-tuning Robustness
- On the Consistency of Maximum Likelihood Estimation of Probabilistic Principal Component Analysis
- On the Constrained Time-Series Generation Problem
- On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration
- On the Convergence of Black-Box Variational Inference
- On the Convergence of CART under Sufficient Impurity Decrease Condition
- On the Convergence of Encoder-only Shallow Transformers
- On the Convergence of No-Regret Learning Dynamics in Time-Varying Games
- On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms
- On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective
- On the Exploitability of Instruction Tuning
- On the Exploration of Local Significant Differences For Two-Sample Test
- On-the-Fly Adapting Code Summarization on Trainable Cost-Effective Language Models
- On the Generalization Error of Stochastic Mirror Descent for Quadratically-Bounded Losses: an Improved Analysis
- On the Generalization Properties of Diffusion Models
- On the Gini-impurity Preservation For Privacy Random Forests
- On the Identifiability and Interpretability of Gaussian Process Models
- On the Identifiability of Sparse ICA without Assuming Non-Gaussianity
- On the impact of activation and normalization in obtaining isometric embeddings at initialization
- On the Implicit Bias of Linear Equivariant Steerable Networks
- On the Importance of Exploration for Generalization in Reinforcement Learning
- On the Importance of Feature Separability in Predicting Out-Of-Distribution Error
- On the Interplay between Social Welfare and Tractability of Equilibria
- On the Last-iterate Convergence in Time-varying Zero-sum Games: Extra Gradient Succeeds where Optimism Fails
- On the Learnability of Multilabel Ranking
- On the Minimax Regret for Online Learning with Feedback Graphs
- On the Need for a Language Describing Distribution Shifts: Illustrations on Tabular Datasets
- On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective
- On the Overlooked Structure of Stochastic Gradients
- On the Pareto Front of Multilingual Neural Machine Translation
- On the Planning Abilities of Large Language Models - A Critical Investigation
- On the Powerfulness of Textual Outlier Exposure for Visual OoD Detection
- On the Power of SVD in the Stochastic Block Model
- On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributions
- On the Relationship Between Relevance and Conflict in Online Social Link Recommendations
- On the Robustness of Mechanism Design under Total Variation Distance
- On the Robustness of Removal-Based Feature Attributions
- On the Role of Entanglement and Statistics in Learning
- On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences
- On the Role of Randomization in Adversarially Robust Classification
- On the Size and Approximation Error of Distilled Datasets
- On the spectral bias of two-layer linear networks
- On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm
- On the Statistical Consistency of Risk-Sensitive Bayesian Decision-Making
- On the Sublinear Regret of GP-UCB
- On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training
- On the Variance, Admissibility, and Stability of Empirical Risk Minimization
- On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks
- OpenAGI: When LLM Meets Domain Experts
- OpenAssistant Conversations - Democratizing Large Language Model Alignment
- Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation
- OpenDataVal: a Unified Benchmark for Data Valuation
- OpenGSL: A Comprehensive Benchmark for Graph Structure Learning
- OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects
- Opening the Vocabulary of Egocentric Actions
- OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping
- OpenMask3D: Open-Vocabulary 3D Instance Segmentation
- OpenProteinSet: Training data for structural biology at scale
- OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding
- OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
- Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting
- Operation-Level Early Stopping for Robustifying Differentiable NAS
- Operator Learning with Neural Fields: Tackling PDEs on General Geometries
- OPT 2023: Optimization for Machine Learning
- Optimal Algorithms for the Inhomogeneous Spiked Wigner Model
- Optimal and Fair Encouragement Policy Evaluation and Learning
- Optimal approximation using complex-valued neural networks
- Optimal Block-wise Asymmetric Graph Construction for Graph-based Semi-supervised Learning
- Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes
- Optimal cross-learning for contextual bandits with unknown context distributions
- Optimal Excess Risk Bounds for Empirical Risk Minimization on $p$-Norm Linear Regression
- Optimal Exploration for Model-Based RL in Nonlinear Systems
- Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure
- Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
- Optimality in Mean Estimation: Beyond Worst-Case, Beyond Sub-Gaussian, and Beyond $1+\alpha$ Moments
- Optimality of Message-Passing Architectures for Sparse Graphs
- Optimal Learners for Realizable Regression: PAC Learning and Online Learning
- Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection
- Optimal Preconditioning and Fisher Adaptive Langevin Sampling
- Optimal privacy guarantees for a relaxed threat model: Addressing sub-optimal adversaries in differentially private machine learning
- Optimal Rates for Bandit Nonstochastic Control
- Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework
- Optimal testing using combined test statistics across independent studies
- Optimal Time Complexities of Parallel Stochastic Optimization Methods Under a Fixed Computation Model
- Optimal Transport and Machine Learning
- Optimal Transport for Treatment Effect Estimation
- Optimal Transport-Guided Conditional Score-Based Diffusion Model
- Optimal Transport Model Distributional Robustness
- Optimal Treatment Allocation for Efficient Policy Evaluation in Sequential Decision Making
- Optimal Treatment Regimes for Proximal Causal Learning
- Optimal Unbiased Randomizers for Regression with Label Differential Privacy
- Optimistic Active Exploration of Dynamical Systems
- Optimistic Exploration in Reinforcement Learning Using Symbolic Model Estimates
- Optimistic Meta-Gradients
- Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL
- Optimistic Rates for Multi-Task Representation Learning
- Optimization and Bayes: A Trade-off for Overparameterized Neural Networks
- Optimization of Inter-group criteria for clustering with minimum size constraints
- Optimization or Architecture: How to Hack Kalman Filtering
- Optimized Covariance Design for AB Test on Social Network under Interference
- Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goal
- Optimizing over trained GNNs via symmetry breaking
- Optimizing Prompts for Text-to-Image Generation
- Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Method
- Oracle Complexity of Single-Loop Switching Subgradient Methods for Non-Smooth Weakly Convex Functional Constrained Optimization
- Ordering-based Conditions for Global Convergence of Policy Gradient Methods
- Order Matters in the Presence of Dataset Imbalance for Multilingual Learning
- Orthogonal Non-negative Tensor Factorization based Multi-view Clustering
- Outlier-Robust Gromov-Wasserstein for Graph Data
- Outlier-Robust Wasserstein DRO
- Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources
- Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation
- OV-PARTS: Towards Open-Vocabulary Part Segmentation
- PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction
- PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization
- PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile
- PAC Learning Linear Thresholds from Label Proportions
- PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection
- PaintSeg: Painting Pixels for Training-free Segmentation
- Pairwise Causality Guided Transformers for Event Sequences
- Pairwise GUI Dataset Construction Between Android Phones and Tablets
- PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation
- PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas
- PAPR: Proximity Attention Point Rendering
- ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP
- Parallel-mentoring for Offline Model-based Optimization
- Parallel Sampling of Diffusion Models
- Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies
- Parallel Submodular Function Minimization
- Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models
- Parameter-efficient Tuning of Large-scale Multimodal Foundation Model
- Parameterizing Context: Unleashing the Power of Parameter-Efficient Fine-Tuning and In-Context Tuning for Continual Table Semantic Parsing
- Parameterizing Non-Parametric Meta-Reinforcement Learning Tasks via Subtask Decomposition
- Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
- Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck
- Parsel🐍: Algorithmic Reasoning with Language Models by Composing Decompositions
- Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model
- Partial Label Learning with Dissimilarity Propagation guided Candidate Label Shrinkage
- Partial Matrix Completion
- Partial Multi-Label Learning with Probabilistic Graphical Disambiguation
- Participatory Personalization in Classification
- Particle-based Variational Inference with Generalized Wasserstein Gradient Flow
- Parts of Speech–Grounded Subspaces in Vision-Language Models
- Passive learning of active causal strategies in agents and language models
- Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models
- Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
- Path following algorithms for $\ell_2$-regularized $M$-estimation with approximation guarantee
- Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks
- Paxion: Patching Action Knowledge in Video-Language Foundation Models
- Payoff-based Learning with Matrix Multiplicative Weights in Quantum Games
- PCF-GAN: generating sequential data via the characteristic function of measures on the path space
- PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers
- PDF: Point Diffusion Implicit Function for Large-scale Scene Neural Representation
- PDP: Parameter-free Differentiable Pruning is All You Need
- Penalising the biases in norm regularisation enforces sparsity
- Pengi: An Audio Language Model for Audio Tasks
- Penguin: Parallel-Packed Homomorphic Encryption for Fast Graph Convolutional Network Inference
- Percentile Criterion Optimization in Offline Reinforcement Learning
- Perception Test: A Diagnostic Benchmark for Multimodal Video Models
- Perceptual adjustment queries and an inverted measurement paradigm for low-rank metric learning
- Perceptual Kalman Filters: Online State Estimation under a Perfect Perceptual-Quality Constraint
- PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis
- Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms
- Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex
- Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources
- Permutation Equivariant Neural Functionals
- Personalized Dictionary Learning for Heterogeneous Datasets
- Persuading Farsighted Receivers in MDPs: the Power of Honesty
- Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability
- PETAL: Physics Emulation Through Averaged Linearizations for Solving Inverse Problems
- P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting
- PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance
- Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning
- Phase diagram of early training dynamics in deep neural networks: effect of the learning rate, depth, and width
- PHOTOSWAP: Personalized Subject Swapping in Images
- Physics-Driven ML-Based Modelling for Correcting Inverse Estimation
- Physics-Informed Bayesian Optimization of Variational Quantum Circuits
- Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties
- Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
- PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification
- PID-Inspired Inductive Biases for Deep Reinforcement Learning in Partially Observable Control Tasks
- Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion
- PIXIU: A Comprehensive Benchmark, Instruction Dataset and Large Language Model for Finance
- PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change
- PlanE: Representation Learning over Planar Graphs
- PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model
- PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning
- Plug-and-Play Stability for Intracortical Brain-Computer Interfaces: A One-Year Demonstration of Seamless Brain-to-Text Communication
- PoET: A generative model of protein families as sequences-of-sequences
- Point Cloud Completion with Pretrained Text-to-Image Diffusion Models
- PointGPT: Auto-regressively Generative Pre-training from Point Clouds
- Pointwise uncertainty quantification for sparse variational Gaussian process regression with a Brownian motion prior
- Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data
- Policy Gradient for Rectangular Robust Markov Decision Processes
- Policy Optimization for Continuous Reinforcement Learning
- Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control
- Policy Space Diversity for Non-Transitive Games
- PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion Models
- Polyhedron Attention Module: Learning Adaptive-order Interactions
- Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets
- Polynomial-Time Linear-Swap Regret Minimization in Imperfect-Information Sequential Games
- POMDP Planning for Object Search in Partially Unknown Environment
- POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
- PopSign ASL v1.0: An Isolated American Sign Language Dataset Collected via Smartphones
- Posterior Contraction Rates for Matérn Gaussian Processes on Riemannian Manifolds
- Posterior Sampling for Competitive RL: Function Approximation and Partial Observation
- Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
- Post Hoc Explanations of Language Models Can Improve Language Models
- Posthoc privacy guarantees for collaborative inference with modified Propose-Test-Release
- Post-processing Private Synthetic Data for Improving Utility on Selected Measures
- PPi: Pretraining Brain Signal Model for Patient-independent Seizure Detection
- Practical and Asymptotically Exact Conditional Sampling in Diffusion Models
- Practical Contextual Bandits with Feedback Graphs
- Practical Differentially Private Hyperparameter Tuning with Subsampling
- Practical Equivariances via Relational Conditional Neural Processes
- Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima
- Precise asymptotic generalization for multiclass classification with overparameterized linear models
- Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows
- Preconditioning Matters: Fast Global Convergence of Non-convex Matrix Factorization via Scaled Gradient Descent
- Predicting a Protein's Stability under a Million Mutations
- Predicting Global Label Relationship Matrix for Graph Neural Networks under Heterophily
- Predicting mutational effects on protein-protein binding via a side-chain diffusion probabilistic model
- Prediction and Control in Continual Reinforcement Learning
- Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting
- Predict-then-Calibrate: A New Perspective of Robust Contextual LP
- PreDiff: Precipitation Nowcasting with Latent Diffusion Models
- PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds
- Preference-grounded Token-level Guidance for Language Model Fine-tuning
- Prefix-Tree Decoding for Predicting Mass Spectra from Molecules
- Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers
- Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning
- Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction
- Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression
- Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation
- PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation
- Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
- Principled Weight Initialisation for Input-Convex Neural Networks
- PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning
- Prioritizing Samples in Reinforcement Learning with Reducible Loss
- PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.
- Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation
- Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?
- Privacy Auditing with One (1) Training Run
- Private Distribution Learning with Public Data: The View from Sample Compression
- Private estimation algorithms for stochastic block models and mixture models
- Private Everlasting Prediction
- Private Federated Frequency Estimation: Adapting to the Hardness of the Instance
- Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
- Probabilistic Exponential Integrators
- Probabilistic Inference in Reinforcement Learning Done Right
- Probabilistic Invariant Learning with Randomized Linear Classifiers
- Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costs
- Probabilistic Weight Fixing: Large-scale training of neural network weight uncertainties for quantisation.
- PrObeD: Proactive Object Detection Wrapper
- ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab
- PRODIGY: Enabling In-context Learning Over Graphs
- Progressive Ensemble Distillation: Building Ensembles for Efficient Inference
- Projection-Free Methods for Solving Nonconvex-Concave Saddle Point Problems
- Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problem
- Projection-Free Online Convex Optimization via Efficient Newton Iterations
- Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models
- ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
- Promises and Pitfalls of Threshold-based Auto-labeling
- Prompt-augmented Temporal Point Process for Streaming Event Sequence
- PromptIR: Prompting for All-in-One Image Restoration
- Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition
- PromptRestorer: A Prompting Image Restoration Method with Degradation Perception
- Propagating Knowledge Updates to LMs Through Distillation
- ProPILE: Probing Privacy Leakage in Large Language Models
- Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization
- Protein Design with Guided Discrete Diffusion
- ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design
- ProteinInvBench: Benchmarking Protein Inverse Folding on Diverse Tasks, Models, and Metrics
- ProteinNPT: Improving Protein Property Prediction and Design with Non-Parametric Transformers
- ProteinShake: Building datasets and benchmarks for deep learning on protein structures
- PROTES: Probabilistic Optimization with Tensor Sampling
- ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion
- Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval
- Prototypical Variational Autoencoder for 3D Few-shot Object Detection
- Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs
- Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More
- Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond
- Provable benefits of score matching
- Provable convergence guarantees for black-box variational inference
- Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior
- Provable Guarantees for Neural Networks via Gradient Feature Learning
- Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks
- Provable Training for Graph Contrastive Learning
- Provably Bounding Neural Network Preimages
- Provably Efficient Algorithm for Nonstationary Low-Rank MDPs
- Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability
- Provably Efficient Offline Reinforcement Learning in Regular Decision Processes
- Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games
- Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation
- Provably (More) Sample-Efficient Offline RL with Options
- Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards
- Provably Safe Reinforcement Learning with Step-wise Violation Constraints
- Proximity-Informed Calibration for Deep Neural Networks
- Pruning vs Quantization: Which is Better?
- Pseudo-Likelihood Inference
- PTADisc: A Cross-Course Dataset Supporting Personalized Learning in Cold-Start Scenarios
- PTQD: Accurate Post-Training Quantization for Diffusion Models
- Public Opinion Field Effect Fusion in Representation Learning for Trending Topics Diffusion
- PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoising
- PUe: Biased Positive-Unlabeled Learning Enhancement by Causal Inference
- PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning
- Punctuation-level Attack: Single-shot and Single Punctuation Can Fool Text Models
- Puzzlefusion: Unleashing the Power of Diffusion Models for Spatial Puzzle Solving
- PyNeRF: Pyramidal Neural Radiance Fields
- QATCH: Benchmarking SQL-centric tasks with Table Representation Learning Models on Your Data
- Q-DM: An Efficient Low-bit Quantized Diffusion Model
- QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules
- QLoRA: Efficient Finetuning of Quantized LLMs
- QuACK: Accelerating Gradient-Based Quantum Optimization with Koopman Operator Learning
- QuadAttac$K$: A Quadratic Programming Approach to Learning Ordered Top-$K$ Adversarial Attacks
- Quantification of Uncertainty with Adversarial Models
- Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework
- Quantifying the Cost of Learning in Queueing Systems
- Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing
- QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution
- Quantum Bayesian Optimization
- Quantum speedups for stochastic optimization
- Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond
- Quasi-Monte Carlo Graph Random Features
- Query-based Temporal Fusion with Explicit Motion for 3D Object Detection
- Quilt-1M: One Million Image-Text Pairs for Histopathology
- QuIP: 2-Bit Quantization of Large Language Models With Guarantees
- RADAR: Robust AI-Text Detection via Adversarial Learning
- RaLEs: a Benchmark for Radiology Language Evaluations
- Random-Access Infinite Context Length for Transformers
- Random Cuts are Optimal for Explainable k-Medians
- Randomized and Deterministic Maximin-share Approximations for Fractionally Subadditive Valuations
- Randomized Sparse Neural Galerkin Schemes for Solving Evolution Equations with Deep Networks
- RangePerception: Taming LiDAR Range View for Efficient and Accurate 3D Object Detection
- Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization
- Rank-DETR for High Quality Object Detection
- Rank-N-Contrast: Learning Continuous Representations for Regression
- RanPAC: Random Projections and Pre-trained Models for Continual Learning
- RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths
- RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency
- R-divergence for Estimating Model-oriented Distribution Discrepancy
- RD-Suite: A Benchmark for Ranking Distillation
- RDumb: A simple approach that questions our progress in continual test-time adaptation
- [Re] $\mathcal{G}$-Mixup: Graph Data Augmentation for Graph Classification
- Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals
- Reading Relevant Feature from Global Representation Memory for Visual Object Tracking
- Real3D-AD: A Dataset of Point Cloud Anomaly Detection
- Realistic Synthetic Financial Transactions for Anti-Money Laundering Models
- Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding
- RealTime QA: What's the Answer Right Now?
- Real-World Image Super-Resolution as Multi-Task Learning
- Real-World Image Variation by Aligning Diffusion Inversion Chain
- REASONER: An Explainable Recommendation Dataset with Comprehensive Labeling Ground Truths
- [Re] Bandit Theory and Thompson Sampling-guided Directed Evolution for Sequence Optimization
- Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations
- Recasting Continual Learning as Sequence Modeling
- Recent and Upcoming Developments in Randomized Numerical Linear Algebra for ML
- RECESS Vaccine for Federated Learning: Proactive Defense Against Model Poisoning Attacks
- RECKONING: Reasoning through Dynamic Knowledge Encoding
- Recommender Systems with Generative Retrieval
- Reconciling Competing Sampling Strategies of Network Embedding
- Reconsidering Overfitting in the Age of Overparameterized Models
- Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors
- ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction
- Recovering from Out-of-sample States via Inverse Dynamics in Offline Reinforcement Learning
- Recovering Simultaneously Structured Data via Non-Convex Iteratively Reweighted Least Squares
- Recovering Unbalanced Communities in the Stochastic Block Model with Application to Clustering with a Faulty Oracle
- [Re] CrossWalk: Fairness-enhanced Node Representation Learning
- Recurrent Hypernetworks are Surprisingly Strong in Meta-RL
- Recurrent Temporal Revision Graph Networks
- Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability
- ReDS: Offline RL With Heteroskedastic Datasets via Support Constraints
- Red Teaming Deep Neural Networks with Feature Synthesis Tools
- Reduced Policy Optimization for Continuous Control with Hard Constraints
- Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor
- Reducing Shape-Radiance Ambiguity in Radiance Fields with a Closed-Form Color Estimation Method
- [Re] End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking
- [Re] Exploring the Role of Grammar and Word Choice in Bias Toward African American English (AAE) in Hate Speech Classification
- [Re] Fairness Guarantees under Demographic Shift
- Reference-Based POMDPs
- REFINE: A Fine-Grained Medication Recommendation System Using Deep Learning and Personalized Drug Interaction Modeling
- Refined Mechanism Design for Approximately Structured Priors via Active Regression
- Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans
- Reflexion: language agents with verbal reinforcement learning
- [Re] FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles
- RegBN: Batch Normalization of Multimodal Data with Regularization
- Regression with Cost-based Rejection
- Regret Matching+: (In)Stability and Fast Convergence in Games
- Regret Minimization via Saddle Point Optimization
- Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time
- Regularity as Intrinsic Reward for Free Play
- Regularization properties of adversarially-trained linear regression
- Regularized Behavior Cloning for Blocking the Leakage of Past Action Information
- Regularizing Neural Networks with Meta-Learning Generative Models
- Regulatable ML: Towards Bridging the Gaps between Machine Learning Research and Regulations
- Rehearsal Learning for Avoiding Undesired Future
- [Re] Hierarchical Shrinkage: Improving the Accuracy and Interpretability of Tree-Based Methods
- ReHLine: Regularized Composite ReLU-ReHU Loss Minimization with Linear Computation and Linear Convergence
- Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark
- Reinforcement-Enhanced Autoregressive Feature Transformation: Gradient-steered Search in Continuous Space for Postfix Expressions
- Reinforcement Learning with Fast and Forgetful Memory
- Reinforcement Learning with Simple Sequence Priors
- Reining Generalization in Offline Reinforcement Learning via Representation Distinction
- Relative Entropic Optimal Transport: a (Prior-aware) Matching Perspective to (Unbalanced) Classification
- Relax, it doesn’t matter how you get there: A new self-supervised approach for multi-timescale behavior analysis
- Reliable learning in challenging environments
- Reliable Off-Policy Learning for Dosage Combinations
- RELIC: Reproducibility and Extension on LIC metric in quantifying bias in captioning models
- [Re] Masked Autoencoders Are Small Scale Vision Learners: A Reproduction Under Resource Constraints
- ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
- Removing Hidden Confounding in Recommendation: A Unified Multi-Task Learning Approach
- RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars
- Renku: a platform for sustainable data science
- [Re] Numerical influence of ReLU'(0) on backpropagation
- [Re] On Explainability of Graph Neural Networks via Subgraph Explorations
- [Re] On the Reproducibility of CartoonX
- [Re] On the Reproducibility of “FairCal: Fairness Calibration for Face Verification”
- Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective
- Replicability in Reinforcement Learning
- Replicable Clustering
- Replicable Reinforcement Learning
- RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability
- Representational Strengths and Limitations of Transformers
- Representation Equivalent Neural Operators: a Framework for Alias-free Operator Learning
- Representation Learning via Consistent Assignment of Views over Random Partitions
- Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests
- Reproducibility Study of ”CartoonX: Cartoon Explanations of Image Classifiers”
- Reproducibility Study of "Label-Free Explainability for Unsupervised Models"
- Reproducibility Study of ”Label-Free Explainability for Unsupervised Models”
- Reproducibility study of 'Proto2Proto: Can you recognise the car, the way I do?'
- Reproducibility Study of “Quantifying Societal Bias Amplification in Image Captioning”
- Reproducibility study of the Fairness-enhanced Node Representation Learning
- [Re] Pure Noise to the Rescue of Insufficient Data
- Resetting the Optimizer in Deep RL: An Empirical Study
- Residual Alignment: Uncovering the Mechanisms of Residual Networks
- Residual Q-Learning: Offline and Online Policy Customization without Value
- Resilient Constrained Learning
- Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis
- ResMem: Learn what you can and memorize the rest
- Resolving the Tug-of-War: A Separation of Communication and Learning in Federated Learning
- ResoNet: Noise-Trained Physics-Informed MRI Off-Resonance Correction
- Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline
- Responsible AI (RAI) Games and Ensembles
- ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting
- Restart Sampling for Improving Generative Processes
- Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption
- Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone
- ReSync: Riemannian Subgradient-based Robust Rotation Synchronization
- Retaining Beneficial Information from Detrimental Data for Neural Network Repair
- Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals
- Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition
- Rethinking Conditional Diffusion Sampling with Progressive Guidance
- Rethinking Gauss-Newton for learning over-parameterized models
- Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial?
- Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition
- Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective
- Rethinking the Backward Propagation for Adversarial Transferability
- Rethinking the Role of Token Retrieval in Multi-Vector Retrieval
- Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules
- Retrieval-Augmented Multiple Instance Learning
- ReTR: Modeling Rendering Via Transformer for Generalizable Neural Surface Reconstruction
- RETVec: Resilient and Efficient Text Vectorizer
- Reusable Slotwise Mechanisms
- Reusing Pretrained Models by Multi-linear Operators for Efficient Training
- [Re] VAE Approximation Error: ELBO and Exponential Families
- [Re] Variational Neural Cellular Automata
- RevColV2: Exploring Disentangled Representations in Masked Image Modeling
- Revealing the unseen: Benchmarking video action recognition under occlusion
- Reverse Engineering Self-Supervised Learning
- Reversible and irreversible bracket-based dynamics for deep graph neural networks
- Revisiting Adversarial Robustness Distillation from the Perspective of Robust Fairness
- Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models
- Revisiting Area Convexity: Faster Box-Simplex Games and Spectrahedral Generalizations
- Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union
- Revisiting Implicit Differentiation for Learning Problems in Optimal Control
- Revisiting Logistic-softmax Likelihood in Bayesian Meta-Learning for Few-Shot Classification
- Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations
- Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective
- Revisiting the Evaluation of Image Synthesis with GANs
- Revisiting the Minimalist Approach to Offline Reinforcement Learning
- Revisiting Visual Model Robustness: A Frequency Long-Tailed Distribution View
- Revisit the Power of Vanilla Knowledge Distillation: from Small Scale to Large Scale
- Revisit Weakly-Supervised Audio-Visual Video Parsing from the Language Perspective
- Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning
- Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement
- Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
- Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery
- Reward Imputation with Sketching for Contextual Batched Bandits
- Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks
- Rewiring Neurons in Non-Stationary Environments
- Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation
- REx: Data-Free Residual Quantization Error Expansion
- RGMIL: Guide Your Multiple-Instance Learning Model with Regressor
- RH-BrainFS: Regional Heterogeneous Multimodal Brain Networks Fusion Strategy
- Riemannian Laplace approximations for Bayesian neural networks
- Riemannian Projection-free Online Learning
- Riemannian Residual Neural Networks
- Riemannian SAM: Sharpness-Aware Minimization on Riemannian Manifolds
- Riemannian stochastic optimization methods avoid strict saddle points
- Rigorous Runtime Analysis of MOEA/D for Solving Multi-Objective Minimum Weight Base Problems
- RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments
- Risk-Averse Active Sensing for Timely Outcome Prediction under Cost Pressure
- Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning
- RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization
- RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing
- RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization
- RoboCLIP: One Demonstration is Enough to Learn Robot Policies
- RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions
- RoboHive: A Unified Framework for Robot Learning
- Robust and Actively Secure Serverless Collaborative Learning
- Robust Bayesian Satisficing
- Robust Concept Erasure via Kernelized Rate-Distortion Maximization
- Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks
- Robust covariance estimation with missing values and cell-wise contamination
- Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy
- Robust Data Valuation with Weighted Banzhaf Values
- Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity
- Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Model
- Robust Knowledge Transfer in Tiered Reinforcement Learning
- Robust Learning for Smoothed Online Convex Optimization with Feedback Delay
- Robust Learning with Progressive Data Expansion Against Spurious Correlation
- Robust Lipschitz Bandits to Adversarial Corruptions
- Robust low-rank training via approximate orthonormal constraints
- Robust Matrix Sensing in the Semi-Random Model
- Robust Mean Estimation Without Moments for Symmetric Distributions
- Robust Model Reasoning and Fitting via Dual Sparsity Pursuit
- Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms
- Robustness Guarantees for Adversarially Trained Neural Networks
- Robust Second-Order Nonconvex Optimization and Its Application to Low Rank Matrix Sensing
- Rotating Features for Object Discovery
- rPPG-Toolbox: Deep Remote PPG Toolbox
- RRHF: Rank Responses to Align Language Models with Human Feedback
- RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion
- Rubik's Cube: High-Order Channel Interactions with a Hierarchical Receptive Field
- RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation
- Saddle-to-Saddle Dynamics in Diagonal Linear Networks
- SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations
- Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms
- Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmark
- Safety Verification of Decision-Tree Policies in Continuous Time
- SALSA VERDE: a machine learning attack on LWE with sparse small secrets
- SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multipiece Explanations
- SAMoSSA: Multivariate Singular Spectrum Analysis with Stochastic Autoregressive Noise
- Sample based Explanations via Generalized Representers
- Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling
- Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms
- Sample Complexity of Forecast Aggregation
- Sample Complexity of Goal-Conditioned Hierarchical Reinforcement Learning
- Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds
- Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agents
- Sample-efficient Multi-objective Molecular Optimization with GFlowNets
- Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks
- Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent
- Sampling from Structured Log-Concave Distributions via a Soft-Threshold Dikin Walk
- Sampling weights of deep neural networks
- SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model
- SANFlow: Semantic-Aware Normalizing Flow for Anomaly Detection
- SARAMIS: Simulation Assets for Robotic Assisted and Minimally Invasive Surgery
- SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models
- SatBird: a Dataset for Bird Species Distribution Modeling using Remote Sensing and Citizen Science Data
- SatLM: Satisfiability-Aided Language Models Using Declarative Prompting
- SaVeNet: A Scalable Vector Network for Enhanced Molecular Representation Learning
- Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation
- Scalable 3D Captioning with Pretrained Models
- Scalable Fair Influence Maximization
- Scalable Membership Inference Attacks via Quantile Regression
- Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities
- Scalable Transformer for PDE Surrogate Modeling
- Scalarization for Multi-Task and Multi-Domain Learning at Scale
- Scale Alone Does not Improve Mechanistic Interpretability in Vision Models
- ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection
- Scale-Space Hypernetworks for Efficient Biomedical Image Analysis
- Scale-teaching: Robust Multi-scale Training for Time Series Classification with Noisy Labels
- Scaling Data-Constrained Language Models
- Scaling Laws for Hyperparameter Optimization
- Scaling laws for language encoding models in fMRI
- Scaling MLPs: A Tale of Inductive Bias
- Scaling Open-Vocabulary Object Detection
- Scaling Riemannian Diffusion Models
- Scaling Up Differentially Private LASSO Regularized Logistic Regression via Faster Frank-Wolfe Iterations
- Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer
- Scattering Vision Transformer: Spectral Mixing Matters
- Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion
- ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling
- SceneScape: Text-Driven Consistent Scene Generation
- Schema-learning and rebinding as mechanisms of in-context learning and emergence
- Scientific Document Retrieval using Multi-level Aspect-based Queries
- Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time
- S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions
- Score-based Data Assimilation
- Score-based Generative Modeling through Stochastic Evolution Equations in Hilbert Spaces
- Score-based Generative Models with Lévy Processes
- Score-based Source Separation with Applications to Digital Communication Signals
- SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation
- SE(3) Equivariant Augmented Coupling Flows
- Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking
- Secure Out-of-Distribution Task Generalization with Energy-Based Models
- SEEDS: Exponential SDE Solvers for Fast High-Quality Sampling from Diffusion Models
- Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images
- Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation
- SEENN: Towards Temporal Spiking Early Exit Neural Networks
- SEGA: Instructing Text-to-Image Models using Semantic Guidance
- Segment Any Point Cloud Sequences by Distilling Vision Foundation Models
- Segment Anything in 3D with NeRFs
- Segment Anything in High Quality
- Segment Everything Everywhere All at Once
- SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process
- Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models
- Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning
- Selective Sampling and Imitation Learning via Online Regression
- Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning
- Self-Adaptive Motion Tracking against On-body Displacement of Flexible Sensors
- Self-Chained Image-Language Model for Video Localization and Question Answering
- Self-Consistent Velocity Matching of Probability Flows
- Self-Correcting Bayesian Optimization through Bayesian Active Learning
- Self-Evaluation Guided Beam Search for Reasoning
- Self-Predictive Universal AI
- Self-Refine: Iterative Refinement with Self-Feedback
- Self-supervised Graph Neural Networks via Low-Rank Decomposition
- Self-Supervised Learning of Representations for Space Generates Multi-Modular Grid Cells
- Self-Supervised Learning with Lie Symmetries for Partial Differential Equations
- Self-Supervised Motion Magnification by Backpropagating Through Optical Flow
- Self-supervised Object-Centric Learning for Videos
- Self-Supervised Reinforcement Learning that Transfers using Random Features
- Self-supervised video pretraining yields robust and more human-aligned visual representations
- Self-Supervised Visual Acoustic Matching
- Self-Weighted Contrastive Learning among Multiple Views for Mitigating Representation Degeneration
- Semantic HELM: A Human-Readable Memory for Reinforcement Learning
- Semantic Image Synthesis with Unconditional Generator
- Semantic segmentation of sparse irregular point clouds for leaf/wood discrimination
- Semi-Implicit Denoising Diffusion Models (SIDDMs)
- Semi-Supervised Contrastive Learning for Deep Regression with Ordinal Rankings from Spectral Seriation
- Semi-Supervised Domain Generalization with Known and Unknown Classes
- Sensitivity in Translation Averaging
- Separable Physics-Informed Neural Networks
- Sequential Memory with Temporal Predictive Coding
- Sequential Predictive Two-Sample and Independence Testing
- Sequential Preference Ranking for Efficient Reinforcement Learning from Human Feedback
- Sequential Subset Matching for Dataset Distillation
- Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots
- SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction
- (S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
- SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations
- SG×P : A Sorghum Genotype × Phenotype Prediction Dataset and Benchmark
- Shape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching via Unsupervised Functional Map Regularized Reconstruction
- SHAP-IQ: Unified Approximation of any-order Shapley Interactions
- Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
- Sharp Bounds for Generalized Causal Sensitivity Analysis
- Sharp Calibrated Gaussian Processes
- Sharpness-Aware Minimization Leads to Low-Rank Features
- Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization
- Sharp Recovery Thresholds of Tensor PCA Spectral Algorithms
- Sharp Spectral Rates for Koopman Operator Learning
- Sheaf Hypergraph Networks
- SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models
- ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer
- SHOT: Suppressing the Hessian along the Optimization Trajectory for Gradient-Based Meta-Learning
- Should I Stop or Should I Go: Early Stopping with Heterogeneous Populations
- Should Under-parameterized Student Networks Copy or Average Teacher Weights?
- Should We Learn Most Likely Functions or Parameters?
- Siamese Masked Autoencoders
- SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning
- Similarity-based cooperative equilibrium
- Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities
- SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization
- SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling
- Simple and Asymmetric Graph Contrastive Learning without Augmentations
- Simple and Controllable Music Generation
- Simple, Scalable and Effective Clustering via One-Dimensional Projections
- Simplicity Bias in 1-Hidden Layer Neural Networks
- Simplifying Neural Network Training Under Class Imbalance
- Simultaneous embedding of multiple attractor manifolds in a recurrent neural network using constrained gradient optimization
- Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions
- Single-Pass Pivot Algorithm for Correlation Clustering. Keep it simple!
- Single-Stage Visual Query Localization in Egocentric Videos
- SiT Dataset: Socially Interactive Pedestrian Trajectory Dataset for Social Navigation Robots
- SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoning
- Sketching Algorithms for Sparse Dictionary Learning: PTAS and Turnstile Streaming
- Sketching: core tools, learning-augmentation, and adaptive robustness
- Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions
- Skill-it! A data-driven skills framework for understanding and training language models
- SLaM: Student-Label Mixing for Distillation with Unlabeled Examples
- SLIBO-Net: Floorplan Reconstruction via Slicing Box Representation with Local Geometry Regularization
- Slimmed Asymmetrical Contrastive Learning and Cross Distillation for Lightweight Model Training
- SLM: A Smoothed First-Order Lagrangian Method for Structured Constrained Nonconvex Optimization
- SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models
- Slot-guided Volumetric Object Radiance Fields
- Slow and Weak Attractor Computation Embedded in Fast and Strong E-I Balanced Neural Dynamics
- SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning
- Small batch deep reinforcement learning
- Small Total-Cost Constraints in Contextual Bandits with Knapsacks, with Application to Fairness
- Small Transformers Compute Universal Metric Embeddings
- SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation
- Smoothed Analysis of Sequential Probability Assignment
- Smoothed Online Learning for Prediction in Piecewise Affine Systems
- Smooth, exact rotational symmetrization for deep learning on point clouds
- Smooth Flipping Probability for Differential Private Sign Random Projection Methods
- SmoothHess: ReLU Network Feature Interactions via Stein's Lemma
- Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models
- SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation
- SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds
- SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding
- SNEkhorn: Dimension Reduction with Symmetric Entropic Affinities
- SOAR: Improved Indexing for Approximate Nearest Neighbor Search
- Socially Responsible Language Modelling Research (SoLaR)
- Social Motion Prediction with Cognitive Hierarchies
- SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation
- SODA: Robust Training of Test-Time Data Adaptors
- Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks
- Soft-Unification in Deep Probabilistic Logic
- SOL: Sampling-based Optimal Linear bounding of arbitrary scalar functions
- Solving a Class of Non-Convex Minimax Optimization in Federated Learning
- Solving Inverse Physics Problems with Score Matching
- Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models
- Sorting with Predictions
- SoTTA: Robust Test-Time Adaptation on Noisy Data Streams
- SoundCam: A Dataset for Finding Humans Using Room Acoustics
- Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio
- SPA: A Graph Spectral Alignment Perspective for Domain Adaptation
- SPACE: Single-round Participant Amalgamation for Contribution Evaluation in Federated Learning
- SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs
- Sparse Deep Learning for Time Series Data: Theory and Applications
- Sparse Graph Learning from Spatiotemporal Time Series
- Sparse Modular Activation for Efficient Sequence Modeling
- Sparse Parameterization for Epitomic Dataset Distillation
- SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networks
- Sparsity-Preserving Differentially Private Training of Large Embedding Models
- Spatial-frequency channels, shape bias, and adversarial robustness
- Spatially Resolved Gene Expression Prediction from Histology Images via Bi-modal Contrastive Learning
- SpatialRank: Urban Event Ranking with NDCG Optimization on Spatiotemporal Data
- Spatio-Angular Convolutions for Super-resolution in Diffusion MRI
- Species196: A One-Million Semi-supervised Dataset for Fine-grained Species Recognition
- Spectral Co-Distillation for Personalized Federated Learning
- Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning
- Spectral Evolution and Invariance in Linear-width Neural Networks
- Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts
- SpecTr: Fast Speculative Decoding via Optimal Transport
- Speculative Decoding with Big Little Decoder
- Spike-driven Transformer
- Spiking PointNet: Spiking Neural Networks for Point Clouds
- SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents
- Spontaneous symmetry breaking in generative diffusion models
- SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning
- SPRING: Studying Papers and Reasoning to play Games
- Spuriosity Didn’t Kill the Classifier: Using Invariant Predictions to Harness Spurious Features
- Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases
- SQ Lower Bounds for Learning Mixtures of Linear Classifiers
- SQ Lower Bounds for Non-Gaussian Component Analysis with Weaker Assumptions
- Squared Neural Families: A New Class of Tractable Density Models
- Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective
- SSL4EO-L: Datasets and Foundation Models for Landsat Imagery
- Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm
- Stability Guarantees for Feature Attributions with Multiplicative Smoothing
- Stability of Random Forests and Coverage of Random-Forest Prediction Intervals
- Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds
- Stabilized Neural Differential Equations for Learning Dynamics with Explicit Constraints
- Stable and low-precision training for large-scale vision-language models
- Stable Bias: Evaluating Societal Representations in Diffusion Models
- Stable Diffusion is Unstable
- StableFDG: Style and Attention Based Learning for Federated Domain Generalization
- Stable Nonconvex-Nonconcave Training via Linear Interpolation
- StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners
- Stable Vectorization of Multiparameter Persistent Homology using Signed Barcodes as Measures
- Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark
- Star-Shaped Denoising Diffusion Probabilistic Models
- STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events
- State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding
- State-Action Similarity-Based Representations for Off-Policy Evaluation
- StateMask: Explaining Deep Reinforcement Learning through State Mask
- State Regularized Policy Optimization on Data with Dynamics Shift
- State Sequences Prediction via Fourier Transform for Representation Learning
- State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory
- Static and Sequential Malicious Attacks in the Context of Selective Forgetting
- Statistical Analysis of Quantum State Learning Process in Quantum Neural Networks
- Statistical and Computational Trade-off in Multi-Agent Multi-Armed Bandits
- Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory
- Statistical Insights into HSIC in High Dimensions
- Statistical Knowledge Assessment for Large Language Models
- Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference
- Statistically Valid Variable Importance Assessment through Conditional Permutations
- StEik: Stabilizing the Optimization of Neural Signed Distance Functions and Finer Shape Representation
- Stein $\Pi$-Importance Sampling
- STEVE-1: A Generative Model for Text-to-Behavior in Minecraft
- Stochastic Approximation Algorithms for Systems of Interacting Particles
- Stochastic Approximation Approaches to Group Distributionally Robust Optimization
- Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks
- Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis
- Stochastic Multi-armed Bandits: Optimal Trade-off among Optimality, Consistency, and Tail Risk
- Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Paths
- STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning
- StoryBench: A Multifaceted Benchmark for Continuous Story Visualization
- Strategic Apple Tasting
- Strategic Behavior in Two-sided Matching Markets with Prediction-enhanced Preference-formation
- Strategic Classification under Unknown Personalized Manipulation
- Strategic Data Sharing between Competitors
- Strategic Distribution Shift of Interacting Agents via Coupled Gradient Flows
- Strategyproof Voting under Correlated Beliefs
- STREAMER: Streaming Representation Learning and Event Segmentation in a Hierarchical Manner
- Streaming Algorithms and Lower Bounds for Estimating Correlation Clustering Cost
- Streaming Factor Trajectory Learning for Temporal Tensor Decomposition
- Streaming PCA for Markovian Data
- StreamNet: Memory-Efficient Streaming Tiny Deep Learning Inference on the Microcontroller
- StressID: a Multimodal Dataset for Stress Identification
- Strong and Precise Modulation of Human Percepts via Robustified ANNs
- Structural Pruning for Diffusion Models
- Structured Federated Learning through Clustered Additive Modeling
- Structured Neural Networks for Density Estimation and Causal Inference
- Structured Neural-PI Control with End-to-End Stability and Output Tracking Guarantees
- Structured Prediction with Stronger Consistency Guarantees
- Structured Semidefinite Programming for Recovering Structured Preconditioners
- Structured State Space Models for In-Context Reinforcement Learning
- Structured Voronoi Sampling
- Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data
- Structure from Duplicates: Neural Inverse Graphics from a Pile of Objects
- Structure Learning with Adaptive Random Neighborhood Informed MCMC
- Structure of universal formulas
- Students Parrot Their Teachers: Membership Inference on Model Distillation
- STXD: Structural and Temporal Cross-Modal Distillation for Multi-View 3D Object Detection
- StyleDrop: Text-to-Image Synthesis of Any Style
- StyleGAN knows Normal, Depth, Albedo, and More
- StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
- Subclass-Dominant Label Noise: A Counterexample for the Success of Early Stopping
- Subject-driven Text-to-Image Generation via Apprenticeship Learning
- Sub-optimality of the Naive Mean Field approximation for proportional high-dimensional Linear Regression
- SUBP: Soft Uniform Block Pruning for 1$\times$N Sparse CNNs Multithreading Acceleration
- SubseasonalClimateUSA: A Dataset for Subseasonal Forecasting and Benchmarking
- Subspace Identification for Multi-Source Domain Adaptation
- Successor-Predecessor Intrinsic Exploration
- SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality
- Suggesting Variable Order for Cylindrical Algebraic Decomposition via Reinforcement Learning
- SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics
- Supervised Pretraining Can Learn In-Context Reinforcement Learning
- Supply-Side Equilibria in Recommender Systems
- Supported Value Regularization for Offline Reinforcement Learning
- Survival Instinct in Offline Reinforcement Learning
- Survival Permanental Processes for Survival Analysis with Time-Varying Covariates
- SustainGym: Reinforcement Learning Environments for Sustainable Energy Systems
- SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting
- Swap Agnostic Learning, or Characterizing Omniprediction via Multicalibration
- SwapPrompt: Test-Time Prompt Adaptation for Vision-Language Models
- Swarm Reinforcement Learning for Adaptive Mesh Refinement
- SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
- SwiFT: Swin 4D fMRI Transformer
- Switching Autoregressive Low-rank Tensor Models
- Switching Temporary Teachers for Semi-Supervised Semantic Segmentation
- Symbolic Discovery of Optimization Algorithms
- Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning
- Symmetry and Geometry in Neural Representations
- Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials
- SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions
- SyncTREE: Fast Timing Analysis for Integrated Circuit Design through a Physics-informed Tree-based Graph Neural Network
- SynMob: Creating High-Fidelity Synthetic GPS Trajectory Dataset for Urban Mobility Analysis
- Synthcity: a benchmark framework for diverse use cases of tabular synthetic data
- Synthetic Combinations: A Causal Inference Framework for Combinatorial Interventions
- Synthetic Data Generation with Generative AI
- Synthetic Experience Replay
- Synthetic-to-Real Pose Estimation with Geometric Reconstruction
- Systematic Visual Reasoning through Object-Centric Relational Abstraction
- Systems for Foundation Models, and Foundation Models for Systems.
- T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation
- T2T: From Distribution Learning in Training to Gradient Search in Testing for Combinatorial Optimization
- Table Representation Learning Workshop
- TabMT: Generating tabular data with masked transformers
- Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds
- Tailoring Self-Attention for Graph via Rooted Subtrees
- Taking the neural sampling code very seriously: A data-driven approach for evaluating generative models of the visual system
- Tame a Wild Camera: In-the-Wild Monocular Camera Calibration
- Taming Local Effects in Graph-based Spatiotemporal Forecasting
- Tanh Works Better with Asymmetry
- Tanimoto Random Features for Scalable Molecular Machine Learning
- TART: A plug-and-play Transformer module for task-agnostic reasoning
- Tartarus: A Benchmarking Platform for Realistic And Practical Inverse Molecular Design
- Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models
- Task-aware Distributed Source Coding under Dynamic Bandwidth
- Task-aware world model learning with meta weighting via bi-level optimization
- TaskMet: Task-driven Metric Learning for Model Learning
- Task-Robust Pre-Training for Worst-Case Downstream Adaptation
- Taylor TD-learning
- TD Convergence: An Optimization Perspective
- Team-PSRO for Learning Approximate TMECor in Large Team Games via Cooperative Reinforcement Learning
- Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training
- Template-free Articulated Neural Point Clouds for Reposable View Synthesis
- TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery
- Tempo Adaptation in Non-stationary Reinforcement Learning
- Temporal Causal Mediation through a Point Process: Direct and Indirect Effects of Healthcare Interventions
- Temporal Conditioning Spiking Latent Variable Models of the Neural Response to Natural Visual Scenes
- Temporal Continual Learning with Prior Compensation for Human Motion Prediction
- Temporal Dynamic Quantization for Diffusion Models
- Temporal Graph Benchmark for Machine Learning on Temporal Graphs
- Temporal Graph Learning Workshop @ NeurIPS 2023
- Temporally Disentangled Representation Learning under Unknown Nonstationarity
- Temporal Robustness against Data poisoning
- TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials
- Tester-Learners for Halfspaces: Universal Algorithms
- Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples
- Test-Time Amendment with a Coarse Classifier for Fine-Grained Classification
- Test-Time Distribution Normalization for Contrastively Learned Visual-language Models
- Test-time Training for Matching-based Video Object Segmentation
- TexQ: Zero-shot Network Quantization with Texture Feature Distribution Calibration
- Text Alignment Is An Efficient Unified Model for Massive NLP Tasks
- TextDiffuser: Diffusion Models as Text Painters
- Text Promptable Surgical Instrument Segmentation with Vision-Language Models
- Text-to-Image Diffusion Models are Zero Shot Classifiers
- Textually Pretrained Speech Language Models
- TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graph
- The Adversarial Consistency of Surrogate Risks for Binary Classification
- The Bayesian Stability Zoo
- The Behavior and Convergence of Local Bayesian Optimization
- The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning
- The Best of Both Worlds in Network Population Games: Reaching Consensus and Convergence to Equilibrium
- The Cambridge Law Corpus: A Corpus for Legal AI Research
- The CLIP Model is Secretly an Image-to-Prompt Converter
- The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks
- The Contextual Lasso: Sparse Linear Models via Deep Neural Networks
- The Crucial Role of Normalization in Sharpness-Aware Minimization
- The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model
- The Distortion of Binomial Voting Defies Expectation
- The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks
- The Drunkard’s Odometry: Estimating Camera Motion in Deforming Scenes
- The emergence of clusters in self-attention dynamics
- The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter
- The Equivalence of Dynamic and Strategic Stability under Regularized Learning in Games
- The Exact Sample Complexity Gain from Invariances for Kernel Regression
- The expressive power of pooling in Graph Neural Networks
- The Gain from Ordering in Online Learning
- The geometry of hidden representations of large transformer models
- The Geometry of Neural Nets' Parameter Spaces Under Reparametrization
- The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs
- The Grand Illusion: The Myth of Software Portability and Implications for ML Progress.
- The Graph Pencil Method: Mapping Subgraph Densities to Stochastic Block Models
- The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications
- The Impact of Positional Encoding on Length Generalization in Transformers
- The Learnability of In-Context Learning
- The Many Faces of Responsible AI
- The Memory-Perturbation Equation: Understanding Model's Sensitivity to Data
- The noise level in linear regression with dependent data
- Theoretical Analysis of the Inductive Biases in Deep Convolutional Networks
- Theoretical and Practical Perspectives on what Influence Functions Do
- Theoretically Guaranteed Bidirectional Data Rectification for Robust Sequential Recommendation
- The Pick-to-Learn Algorithm: Empowering Compression for Tight Generalization Bounds and Improved Post-training Performance
- The probability flow ODE is provably fast
- The Pursuit of Human Labeling: A New Perspective on Unsupervised Learning
- The Quantization Model of Neural Scaling
- The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions
- The Rashomon Importance Distribution: Getting RID of Unstable, Single Model-based Variable Importance
- The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data Only
- The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification
- The Separation Capacity of Random Neural Networks
- The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit
- The Simplicity Bias in Multi-Task RNNs: Shared Attractors, Reuse of Dynamics, and Geometric Representation
- The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation
- The s-value: evaluating stability with respect to distributional shifts
- The Symbiosis of Deep Learning and Differential Equations -- III
- The Target-Charging Technique for Privacy Analysis across Interactive Computations
- The ToMCAT Dataset
- The Transient Nature of Emergent In-Context Learning in Transformers
- The Tunnel Effect: Building Data Representations in Deep Neural Networks
- The Utility of “Even if” Semifactual Explanation to Optimise Positive Outcomes
- The Waymo Open Sim Agents Challenge
- Thin and deep Gaussian processes
- Thinker: Learning to Plan and Act
- Third Workshop on Efficient Natural Language and Speech Processing (ENLSP-III): Towards the Future of Large Language Models and their Emerging Descendants
- This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations
- Thought Cloning: Learning to Think while Acting by Imitating Human Thinking
- Three Iterations of (d − 1)-WL Test Distinguish Non Isometric Clouds of d-dimensional Points
- Three Towers: Flexible Contrastive Learning with Pretrained Image Models
- Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance
- Thrust: Adaptively Propels Large Language Models with External Knowledge
- TIES-Merging: Resolving Interference When Merging Models
- Tight Bounds for Volumetric Spanners and Applications
- Tight Risk Bounds for Gradient Descent on Separable Data
- Time-Independent Information-Theoretic Generalization Bounds for SGLD
- Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value
- Time Series as Images: Vision Transformer for Irregularly Sampled Time Series
- Time Series Kernels based on Nonlinear Vector AutoRegressive Delay Embeddings
- Time-uniform confidence bands for the CDF under nonstationarity
- Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics
- TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation
- TOA: Task-oriented Active VQA
- Token-Scaled Logit Distillation for Ternary Weight Generative Language Models
- Toolbox for Multimodal Learn (scikit-multimodallearn)
- Toolformer: Language Models Can Teach Themselves to Use Tools
- ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings
- ToolQA: A Dataset for LLM Question Answering with External Tools
- Tools for Verifying Neural Models' Training Data
- Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification
- Topological Obstructions and How to Avoid Them
- Topological Parallax: A Geometric Specification for Deep Perception Models
- Topological RANSAC for instance verification and retrieval without fine-tuning
- Topology-Aware Uncertainty for Image Segmentation
- TopoSRL: Topology preserving self-supervised Simplicial Representation Learning
- TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models
- To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis
- To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning
- Touch Processing: a new Sensing Modality for AI
- Toward Better PAC-Bayes Bounds for Uniformly Stable Algorithms
- Toward Re-Identifying Any Animal
- Towards Accelerated Model Training via Bayesian Data Selection
- Towards a Comprehensive Benchmark for High-Level Synthesis Targeted to FPGAs
- Towards a fuller understanding of neurons with Clustered Compositional Explanations
- Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity
- Towards A Richer 2D Understanding of Hands at Scale
- Towards a Unified Analysis of Kernel-based Methods Under Covariate Shift
- Towards a Unified Framework of Contrastive Learning for Disentangled Representations
- Towards Automated Circuit Discovery for Mechanistic Interpretability
- Towards Better Dynamic Graph Learning: New Architecture and Unified Library
- Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games
- Towards Combinatorial Generalization for Catalysts: A Kohn-Sham Charge-Density Approach
- Towards Consistent Video Editing with Text-to-Image Diffusion Models
- Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask?
- Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression
- Towards Distribution-Agnostic Generalized Category Discovery
- Towards Efficient and Accurate Winograd Convolution via Full Quantization
- Towards Efficient Image Compression Without Autoregressive Models
- Towards Efficient Pre-Trained Language Model via Feature Correlation Distillation
- Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly
- Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning
- Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior
- Towards Free Data Selection with General-Purpose Models
- Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation
- Towards Higher Ranks via Adversarial Weight Pruning
- Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network
- Towards In-context Scene Understanding
- Towards Label-free Scene Understanding by Vision Foundation Models
- Towards Label Position Bias in Graph Neural Networks
- Towards Last-layer Retraining for Group Robustness with Fewer Annotations
- Towards Optimal Caching and Model Selection for Large Model Inference
- Towards Optimal Effective Resistance Estimation
- Towards Personalized Federated Learning via Heterogeneous Model Reassembly
- Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective
- Towards Robust and Expressive Whole-body Human Pose and Shape Estimation
- Towards robust and generalizable representations of extracellular data using contrastive learning
- Towards Self-Interpretable Graph-Level Anomaly Detection
- Towards Semi-Structured Automatic ICD Coding via Tree-based Contrastive Learning
- Towards Stable Backdoor Purification through Feature Shift Tuning
- Towards Symmetry-Aware Generation of Periodic Materials
- Towards Test-Time Refusals via Concept Negation
- Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities
- Towards Unbounded Machine Unlearning
- Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent
- Toward Understanding Generative Data Augmentation
- TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs
- Tracking Most Significant Shifts in Nonparametric Contextual Bandits
- Tracr: Compiled Transformers as a Laboratory for Interpretability
- TradeMaster: A Holistic Quantitative Trading Platform Empowered by Reinforcement Learning
- Trade-off Between Efficiency and Consistency for Removal-based Explanations
- Trading-off price for data quality to achieve fair online allocation
- Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models
- Train Hard, Fight Easy: Robust Meta Reinforcement Learning
- Training biologically plausible recurrent neural networks on cognitive tasks with long-term dependencies
- Training Chain-of-Thought via Latent-Variable Inference
- Training Energy-Based Normalizing Flow with Score-Matching Objectives
- Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis
- Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete
- Training Neural Networks is NP-Hard in Fixed Dimension
- Training neural operators to preserve invariant measures of chaotic attractors
- Training on Foveated Images Improves Robustness to Adversarial Attacks
- Training Private Models That Know What They Don’t Know
- Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign?
- Training Transformers with 4-bit Integers
- Training Transitive and Commutative Multimodal Transformers with LoReTTa
- Training Your Image Restoration Network Better with Random Weight Network as Optimization Function
- Train 'n Trade: Foundations of Parameter Markets
- Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks
- Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning
- trajdata: A Unified Interface to Multiple Human Trajectory Datasets
- Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory
- Trans-Dimensional Generative Modeling via Jump Diffusion Models
- Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings
- Transfer learning for atomistic simulations using GNNs and kernel mean embeddings
- Transfer Learning with Affine Model Transformation
- Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks
- Transformer as a hippocampal memory consolidation model based on NMDAR-inspired nonlinearity
- Transformer-based Planning for Symbolic Regression
- Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars
- Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection
- Transformers learn through gradual rank increase
- Transformers learn to implement preconditioned gradient descent for in-context learning
- Transformers over Directed Acyclic Graphs
- TransHP: Image Classification with Hierarchical Prompting
- Transient Neural Radiance Fields for Lidar View Synthesis and 3D Reconstruction
- Transition-constant Normalization for Image Enhancement
- Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships
- Transportability for Bandits with Data from Different Environments
- Tree-Based Diffusion Schrödinger Bridge with Applications to Wasserstein Barycenters
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models
- Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images
- Tree Variational Autoencoders
- TRIAGE: Characterizing and auditing training data for improved regression
- Trial matching: capturing variability with data-constrained spiking neural networks
- Triangulation Residual Loss for Data-efficient 3D Pose Estimation
- Triple Eagle: Simple, Fast and Practical Budget-Feasible Mechanisms
- TriRE: A Multi-Mechanism Learning Paradigm for Continual Knowledge Retention and Promotion
- TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models
- Truly Scale-Equivariant Deep Nets with Fourier Layers
- Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection
- Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach
- Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints
- Trust Your $\nabla$: Gradient-based Intervention Targeting for Causal Discovery
- Tuning Multi-mode Token-level Prompt Alignment across Modalities
- Turbulence in Focus: Benchmarking Scaling Behavior of 3D Volumetric Super-Resolution with BLASTNet 2.0 Data
- TWIGMA: A dataset of AI-Generated Images with Metadata From Twitter
- Two Heads are Better Than One: A Simple Exploration Framework for Efficient Multi-Agent Reinforcement Learning
- Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods
- Two Sides of The Same Coin: Bridging Deep Equilibrium Models and Neural ODEs via Homotopy Continuation
- Two-Stage Learning to Defer with Multiple Experts
- Two-Stage Predict+Optimize for MILPs with Unknown Parameters in Constraints
- Type-to-Track: Retrieve Any Object via Prompt-based Tracking
- UDC-SIT: A Real-World Dataset for Under-Display Cameras
- UE4-NeRF:Neural Radiance Field for Real-Time Rendering of Large-Scale Scene
- UltraRE: Enhancing RecEraser for Recommendation Unlearning via Error Decomposition
- Unbalanced Low-rank Optimal Transport Solvers
- Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?
- Unbiased constrained sampling with Self-Concordant Barrier Hamiltonian Monte Carlo
- Unbiased learning of deep generative models with structured discrete representations
- Unbounded Differentially Private Quantile and Maximum Estimation
- Uncertainty-Aware Alignment Network for Cross-Domain Video-Text Retrieval
- Uncertainty-Aware Instance Reweighting for Off-Policy Learning
- Uncertainty Estimation for Safety-critical Scene Segmentation via Fine-grained Reward Maximization
- Uncertainty Quantification over Graph with Conformalized Graph Neural Networks
- Uncertainty Quantification via Neural Posterior Principal Components
- Unconstrained Dynamic Regret via Sparse Coding
- Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback
- Uncovering and Quantifying Social Biases in Code Generation
- Uncovering Meanings of Embeddings via Partial Orthogonality
- Uncovering motifs of concurrent signaling across multiple neuronal populations
- Uncovering Neural Scaling Laws in Molecular Representation Learning
- Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation
- Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts
- Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning
- Understanding and Improving Ensemble Adversarial Defense
- Understanding and Improving Feature Learning for Out-of-Distribution Generalization
- Understanding and Mitigating Copying in Diffusion Models
- Understanding Contrastive Learning via Distributionally Robust Optimization
- Understanding Deep Gradient Leakage via Inversion Influence Functions
- Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation
- Understanding Few-Shot Learning: Measuring Task Relatedness and Adaptation Difficulty via Attributes
- Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization
- Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks
- Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers
- Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL
- Understanding Social Reasoning in Language Models with Language Models
- Understanding the detrimental class-level effects of data augmentation
- Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry
- Understanding the Limitations of Deep Models for Molecular property prediction: Insights and Solutions
- Undirected Probabilistic Model for Tensor Decomposition
- Unexpected Improvements to Expected Improvement for Bayesian Optimization
- Uni3DETR: Unified 3D Detection Transformer
- UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
- Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
- Unified 3D Segmenter As Prototypical Classifiers
- Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems
- Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy
- Unified Lower Bounds for Interactive High-dimensional Estimation under Information Constraints
- Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective
- Unified Segment-to-Segment Framework for Simultaneous Sequence Generation
- Uniform Convergence with Square-Root Lipschitz Loss
- Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent
- Unifying GANs and Score-Based Diffusion as Generative Particle Models
- Unifying Predictions of Deterministic and Stochastic Physics in Mesh-reduced Space with Sequential Flow Generative Model
- UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models
- UniReps: Unifying Representations in Neural Models
- UniT: A Unified Look at Certified Robust Training against Text Adversarial Perturbation
- UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition
- Universal Gradient Descent Ascent Method for Nonconvex-Nonconcave Minimax Optimization
- Universality and Limitations of Prompt Tuning
- Universality laws for Gaussian mixtures in generalized linear models
- Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach
- Universal Prompt Tuning for Graph Neural Networks
- Unleashing the Full Potential of Product Quantization for Large-Scale Image Retrieval
- Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift
- Unleashing the Power of Randomization in Auditing Differentially Private ML
- Unleash the Potential of Image Branch for Cross-modal 3D Object Detection
- Unlimiformer: Long-Range Transformers with Unlimited Length Input
- Unlocking Deterministic Robustness Certification on ImageNet
- Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization
- Unpaired Multi-Domain Causal Representation Learning
- UNSSOR: Unsupervised Neural Speech Separation by Leveraging Over-determined Training Mixtures
- Unsupervised Anomaly Detection with Rejection
- Unsupervised Behavior Extraction via Random Intent Priors
- Unsupervised Graph Neural Architecture Search with Disentangled Self-Supervision
- Unsupervised Image Denoising with Score Function
- Unsupervised Learning for Solving the Travelling Salesman Problem
- Unsupervised Optical Flow Estimation with Dynamic Timing Representation for Spike Camera
- Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reduction
- Unsupervised Protein-Ligand Binding Energy Prediction via Neural Euler's Rotation Equation
- Unsupervised Semantic Correspondence Using Stable Diffusion
- Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective
- UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models
- UP-NeRF: Unconstrained Pose Prior-Free Neural Radiance Field
- URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates
- Use perturbations when learning from explanations
- User-Level Differential Privacy With Few Examples Per User
- Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models
- Utilitarian Algorithm Configuration
- UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction
- Validated Image Caption Rating Dataset
- VanillaNet: the Power of Minimalism in Deep Learning
- Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies
- Variational Annealing on Graphs for Combinatorial Optimization
- Variational Gaussian processes for linear inverse problems
- Variational Gaussian Processes with Decoupled Conditionals
- Variational Gibbs Inference for Statistical Model Estimation from Incomplete Data
- Variational Imbalanced Regression: Fair Uncertainty Quantification via Probabilistic Smoothing
- Variational Inference with Gaussian Score Matching
- Variational Monte Carlo on a Budget — Fine-tuning pre-trained Neural Wavefunctions
- Variational Weighting for Kernel Density Ratios
- VaRT: Variational Regression Trees
- VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
- VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens
- VeriX: Towards Verified Explainability of Deep Neural Networks
- Versatile Energy-Based Probabilistic Models for High Energy Physics
- ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields
- VidChapters-7M: Video Chapters at Scale
- VideoComposer: Compositional Video Synthesis with Motion Controllability
- Video Dynamics Prior: An Internal Learning Approach for Robust Video Enhancements
- Video-Mined Task Graphs for Keystep Recognition in Instructional Videos
- Video Prediction Models as Rewards for Reinforcement Learning
- Video Timeline Modeling For News Story Understanding
- VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
- V-InFoR: A Robust Graph Neural Networks Explainer for Structurally Corrupted Graphs
- VisAlign: Dataset for Measuring the Alignment between AI and Humans in Visual Perception
- VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks
- VisIT-Bench: A Dynamic Benchmark for Evaluating Instruction-Following Vision-and-Language Models
- VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution
- ViSt3D: Video Stylization with 3D CNN
- Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution
- Visual Instruction Inversion: Image Editing via Image Prompting
- Visual Instruction Tuning
- Visual Programming for Step-by-Step Text-to-Image Generation and Evaluation
- VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
- Vocabulary-free Image Classification
- VOCE: Variational Optimization with Conservative Estimation for Offline Safe Reinforcement Learning
- Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
- Volume Feature Rendering for Fast Neural Radiance Field Reconstruction
- VoxDet: Voxel Learning for Novel Instance Detection
- VPGTrans: Transfer Visual Prompt Generator across LLMs
- VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation
- VRA: Variational Rectified Activation for Out-of-distribution Detection
- VTaC: A Benchmark Dataset of Ventricular Tachycardia Alarms from ICU Monitors
- Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attacks
- WalkLM: A Uniform Language Model Fine-tuning Framework for Attributed Graph Embedding
- Wasserstein distributional robustness of neural networks
- Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies
- Wasserstein Quantum Monte Carlo: A Novel Approach for Solving the Quantum Many-Body Schrödinger Equation
- Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research
- Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets
- WBCAtt: A White Blood Cell Dataset Annotated with Detailed Morphological Attributes
- WCLD: Curated Large Dataset of Criminal Cases from Wisconsin Circuit Courts
- Weakly Coupled Deep Q-Networks
- Weakly Supervised 3D Open-vocabulary Segmentation
- Weakly-Supervised Audio-Visual Segmentation
- Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping
- Weighted ROC Curve in Cost Space: Extending AUC to Cost-Sensitive Learning
- Weitzman's Rule for Pandora's Box with Correlations
- What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation
- What can a Single Attention Layer Learn? A Study Through the Random Features Lens
- What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks
- What can we do about NeurIPS Reviewer #2?Challenges, Solutions, Experiments and Open Problemsin Peer Review
- What Can We Learn from Unlearnable Datasets?
- What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?
- What Do Deep Saliency Models Learn about Visual Attention?
- What functions can Graph Neural Networks compute on random graphs? The role of Positional Encoding
- What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization
- What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models
- What Knowledge Gets Distilled in Knowledge Distillation?
- What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement.
- What Makes Good Examples for Visual In-Context Learning?
- What Planning Problems Can A Relational Neural Network Solve?
- What’s Left? Concept Grounding with Logic-Enhanced Foundation Models
- What Truly Matters in Trajectory Prediction for Autonomous Driving?
- What You See is What You Read? Improving Text-Image Alignment Evaluation
- When are ensembles really effective?
- When can Regression-Adjusted Control Variate Help? Rare Events, Sobolev Embedding and Minimax Optimality
- When Can We Track Significant Preference Shifts in Dueling Bandits?
- When Demonstrations meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning
- When Does Confidence-Based Cascade Deferral Suffice?
- When Does Optimizing a Proper Loss Yield Calibration?
- When Do Graph Neural Networks Help with Node Classification? Investigating the Homophily Principle on Node Distinguishability
- When Do Neural Nets Outperform Boosted Trees on Tabular Data?
- When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment
- When is Agnostic Reinforcement Learning Statistically Tractable?
- When Visual Prompt Tuning Meets Source-Free Domain Adaptive Semantic Segmentation
- Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objects
- Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?
- Where Did I Come From? Origin Attribution of AI-Generated Images
- Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness
- White-Box Transformers via Sparse Rate Reduction
- Why Did This Model Forecast This Future? Information-Theoretic Saliency for Counterfactual Explanations of Probabilistic Regression Models
- Why Does Sharpness-Aware Minimization Generalize Better Than SGD?
- “Why Not Looking backward?” A Robust Two-Step Method to Automatically Terminate Bayesian Optimization
- Why think step by step? Reasoning emerges from the locality of experience
- Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models
- WildfireSpreadTS: A dataset of multi-modal time series for wildfire spread prediction
- Window-Based Distribution Shift Detection for Deep Neural Networks
- Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model
- Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization
- WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting
- WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data
- Workshop on Advancing Neural Network Training (WANT): Computational Efficiency, Scalability, and Resource Optimization
- Workshop on Distribution Shifts: New Frontiers with Foundation Models
- Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS 2023 (FL@FM-NeurIPS'23)
- Workshop on robustness of zero/few-shot learning in foundation models (R0-FoMo)
- Worst-case Performance of Popular Approximate Nearest Neighbor Search Implementations: Guarantees and Limitations
- Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis
- Wyze Rule: Federated Rule Dataset for Rule Recommendation Benchmarking
- XAGen: 3D Expressive Human Avatars Generation
- XAI in Action: Past, Present, and Future Applications
- XES3G5M: A Knowledge Tracing Benchmark Dataset with Auxiliary Information
- xTrimoGene: An Efficient and Scalable Representation Learner for Single-Cell RNA-Seq Data
- You Only Condense Once: Two Rules for Pruning Condensed Datasets
- Your representations are in the network: composable and parallel adaptation for large scale models
- YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus
- YouTubePD: A Multimodal Benchmark for Parkinson’s Disease Analysis
- Zero-One Laws of Graph Neural Networks
- Zero-Regret Performative Prediction Under Inequality Constraints
- Zero-Shot Anomaly Detection via Batch Normalization
- Zero-shot causal learning
- Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models
- Zero-sum Polymatrix Markov Games: Equilibrium Collapse and Efficient Computation of Nash Equilibria
- Zeroth-Order Methods for Nondifferentiable, Nonconvex, and Hierarchical Federated Optimization
- ZipLM: Inference-Aware Structured Pruning of Language Models
- ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking