Downloads 2024
Number of events: 2341
- $\alpha$TC-VAE: On the relationship between Disentanglement and Diversity
- $\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States
- $\mathbb{D}^2$ Pruning: Message Passing for Balancing Diversity & Difficulty in Data Pruning
- $\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis
- $\pi$2vec: Policy Representation with Successor Features
- $t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence
- $\texttt{NAISR}$: A 3D Neural Additive Model for Interpretable Shape Representation
- 2nd Workshop on Mathematical and Empirical Understanding of Foundation Models
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation
- 3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining
- 3D Reconstruction with Generalizable Neural Fields using Scene Priors
- 5th Workshop on African Natural Language Processing (AfricaNLP 2024)
- 5th Workshop on practical ML for limited/low resource settings (PML4LRS) @ ICLR 2024
- A 2-Dimensional State Space Layer for Spatial Inductive Bias
- A Benchmark for Learning to Translate a New Language from One Grammar Book
- A Benchmark Study on Calibration
- A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
- A Branching Decoder for Set Generation
- Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers
- Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise
- Accelerated Sampling with Stacked Restricted Boltzmann Machines
- Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
- Accelerating Distributed Stochastic Optimization via Self-Repellent Random Walks
- Accelerating Sinkhorn algorithm with sparse Newton iterations
- Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks
- Accurate Forgetting for Heterogeneous Federated Continual Learning
- Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models
- A Characterization Theorem for Equivariant Networks with Point-wise Activations
- Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning
- Achieving Human Parity in Content-Grounded Datasets Generation
- Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping
- Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits
- A Cognitive Model for Learning Abstract Relational Structures from Memory-based Decision-Making Tasks
- ACRF: Compressing Explicit Neural Radiance Fields via Attribute Compression
- Active Retrosynthetic Planning Aware of Route Quality
- Active Test-Time Adaptation: Theoretical Analyses and An Algorithm
- AdaMerging: Adaptive Model Merging for Multi-Task Learning
- Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees
- Adapting Large Language Models via Reading Comprehension
- Adapting to Distribution Shift by Visual Domain Prompt Generation
- Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts
- Adaptive deep spiking neural network with global-local learning via balanced excitatory and inhibitory mechanism
- Adaptive Federated Learning with Auto-Tuned Clients
- Adaptive Instrument Design for Indirect Experiments
- Adaptive Rational Activations to Boost Deep Reinforcement Learning
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice
- Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation
- Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders
- Adaptive Self-training Framework for Fine-grained Scene Graph Generation
- Adaptive Sharpness-Aware Pruning for Robust Sparse Networks
- Adaptive Stochastic Gradient Algorithm for Black-box Multi-Objective Learning
- Adaptive Window Pruning for Efficient Local Motion Deblurring
- A Data-Driven Measure of Relative Uncertainty for Misclassification Detection
- ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process
- Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
- Addressing Signal Delay in Deep Reinforcement Learning
- A differentiable brain simulator bridging brain simulation and brain-inspired computing
- A Differentially Private Clustering Algorithm for Well-Clustered Graphs
- A Discretization Framework for Robust Contextual Stochastic Optimization
- AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models
- ADOPD: A Large-Scale Document Page Decomposition Dataset
- Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
- Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness
- Adversarial Adaptive Sampling: Unify PINN and Optimal Transport for the Approximation of PDEs
- Adversarial Attacks on Fairness of Graph Neural Networks
- Adversarial AutoMixup
- Adversarial Causal Bayesian Optimization
- Adversarial Feature Map Pruning for Backdoor
- Adversarial Imitation Learning via Boosting
- Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive
- Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
- Adversarial Training Should Be Cast as a Non-Zero-Sum Game
- A Dynamical View of the Question of Why
- A Fast and Provable Algorithm for Sparse Phase Retrieval
- AffineQuant: Affine Transformation Quantization for Large Language Models
- A Flexible Generative Model for Heterogeneous Tabular EHR with Missing Modality
- A Foundation Model for Error Correction Codes
- A Framework and Benchmark for Deep Batch Active Learning for Regression
- A Framework for Inference Inspired by Human Memory Mechanisms
- A General Framework for User-Guided Bayesian Optimization
- A Generalist Agent
- AgentBench: Evaluating LLMs as Agents
- AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
- AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation
- A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation
- A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
- A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
- A Hierarchical Bayesian Model for Few-Shot Meta Learning
- AI4DifferentialEquations In Science
- AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction
- ALAM: Averaged Low-Precision Activation for Memory-Efficient Training of Transformer Models
- Algorithms for Caching and MTS with reduced number of predictions
- Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic
- A Lie Group Approach to Riemannian Batch Normalization
- A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averaging
- AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
- Aligning Relational Learning with Lipschitz Fairness
- Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework
- A Linear Algebraic Framework for Counterfactual Generation
- Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
- AlpaGasus: Training a Better Alpaca with Fewer Data
- Alt-Text with Context: Improving Accessibility for Images on Twitter
- AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents
- Amortized Network Intervention to Steer the Excitatory Point Processes
- AmortizedPeriod: Attention-based Amortized Inference for Periodicity Identification
- Amortizing intractable inference in large language models
- A Multi-Level Framework for Accelerating Training Transformer Models
- A Mutual Information Perspective on Federated Contrastive Learning
- An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
- Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity
- Analytically Tractable Hidden-States Inference in Bayesian Neural Networks
- Analyzing and Improving Optimal-Transport-based Adversarial Networks
- Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
- Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps
- An Analytical Solution to Gauss-Newton Loss for Direct Image Alignment
- An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization
- An Efficient Tester-Learner for Halfspaces
- An Emulator for Fine-tuning Large Language Models using Small Language Models
- A Neural Framework for Generalized Causal Sensitivity Analysis
- A Newborn Embodied Turing Test for Comparing Object Segmentation Across Animals and Machines
- An Extensible Framework for Open Heterogeneous Collaborative Perception
- An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models
- AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
- An improved analysis of per-sample and per-update clipping in federated learning
- An interpretable error correction method for enhancing code-to-code translation
- An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks
- An Investigation of Representation and Allocation Harms in Contrastive Learning
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack
- Annealing Self-Distillation Rectification Improves Adversarial Training
- AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection
- An operator preconditioning perspective on training in physics-informed machine learning
- AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
- An Unforgeable Publicly Verifiable Watermark for Large Language Models
- AnyText: Multilingual Visual Text Generation and Editing
- A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models
- A path-norm toolkit for modern networks: consequences, promises and challenges
- A Plug-and-Play Image Registration Network
- A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs
- A Policy Gradient Method for Confounded POMDPs
- Approximately Piecewise E(3) Equivariant Point Networks
- Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization
- A Precise Characterization of SGD Stability Using Loss Surface Geometry
- A Primal-Dual Approach to Solving Variational Inequalities with General Constraints
- A Probabilistic Framework for Modular Continual Learning
- A Progressive Training Framework for Spiking Neural Networks with Learnable Multi-hierarchical Model
- A Quadratic Synchronization Rule for Distributed Deep Learning
- ArchLock: Locking DNN Transferability at the Architecture Level with a Zero-Cost Binary Predictor
- A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
- Are Bert Family Good Instruction Followers? A Study on Their Potential And Limitations
- A Recipe for Improved Certifiable Robustness
- Are Human-generated Demonstrations Necessary for In-context Learning?
- Are Models Biased on Text without Gender-related Language?
- A representation-learning game for classes of prediction tasks
- A Restoration Network as an Implicit Prior
- Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?
- ARGS: Alignment as Reward-Guided Search
- ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning
- A ROBUST DIFFERENTIAL NEURAL ODE OPTIMIZER
- A Semantic Invariant Robust Watermark for Large Language Models
- ASID: Active Exploration for System Identification in Robotic Manipulation
- A Simple and Effective Pruning Approach for Large Language Models
- A Simple and Scalable Representation for Graph Generation
- A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis
- A Simple Romance Between Multi-Exit Vision Transformer and Token Reduction
- ASMR: Activation-Sharing Multi-Resolution Coordinate Networks for Efficient Inference
- Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face Recognition
- A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks
- A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data
- A Study of Bayesian Neural Network Surrogates for Bayesian Optimization
- A Sublinear Adversarial Training Algorithm
- A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors
- Asymptotically Free Sketched Ridge Ensembles: Risks, Cross-Validation, and Tuning
- A Topological Perspective on Demystifying GNN-Based Link Prediction Performance
- Attacking Perceptual Similarity Metrics
- Attention-based Iterative Decomposition for Tensor Product Representation
- Attention-Guided Contrastive Role Representations for Multi-agent Reinforcement Learning
- Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models
- AttEXplore: Attribution for Explanation with model parameters eXploration
- At Which Training Stage Does Code Data Help LLMs Reasoning?
- AUC-CL: A Batchsize-Robust Framework for Self-Supervised Contrastive Representation Learning
- AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Images
- AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation
- Augmented Bayesian Policy Search
- Augmenting Transformers with Recursively Composed Multi-grained Representations
- A Unified and General Framework for Continual Learning
- A Unified Experiment Design Approach for Cyclic and Acyclic Causal Models
- A Unified Framework for Bayesian Optimization under Contextual Uncertainty
- A Unified Sampling Framework for Solver Searching of Diffusion Probabilistic Models
- A unique M-pattern for micro-expression spotting in long videos
- AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval
- AutoChunk: Automated Activation Chunk for Memory-Efficient Deep Learning Inference
- AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
- AutoLoRa: An Automated Robust Fine-Tuning Framework
- Automatic Functional Differentiation in JAX
- AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ
- AutoVP: An Automated Visual Prompting Framework and Benchmark
- Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost
- A Variational Framework for Estimating Continuous Treatment Effects with Measurement Error
- A Variational Perspective on Solving Inverse Problems with Diffusion Models
- A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables
- Backdoor Contrastive Learning via Bi-level Trigger Optimization
- Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
- Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
- BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
- BadEdit: Backdooring Large Language Models by Model Editing
- BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
- Balancing Act: Constraining Disparate Impact in Sparse Models
- Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation
- Bandits with Replenishable Knapsacks: the Best of both Worlds
- BarLeRIa: An Efficient Tuning Framework for Referring Image Segmentation
- Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering
- Batched Low-Rank Adaptation of Foundation Models
- Batch normalization is sufficient for universal function approximation in CNNs
- BatchPrompt: Accomplish more with less
- BatteryML: An Open-source Platform for Machine Learning on Battery Degradation
- Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information
- BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference
- Bayesian Bi-clustering of Neural Spiking Activity with Latent Structures
- Bayesian Coreset Optimization for Personalized Federated Learning
- Bayesian Low-rank Adaptation for Large Language Models
- Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation
- Bayesian Optimization through Gaussian Cox Process Models for Spatio-temporal Data
- BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction
- Beam Enumeration: Probabilistic Explainability For Sample Efficient Self-conditioned Molecular Design
- Beating Price of Anarchy and Gradient Descent without Regret in Potential Games
- Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference
- Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
- BECLR: Batch Enhanced Contrastive Few-Shot Learning
- Behaviour Distillation
- Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations
- Bellman Optimal Stepsize Straightening of Flow-Matching Models
- Be More Active! Understanding the Differences Between Mean and Sampled Representations of Variational Autoencoders
- Benchmarking Algorithms for Federated Domain Generalization
- Benchmarking and Improving Generator-Validator Consistency of Language Models
- BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks
- Benign Oscillation of Stochastic Gradient Descent with Large Learning Rate
- Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data
- BENO: Boundary-embedded Neural Operators for Elliptic PDEs
- BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation
- Bespoke Solvers for Generative Flow Models
- Better Neural PDE Solvers Through Data-Free Mesh Movers
- Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain
- Beyond IID weights: sparse and low-rank deep Neural Networks are also Gaussian Processes
- Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment
- Beyond Memorization: Violating Privacy via Inference with Large Language Models
- Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints
- Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs
- Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods
- Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learning
- Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders
- Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness
- Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
- Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values
- Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
- Bidirectional Temporal Diffusion Model for Temporally Consistent Human Animation
- Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis
- BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs
- Blending Imitation and Reinforcement Learning for Robust Policy Improvement
- Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
- BooookScore: A systematic exploration of book-length summarization in the era of LLMs
- Boosting Graph Anomaly Detection with Adaptive Message Passing
- Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models
- Boosting the Adversarial Robustness of Graph Neural Networks: An OOD Perspective
- Boosting Vanilla Lightweight Vision Transformers via Re-parameterization
- Bootstrapping Variational Information Pursuit with Large Language and Vision Models for Interpretable Image Classification
- Boundary Denoising for Video Activity Localization
- Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments
- Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
- Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation
- Brain decoding: toward real-time reconstruction of visual perception
- BrainLM: A foundation model for brain activity recordings
- BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity
- Branch-GAN: Improving Text Generation with (not so) Large Language Models
- Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages
- Bridging Neural and Symbolic Representations with Transitional Dictionary Learning
- Bridging State and History Representations: Understanding Self-Predictive RL
- Bridging the Gap Between Practice and Theory in Deep Learning
- Bridging Vision and Language Spaces with Assignment Prediction
- BroGNet: Momentum-Conserving Graph Neural Stochastic Differential Equation for Learning Brownian Dynamics
- BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK
- BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
- Building Cooperative Embodied Agents Modularly with Large Language Models
- Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
- Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game
- CABINET: Content Relevance-based Noise Reduction for Table Question Answering
- CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling
- CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception
- CAMBranch: Contrastive Learning with Augmented MILPs for Branching
- Cameras as Rays: Pose Estimation via Ray Diffusion
- CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images
- Candidate Label Set Pruning: A Data-centric Perspective for Deep Partial-label Learning
- Can Large Language Models Infer Causation from Correlation?
- Can LLM-Generated Misinformation Be Detected?
- Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
- Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
- Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks
- Can Transformers Capture Spatial Relations between Objects?
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?
- Can we get the best of both Binary Neural Networks and Spiking Neural Networks for Efficient Computer Vision?
- CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting
- CAS: A Probability-Based Approach for Universal Condition Alignment Score
- Cascading Reinforcement Learning
- Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
- Cauchy-Schwarz Divergence Information Bottleneck for Regression
- Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework
- Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencoder
- Causality-Inspired Spatial-Temporal Explanations for Dynamic Graph Neural Networks
- CausalLM is not optimal for in-context learning
- Causally Aligned Curriculum Learning
- Causal Modelling Agents: Causal Graph Discovery through Synergising Metadata- and Data-driven Reasoning
- Causal-StoNet: Causal Inference for High-Dimensional Complex Data
- Causal Structure Recovery with Latent Variables under Milder Distributional and Graphical Assumptions
- CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery
- CCIL: Continuity-Based Data Augmentation for Corrective Imitation Learning
- CellPLM: Pre-training of Cell Language Model Beyond Single Cells
- Certified Adversarial Robustness for Rate Encoded Spiking Neural Networks
- Chain-of-Experts: When LLMs Meet Complex Operations Research Problems
- Chain of Hindsight aligns Language Models with Feedback
- Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources
- Chain of Log-Concave Markov Chains
- Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
- Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
- Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning
- Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
- CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis
- Circuit Component Reuse Across Tasks in Transformer Language Models
- CircuitNet 2.0: An Advanced Dataset for Promoting Machine Learning Innovations in Realistic Chip Design Environment
- Circumventing Concept Erasure Methods For Text-To-Image Generative Models
- CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents
- CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech
- CLAP: Collaborative Adaptation for Patchwork Learning
- Classification with Conceptual Safeguards
- Class Incremental Learning via Likelihood Ratio Based Task Prediction
- Class Probability Matching with Calibrated Networks for Label Shift Adaption
- Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform
- CLEX: Continuous Length Extrapolation for Large Language Models
- Clifford Group Equivariant Simplicial Message Passing Networks
- ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs
- CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic Decoding
- CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
- CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?
- Closing the Curious Case of Neural Text Degeneration
- Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.
- CNN Kernels Can Be the Best Shapelets
- CO2: Efficient Distributed Training with Full Communication-Computation Overlap
- CoBIT: A Contrastive Bi-directional Image-Text Generation Model
- COCO-Periph: Bridging the Gap Between Human and Machine Perception in the Periphery
- CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
- CODE REPRESENTATION LEARNING AT SCALE
- Coeditor: Leveraging Repo-level Diffs for Code Auto-editing
- COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits
- CoLiDE: Concomitant Linear DAG Estimation
- COLLIE: Systematic Construction of Constrained Text Generation Tasks
- Combinatorial Bandits for Maximum Value Reward Function under Value-Index Feedback
- Combining Axes Preconditioners through Kronecker Approximation for Deep Learning
- Communication-Efficient Federated Non-Linear Bandit Optimization
- Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates
- CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models
- Complete and Efficient Graph Transformers for Crystal Material Property Prediction
- Complex priors and flexible inference in recurrent circuits with dendritic nonlinearities
- Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis
- Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization
- Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning
- Compositional Generative Inverse Design
- Compositional Preference Models for Aligning LMs
- Compressed Context Memory for Online Language Model Interaction
- Compressing Latent Space via Least Volume
- Compressing LLMs: The Truth is Rarely Pure and Never Simple
- Concept Bottleneck Generative Models
- Conditional Information Bottleneck Approach for Time Series Imputation
- Conditional Instrumental Variable Regression with Representation Learning for Causal Inference
- Conditional Variational Diffusion Models
- Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
- Confidential-DPproof: Confidential Proof of Differentially Private Training
- Conformal Inductive Graph Neural Networks
- Conformal Language Modeling
- Conformal Prediction via Regression-as-Classification
- Conformal Risk Control
- Confronting Reward Model Overoptimization with Constrained RLHF
- ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection
- Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data
- Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
- ConR: Contrastive Regularizer for Deep Imbalanced Regression
- Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning
- Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training
- Consistency-guided Prompt Learning for Vision-Language Models
- Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning
- Consistency Training with Learnable Data Augmentation for Graph Anomaly Detection with Limited Supervision
- Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
- Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video
- Consistent algorithms for multi-label classification with macro-at-$k$ metrics
- Consistent Multi-Class Classification from Multiple Unlabeled Datasets
- Consistent Video-to-Video Transfer Using Synthetic Dataset
- Constrained Bi-Level Optimization: Proximal Lagrangian Value Function Approach and Hessian-free Algorithm
- Constrained Decoding for Cross-lingual Label Projection
- Constraint-Free Structure Learning with Smooth Acyclic Orientations
- Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit
- Context-Aware Meta-Learning
- Context is Environment
- ContextRef: Evaluating Referenceless Metrics for Image Description Generation
- Contextual Bandits with Online Neural Regression
- Continual Learning in the Presence of Spurious Correlations: Analyses and a Simple Baseline
- Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation
- Continual Momentum Filtering on Parameter Space for Online Test-time Adaptation
- Continuous Field Reconstruction from Sparse Observations with Implicit Neural Networks
- Continuous Invariance Learning
- Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach
- Contrastive Difference Predictive Coding
- Contrastive Learning is Spectral Clustering on Similarity Graph
- Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning
- Controlled Text Generation via Language Model Arithmetic
- Controlling Vision-Language Models for Multi-Task Image Restoration
- ControlVideo: Training-free Controllable Text-to-video Generation
- Convergence of Bayesian Bilevel Optimization
- Conversational Drug Editing Using Retrieval and Domain Feedback
- Convolutional Deep Kernel Machines
- Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model
- Coordinate-Aware Modulation for Neural Fields
- Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
- COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL
- Copula Conformal prediction for multi-step time series prediction
- Copyright Fundamentals for AI Researchers
- Copyright Fundamentals for AI Researchers
- Copyright Fundamentals for AI Researchers
- Copyright Fundamentals for AI Researchers
- CoRe-GD: A Hierarchical Framework for Scalable Graph Visualization with GNNs
- CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects
- Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
- COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
- CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding
- Counterfactual Density Estimation using Kernel Stein Discrepancies
- Counting Graph Substructures with Graph Neural Networks
- Course Correcting Koopman Representations
- CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding
- CPPO: Continual Learning for Reinforcement Learning with Human Feedback
- CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
- CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping
- Critical Learning Periods Emerge Even in Deep Linear Networks
- CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
- CrossLoco: Human Motion Driven Control of Legged Robots via Guided Unsupervised Reinforcement Learning
- Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing
- CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity
- Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding
- C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
- Curiosity-driven Red-teaming for Large Language Models
- Curriculum reinforcement learning for quantum architecture search under hardware errors
- Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning
- Cycle Consistency Driven Object Discovery
- DAFA: Distance-Aware Fair Adversarial Training
- DAM: Towards a Foundation Model for Forecasting
- Data-centric Machine Learning Research (DMLR): Harnessing Momentum for Science
- Data Debugging with Shapley Importance over Machine Learning Pipelines
- Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality
- Data Filtering Networks
- Data-independent Module-aware Pruning for Hierarchical Vision Transformers
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models
- DATS: Difficulty-Aware Task Sampler for Meta-Learning Physics-Informed Neural Networks
- Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation
- DDMI: Domain-agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations
- Debiased Collaborative Filtering with Kernel-Based Causal Balancing
- Debiasing Algorithm through Model Adaptation
- Debiasing Attention Mechanism in Transformer without Demographics
- Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold
- Deceptive Fairness Attacks on Graphs via Meta Learning
- Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making
- Decodable and Sample Invariant Continuous Object Encoder
- Decoding Natural Images from EEG for Object Recognition
- DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization
- Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems
- Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces
- Decoupled Marked Temporal Point Process using Neural Ordinary Differential Equations
- Decoupling regularization from the action space
- Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks
- Deep Confident Steps to New Pockets: Strategies for Docking Generalization
- Deep Generative Clustering with Multimodal Diffusion Variational Autoencoders
- Deep Geodesic Canonical Correlation Analysis for Covariance-Based Neuroimaging Data
- DEEP NEURAL NETWORK INITIALIZATION WITH SPARSITY INDUCING ACTIVATIONS
- Deep Neural Networks Tend To Extrapolate Predictably
- Deep Orthogonal Hypersphere Compression for Anomaly Detection
- Deep Reinforcement Learning for Modelling Protein Complexes
- Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling
- Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks
- DeepSPF: Spherical SO(3)-Equivariant Patches for Scan-to-CAD Estimation
- Deep Temporal Graph Clustering
- DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training
- Defining and extracting generalizable interaction primitives from DNNs
- Defining Expertise: Applications to Treatment Effect Estimation
- Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding
- Delta-AI: Local objectives for amortized inference in sparse graphical models
- Democratizing Fine-grained Visual Recognition with Large Language Models
- Demonstration-Regularized RL
- Demystifying CLIP Data
- Demystifying Embedding Spaces using Large Language Models
- Demystifying Linear MDPs and Novel Dynamics Aggregation Framework
- Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition
- Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
- DENEVIL: TOWARDS DECIPHERING AND NAVIGATING THE ETHICAL VALUES OF LARGE LANGUAGE MODELS VIA INSTRUCTION LEARNING
- Denoising Diffusion Bridge Models
- Denoising Diffusion Step-aware Models
- Denoising Diffusion via Image-Based Rendering
- Denoising Task Routing for Diffusion Models
- De novo Protein Design Using Geometric Vector Field Networks
- DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
- Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit
- Designing Skill-Compatible AI: Methodologies and Frameworks in Chess
- Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization
- Detecting, Explaining, and Mitigating Memorization in Diffusion Models
- Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy
- Detecting Pretraining Data from Large Language Models
- DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation
- Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making
- DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models
- Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
- Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks
- DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation
- DiffEnc: Variational Diffusion with a Learned Encoder
- Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstruction
- Differentiable Euler Characteristic Transforms for Shape Classification
- Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks
- Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
- Differentially Private Synthetic Data via Foundation Model APIs 1: Images
- DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation
- Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
- Diffusion in Diffusion: Cyclic One-Way Diffusion for Text-Vision-Conditioned Generation
- Diffusion Model for Dense Matching
- Diffusion Models for Multi-Task Generative Modeling
- DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
- Diffusion Posterior Sampling for Linear Inverse Problem Solving: A Filtering Perspective
- Diffusion Sampling with Momentum for Mitigating Divergence Artifacts
- DiffusionSat: A Generative Foundation Model for Satellite Imagery
- Diffusion-TS: Interpretable Diffusion for General Time Series Generation
- DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity
- DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models
- Directly Fine-Tuning Diffusion Models on Differentiable Rewards
- Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning
- Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search
- Discovering modular solutions that generalize compositionally
- Discovering Temporally-Aware Reinforcement Learning Algorithms
- DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation
- Disentangling Time Series Representations via Contrastive Independence-of-Support on l-Variational Inference
- Dissecting learning and forgetting in language model finetuning
- Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI
- DistillSpec: Improving Speculative Decoding via Knowledge Distillation
- Distinguished In Uniform: Self-Attention Vs. Virtual Nodes
- Distributionally Robust Optimization with Bias and Variance Reduction
- Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
- DittoGym: Learning to Control Soft Shape-Shifting Robots
- Diverse Projection Ensembles for Distributional Reinforcement Learning
- Divide and not forget: Ensemble of selectively trained experts in Continual Learning
- Diving Segmentation Model into Pixels
- DMBP: Diffusion model-based predictor for robust offline reinforcement learning against state observation perturbations
- DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model
- DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genomes
- DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text
- Does CLIP’s generalization performance mainly stem from high train-test similarity?
- Does Progress On Object Recognition Benchmarks Improve Generalization on Crowdsourced, Global Data?
- Does Writing with Language Models Reduce Content Diversity?
- Do Generated Data Always Help Contrastive Learning?
- DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
- Domain-Agnostic Molecular Generation with Chemical Feedback
- Domain constraints improve risk prediction when outcome data is missing
- Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts
- Domain Randomization via Entropy Maximization
- Don't Judge by the Look: Towards Motion Coherent Video Representation
- Don't Play Favorites: Minority Guidance for Diffusion Models
- Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
- DORSal: Diffusion for Object-centric Representations of Scenes $\textit{et al.}$
- DOS: Diverse Outlier Sampling for Out-of-Distribution Detection
- Doubly Robust Instance-Reweighted Adversarial Training
- Doubly Robust Proximal Causal Learning for Continuous Treatments
- DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
- DP-SGD Without Clipping: The Lipschitz Neural Network Way
- DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning
- DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models
- DreamClean: Restoring Clean Image Using Deep Diffusion Prior
- DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
- DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption
- DreamFlow: High-quality text-to-3D generation by Approximating Probability Flow
- DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
- DreamLLM: Synergistic Multimodal Comprehension and Creation
- DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing
- DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation
- DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
- Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation
- Dropout Enhanced Bilevel Training
- DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks
- DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness
- DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines
- Dual Associated Encoder for Face Restoration
- Dual-Encoders for Extreme Multi-label Classification
- Dual RL: Unification and New Methods for Reinforcement and Imitation Learning
- Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment
- DV-3DLane: End-to-end Multi-modal 3D Lane Detection with Dual-view Representation
- Dynamic Discounted Counterfactual Regret Minimization
- Dynamic Layer Tying for Parameter-Efficient Transformers
- Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces
- Dynamic Neural Response Tuning
- Dynamics-Informed Protein Design with Structure Conditioning
- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
- Dynamic Sparse Training with Structured Sparsity
- DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization
- DyST: Towards Dynamic Neural Scene Representations on Real-World Videos
- DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks
- Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
- Early Stopping Against Label Noise Without Validation Data
- EasyTPP: Towards Open Benchmarking Temporal Point Processes
- EBMDock: Neural Probabilistic Protein-Protein Docking via a Differentiable Energy Model
- ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models
- EControl: Fast Distributed Optimization with Compression and Error Control
- ED-NeRF: Efficient Text-Guided Editing of 3D Scene With Latent Space NeRF
- Effective and Efficient Federated Tree Learning on Hybrid Data
- Effective Data Augmentation With Diffusion Models
- Effective pruning of web-scale datasets based on complexity of concept clusters
- Effective Structural Encodings via Local Curvature Profiles
- Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day
- Efficient and Scalable Graph Generation through Iterative Local Expansion
- Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
- Efficient Backpropagation with Variance Controlled Adaptive Sampling
- Efficient Continual Finite-Sum Minimization
- Efficient ConvBN Blocks for Transfer Learning and Beyond
- EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models
- Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
- Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning
- Efficient Heterogeneous Meta-Learning via Channel Shuffling Modulation
- Efficient Integrators for Diffusion Generative Models
- Efficient Inverse Multiagent Learning
- Efficient local linearity regularization to overcome catastrophic overfitting
- Efficiently Computing Similarities to Private Datasets
- Efficient Modulation for Vision Networks
- Efficient Multi-agent Reinforcement Learning by Planning
- Efficient Planning with Latent Diffusion
- Efficient Score Matching with Deep Equilibrium Layers
- Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models
- Efficient Streaming Language Models with Attention Sinks
- Efficient Subgraph GNNs by Learning Effective Selection Policies
- Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
- Elastic Feature Consolidation For Cold Start Exemplar-Free Incremental Learning
- Elucidating the design space of classifier-guided diffusion generation
- Elucidating the Exposure Bias in Diffusion Models
- Embarrassingly Simple Dataset Distillation
- Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
- EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models
- Emergent Communication with Conversational Repair
- Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks
- EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
- EMO: EARTH MOVER DISTANCE OPTIMIZATION FOR AUTO-REGRESSIVE LANGUAGE MODELING
- Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation
- Empirical Likelihood for Fair Classification
- Emu: Generative Pretraining in Multimodality
- Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products
- Enabling Lanuguage Models to Implicitly Learn Self-Improvement
- Encoding Unitig-level Assembly Graphs with Heterophilous Constraints for Metagenomic Contigs Binning
- End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon
- Energy-based Automated Model Evaluation
- Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations
- Energy-conserving equivariant GNN for elasticity of lattice architected metamaterials
- Energy-guided Entropic Neural Optimal Transport
- Enhanced Face Recognition using Intra-class Incoherence Constraint
- Enhancing Contrastive Learning for Ordinal Regression via Ordinal Content Preserved Data Augmentation
- Enhancing Group Fairness in Online Settings Using Oblique Decision Forests
- Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping
- Enhancing Human-AI Collaboration Through Logic-Guided Reasoning
- Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain
- Enhancing Instance-Level Image Classification with Set-Level Labels
- Enhancing Neural Subset Selection: Integrating Background Information into Set Representations
- Enhancing Neural Training via a Correlated Dynamics Model
- Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting
- Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting
- Enhancing Tail Performance in Extreme Classifiers by Label Variance Reduction
- Enhancing Transferable Adversarial Attacks on Vision Transformers through Gradient Normalization Scaling and High-Frequency Adaptation
- Enhancing Transfer Learning with Flexible Nonparametric Posterior Sampling
- Ensemble Distillation for Unsupervised Constituency Parsing
- Entity-Centric Reinforcement Learning for Object Manipulation from Pixels
- Entropy Coding of Unordered Data Structures
- Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
- Entropy-MCMC: Sampling from Flat Basins with Ease
- Epitopological learning and Cannistraci-Hebb network shape intelligence brain-inspired theory for ultra-sparse advantage in deep learning
- EQA-MX: Embodied Question Answering using Multimodal Expression
- EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
- Equivariant Matrix Function Neural Networks
- Equivariant Scalar Fields for Molecular Docking with Fast Fourier Transforms
- Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants
- Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models
- Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
- Estimating Conditional Mutual Information for Dynamic Feature Selection
- Estimating Shape Distances on Neural Representations with Limited Samples
- Eureka: Human-Level Reward Design via Coding Large Language Models
- Evaluating Language Model Agency Through Negotiations
- Evaluating Large Language Models at Evaluating Instruction Following
- Evaluating Representation Learning on the Protein Structure Universe
- Evaluating the Zero-shot Robustness of Instruction-tuned Language Models
- EventRPG: Event Data Augmentation with Relevance Propagation Guidance
- Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing
- ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis
- EX-Graph: A Pioneering Dataset Bridging Ethereum and X
- Expected flow networks in stochastic environments and two-player zero-sum games
- Experimental Design for Multi-Channel Imaging via Task-Driven Feature Selection
- Explaining Kernel Clustering via Decision Trees
- Explaining Time Series via Contrastive and Locally Sparse Perturbations
- Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
- Exploring Diffusion Time-steps for Unsupervised Representation Learning
- Exploring Effective Stimulus Encoding via Vision System Modeling for Visual Prostheses
- Exploring Target Representations for Masked Autoencoders
- Exploring the cloud of feature interaction scores in a Rashomon set
- Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow
- Exploring the Promise and Limits of Real-Time Recurrent Learning
- Exploring Weight Balancing on Long-Tailed Recognition Problem
- Exposing Text-Image Inconsistency Using Diffusion Models
- Expressive Losses for Verified Robustness via Convex Combinations
- Expressivity of ReLU-Networks under Convex Relaxations
- Extending Power of Nature from Binary to Real-Valued Graph Learning in Real World
- Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning?
- Fair and Efficient Contribution Valuation for Vertical Federated Learning
- Fair Classifiers that Abstain without Harm
- FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
- fairret: a Framework for Differentiable Fairness Regularization Terms
- FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling
- FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis
- Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models
- Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals
- Faithful Rule Extraction for Differentiable Rule Learning Models
- Faithful Vision-Language Interpretation via Concept Bottleneck Models
- Fake It Till Make It: Federated Learning with Consensus-Oriented Generation
- Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model
- Fantastic Generalization Measures are Nowhere to be Found
- Fast and unified path gradient estimators for normalizing flows
- Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature
- Fast-ELECTRA for Efficient Pre-training
- Fast Ensembling with Diffusion Schrödinger Bridge
- Fast Equilibrium of SGD in Generic Situations
- Faster Approximation of Probabilistic and Distributional Values via Least Squares
- Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solvers
- FasterViT: Fast Vision Transformers with Hierarchical Attention
- Fast, Expressive $\mathrm{SE}(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space
- Fast Hyperboloid Decision Tree Algorithms
- Fast Imitation via Behavior Foundation Models
- Fast Updating Truncated SVD for Representation Learning with Sparse Matrices
- Fast Value Tracking for Deep Reinforcement Learning
- FeatUp: A Model-Agnostic Framework for Features at Any Resolution
- Feature-aligned N-BEATS with Sinkhorn divergence
- Feature Collapse
- Feature emergence via margin maximization: case studies in algebraic tasks
- FedCDA: Federated Learning with Cross-rounds Divergence-aware Aggregation
- FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware Scheduler
- FedDA: Faster Adaptive Gradient Methods for Federated Constrained Optimization
- Federated Causal Discovery from Heterogeneous Data
- Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning
- Federated Q-Learning: Linear Regret Speedup with Low Communication Cost
- Federated Recommendation with Additive Personalization
- Federated Text-driven Prompt Generation for Vision-Language Models
- Federated Wasserstein Distance
- FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent
- FedImpro: Measuring and Improving Client Update in Federated Learning
- FedInverse: Evaluating Privacy Leakage in Federated Learning
- FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data
- FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity
- FedTrans: Client-Transparent Utility Estimation for Robust Federated Learning
- FedWon: Triumphing Multi-domain Federated Learning Without Normalization
- Ferret: Refer and Ground Anything Anywhere at Any Granularity
- Few-Shot Detection of Machine-Generated Text using Style Representations
- Few-shot Hybrid Domain Adaptation of Image Generator
- FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods
- f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization
- Fiber Monte Carlo
- Fine-Tuned Language Models Generate Stable Inorganic Materials as Text
- Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
- Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
- Fine-Tuning Language Models for Factuality
- Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
- Finetuning Text-to-Image Diffusion Models for Fairness
- Finite Scalar Quantization: VQ-VAE Made Simple
- Finite-State Autoregressive Entropy Coding for Efficient Learned Lossless Compression
- Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning
- First-order ANIL provably learns representations despite overparametrisation
- First Workshop on Representational Alignment (Re-Align)
- FITS: Modeling Time Series with $10k$ Parameters
- Fixed-Budget Differentially Private Best Arm Identification
- Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation
- Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization
- FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
- FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
- FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
- Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem
- FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing
- FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning
- Flow Matching on General Geometries
- Flow to Better: Offline Preference-based Reinforcement Learning via Preferred Trajectory Generation
- Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification
- Forward $\chi^2$ Divergence Based Variational Importance Sampling
- Forward Learning of Graph Neural Networks
- Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization
- FOSI: Hybrid First and Second Order Optimization
- Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained Models
- Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D
- FreeDyG: Frequency Enhanced Continuous-Time Dynamic Graph Model for Link Prediction
- Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning
- FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling
- FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
- Frequency-Aware Transformer for Learned Image Compression
- From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication
- From Graphs to Hypergraphs: Hypergraph Projection and its Reconstruction
- From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module
- From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction
- From Posterior Sampling to Meaningful Diversity in Image Restoration
- From Sparse to Soft Mixtures of Experts
- From Zero to Turbulence: Generative Modeling for 3D Flow Simulation
- FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action Recognition
- Frozen Transformers in Language Models Are Effective Visual Encoder Layers
- Fully Hyperbolic Convolutional Neural Networks for Computer Vision
- Functional Bayesian Tucker Decomposition for Continuous-indexed Tensor Data
- Functional Interpolation for Relative Positions improves Long Context Transformers
- Function-space Parameterization of Neural Networks for Sequential Learning
- Function Vectors in Large Language Models
- Fusing Models with Complementary Expertise
- Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection
- Future Language Modeling from Temporal Document History
- G$^2$N$^2$ : Weisfeiler and Lehman go grammatical
- GAFormer: Enhancing Timeseries Transformers Through Group-Aware Embeddings
- GAIA: a benchmark for General AI Assistants
- GAIA: Zero-shot Talking Avatar Generation
- Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis
- Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
- GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models
- GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion
- General Graph Random Features
- Generalizability of Adversarial Robustness Under Distribution Shifts
- Generalization error of spectral algorithms
- Generalization in diffusion models arises from geometry-adaptive harmonic representations
- Generalization of Scaled Deep ResNets in the Mean-Field Regime
- Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions
- Generalized Policy Iteration using Tensor Approximation for Hybrid Control
- Generalized Schrödinger Bridge Matching
- General Stability Analysis for Zeroth-Order Optimization Algorithms
- Generating Images with 3D Annotations Using Diffusion Models
- Generating Pragmatic Examples to Train Neural Program Synthesizers
- Generative Adversarial Equilibrium Solvers
- Generative and Experimental Perspectives for Biomolecular Design
- Generative Human Motion Stylization in Latent Space
- Generative Judge for Evaluating Alignment
- Generative Learning for Financial Time Series with Irregular and Scale-Invariant Patterns
- Generative Learning for Solving Non-Convex Problem with Multi-Valued Input-Solution Mapping
- Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs
- Generative Modeling with Phase Stochastic Bridge
- Generative Models for Decision Making
- Generative Pre-training for Speech with Flow Matching
- Generative Sliced MMD Flows with Riesz Kernels
- Gene Regulatory Network Inference in the Presence of Dropouts: a Causal View
- GENOME: Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing Modules
- GenSim: Generating Robotic Simulation Tasks via Large Language Models
- Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions
- GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation
- Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks
- GeoLLM: Extracting Geospatial Knowledge from Large Language Models
- Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks
- Geometry-Aware Projective Mapping for Unbounded Neural Radiance Fields
- Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs
- Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models
- Ghost on the Shell: An Expressive Representation of General 3D Shapes
- GIM: Learning Generalizable Image Matcher From Internet Videos
- GIO: Gradient Information Optimization for Training Dataset Selection
- Global AI Cultures
- Global Optimality for Non-linear Constrained Restoration Problems via Invexity
- GlucoBench: Curated List of Continuous Glucose Monitoring Datasets with Prediction Benchmarks
- GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors
- GNNBoundary: Towards Explaining Graph Neural Networks through the Lens of Decision Boundaries
- GNNCert: Deterministic Certification of Graph Neural Networks against Adversarial Perturbations
- GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking
- GOAt: Explaining Graph Neural Networks via Graph Output Attribution
- Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory
- GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction
- Goodhart's Law in Reinforcement Learning
- GPAvatar: Generalizable and Precise Head Avatar from Image(s)
- GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
- Gradual Domain Adaptation via Gradient Flow
- Gradual Optimization Learning for Conformational Energy Minimization
- GRANDE: Gradient-Based Decision Tree Ensembles for Tabular Data
- Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations
- GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs
- GraphChef: Decision-Tree Recipes to Explain Graph Neural Networks
- GRAPH-CONSTRAINED DIFFUSION FOR END-TO-END PATH PLANNING
- Graph Generation with $K^2$-trees
- Graphical Multioutput Gaussian Process with Attention
- Graph Lottery Ticket Automated
- Graph Metanetworks for Processing Diverse Neural Architectures
- Graph Neural Networks for Learning Equivariant Representations of Neural Networks
- Graph Parsing Networks
- GraphPulse: Topological representations for temporal graph property prediction
- Graph Transformers on EHRs: Better Representation Improves Downstream Performance
- Grokking as a First Order Phase Transition in Two Layer Networks
- Grokking as the transition from lazy to rich training dynamics
- Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding
- GROOT: Learning to Follow Instructions by Watching Gameplay Videos
- Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models
- Grounded Object-Centric Learning
- Grounding Language Plans in Demonstrations Through Counterfactual Perturbations
- Grounding Multimodal Large Language Models to the World
- Group Preference Optimization: Few-Shot Alignment of Large Language Models
- GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers
- GTMGC: Using Graph Transformer to Predict Molecule’s Ground-State Conformation
- Guaranteed Approximation Bounds for Mixed-Precision Neural Operators
- Guess & Sketch: Language Model Guided Transpilation
- Guiding Instruction-based Image Editing via Multimodal Large Language Models
- Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram
- H2O-SDF: Two-phase Learning for 3D Indoor Reconstruction using Object Surface Fields
- Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots
- Hard-Constrained Deep Learning for Climate Downscaling
- Harnessing Density Ratios for Online Reinforcement Learning
- Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning
- Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains
- HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments
- Headless Language Models: Learning without Predicting with Contrastive Weight Tying
- Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks
- Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence Rate
- H-GAP: Humanoid Control with a Generalist Planner
- Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
- Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
- HIFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance
- HiGen: Hierarchical Graph Generative Networks
- High-dimensional SGD aligns with emerging outlier eigenspaces
- High Fidelity Neural Audio Compression
- Hindsight PRIORs for Reward Learning from Human Preferences
- Holistic Evaluation of Language Models
- HoloNets: Spectral Convolutions do extend to Directed Graphs
- Horizon-Free Regret for Linear Markov Decision Processes
- Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs
- How connectivity structure shapes rich and lazy learning in neural circuits
- How Does Unlabeled Data Provably Help Out-of-Distribution Detection?
- How do Language Models Bind Entities in Context?
- How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations
- How Far Are We From AGI
- How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion Models
- How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
- How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization
- How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data
- How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
- How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
- How to Fine-Tune Vision Models with SGD
- How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?
- Human Feedback is not Gold Standard
- Human Motion Diffusion as a Generative Prior
- Hybrid Directional Graph Neural Network for Molecules
- Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners
- Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response
- Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
- Hybrid Sharing for Multi-Label Image Classification
- HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs
- HyperAttention: Long-context Attention in Near-Linear Time
- Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty
- Hypergraph Dynamic System
- HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion
- HYPO: Hyperspherical Out-Of-Distribution Generalization
- Hypothesis Search: Inductive Reasoning with Language Models
- IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs
- ICLR 2024 Workshop on Reliable and Responsible Foundation Models
- IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
- Idempotence and Perceptual Image Compression
- Idempotent Generative Network
- Identifiable Latent Polynomial Causal Models through the Lens of Change
- Identifying Policy Gradient Subspaces
- Identifying Representations for Intervention Extrapolation
- Identifying the Risks of LM Agents with an LM-Emulated Sandbox
- iGraphMix: Input Graph Mixup Method for Node Classification
- Illusory Attacks: Information-theoretic detectability matters in adversarial attacks
- Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval
- Image Background Serves as Good Proxy for Out-of-distribution Data
- Image Clustering Conditioned on Text Criteria
- Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models
- Image Inpainting via Iteratively Decoupled Probabilistic Modeling
- Image Inpainting via Tractable Steering of Diffusion Models
- ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms
- ImagenHub: Standardizing the evaluation of conditional image generation models
- Image Translation as Diffusion Visual Programmers
- Imitation Learning from Observation with Automatic Discount Scheduling
- Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control
- Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank
- Implicit Gaussian process representation of vector fields over arbitrary latent manifolds
- Implicit Maximum a Posteriori Filtering via Adaptive Optimization
- Implicit Neural Representation Inference for Low-Dimensional Bayesian Deep Learning
- Implicit Neural Representations and the Algebra of Complex Wavelets
- Implicit regularization of deep residual networks towards neural ODEs
- ImplicitSLIM and How it Improves Embedding-based Collaborative Filtering
- Improved Active Learning via Dependent Leverage Score Sampling
- Improved algorithm and bounds for successive projection
- Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model
- Improved baselines for vision-language pre-training
- Improved Efficiency Based on Learned Saccade and Continuous Scene Reconstruction From Foveated Visual Sampling
- Improved Probabilistic Image-Text Representations
- Improved Regret Bounds for Non-Convex Online-Within-Online Meta Learning
- Improved sampling via learned diffusions
- Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data
- Improved Techniques for Training Consistency Models
- Improving Convergence and Generalization Using Parameter Symmetries
- Improving Domain Generalization with Domain Relations
- Improving equilibrium propagation without weight symmetry through Jacobian homeostasis
- Improving Generalization of Alignment with Human Preferences through Group Invariant Learning
- Improving Intrinsic Exploration by Creating Stationary Objectives
- Improving LoRA in Privacy-preserving Federated Learning
- Improving Non-Transferable Representation Learning by Harnessing Content and Style
- Improving Offline RL by Blending Heuristics
- Improving protein optimization with smoothed fitness landscapes
- Improving the Convergence of Dynamic NeRFs via Optimal Transport
- IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models
- Incentive-Aware Federated Learning with Training-Time Model Rewards
- Incentivized Truthful Communication for Federated Bandits
- In-context Autoencoder for Context Compression in a Large Language Model
- In-context Exploration-Exploitation for Reinforcement Learning
- In-Context Learning Dynamics with Random Binary Sequences
- In-Context Learning Learns Label Relationships but Is Not Conventional Learning
- In-Context Learning through the Bayesian Prism
- In-Context Pretraining: Language Modeling Beyond Document Boundaries
- Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning
- Incremental Randomized Smoothing Certification
- In defense of parameter sharing for model-compression
- Independent-Set Design of Experiments for Estimating Treatment and Spillover Effects under Network Interference
- Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
- Influencer Backdoor Attack on Semantic Segmentation
- InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning
- InfoCon: Concept Discovery with Generative and Discriminative Informativeness
- Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression
- Information Retention via Learning Supplemental Features
- Inherently Interpretable Time Series Classification via Multiple Instance Learning
- Initializing Models with Larger Ones
- Inner Classifier-Free Guidance and Its Taylor Expansion for Diffusion Models
- Input-gradient space particle inference for neural network ensembles
- Ins-DetCLIP: Aligning Detection Model to Follow Human-Language Instruction
- InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
- INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection
- InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
- #InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models
- Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model
- InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists
- InstructDET: Diversifying Referring Object Detection with Generalized Instructions
- Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions
- InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image
- InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior
- Integrating Planning and Deep Reinforcement Learning via Automatic Induction of Task Substructures
- Intelligent Switching for Reset-Free RL
- Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning
- InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
- InterpGNN: Understand and Improve Generalization Ability of Transdutive GNNs through the Lens of Interplay between Train and Test Nodes
- Interpretable Diffusion via Information Decomposition
- Interpretable Meta-Learning of Physical Systems
- Interpretable Sparse System Identification: Beyond Recent Deep Learning Techniques on Time-Series Prediction
- Interpreting CLIP's Image Representation via Text-Based Decomposition
- Interpreting Robustness Proofs of Deep Neural Networks
- Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach
- Intriguing Properties of Data Attribution on Diffusion Models
- Intriguing Properties of Generative Classifiers
- Invariance-based Learning of Latent Dynamics
- Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
- Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration
- Investigating the Benefits of Projection Head for Representation Learning
- INViTE: INterpret and Control Vision-Language Models with Text Explanations
- I-PHYRE: Interactive Physical Reasoning
- IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
- Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability
- Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
- Is Self-Repair a Silver Bullet for Code Generation?
- Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching
- Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting
- iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
- It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition
- Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
- Jointly-Learned Exit and Inference for a Dynamic Neural Network
- Jointly Training Large Autoregressive Multimodal Models
- JointNet: Extending Text-to-Image Diffusion for Dense Distribution Modeling
- JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and Attention
- Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
- Kalman Filter for Online Classification of Non-Stationary Data
- Kernelised Normalising Flows
- Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies
- Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning
- KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval
- Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models
- Knowledge Distillation Based on Transformed Teacher Matching
- Knowledge Fusion of Large Language Models
- KoLA: Carefully Benchmarking World Knowledge of Large Language Models
- Koopman-based generalization bound: New aspect for full-rank weights
- Kosmos-G: Generating Images in Context with Multimodal Large Language Models
- KW-Design: Pushing the Limit of Protein Design via Knowledge Refinement
- L2MAC: Large Language Model Automatic Computer for Extensive Code Generation
- L2P-MIP: Learning to Presolve for Mixed Integer Programming
- Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models
- LabelDP-Pro: Learning with Label Differential Privacy via Projections
- Label-Focused Inductive Bias over Latent Object Features in Visual Classification
- Label-free Node Classification on Graphs with Large Language Models (LLMs)
- Label-Noise Robust Diffusion Models
- Lagrangian Flow Networks for Conservation Laws
- LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving
- Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited
- LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
- Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks
- Language-Informed Visual Concept Learning
- Language-Interfaced Tabular Oversampling via Progressive Imputation and Self-Authentication
- Language Model Beats Diffusion - Tokenizer is key to visual generation
- Language Model Cascades: Token-Level Uncertainty And Beyond
- Language Model Decoding as Direct Metrics Optimization
- Language Model Detectors Are Easily Optimized Against
- Language Modeling Is Compression
- Language Model Inversion
- Language Model Self-improvement by Reinforcement Learning Contemplation
- Language Models Represent Space and Time
- Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI
- Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior
- Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient Reasoning
- Large Language Models are Efficient Learners of Noise-Robust Speech Recognition
- Large Language Models Are Not Robust Multiple Choice Selectors
- Large Language Models as Analogical Reasoners
- Large Language Models as Automated Aligners for benchmarking Vision-Language Models
- Large Language Models as Generalizable Policies for Embodied Tasks
- Large Language Models as Optimizers
- Large Language Models as Tool Makers
- Large Language Models Cannot Self-Correct Reasoning Yet
- Large Language Models to Enhance Bayesian Optimization
- Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages
- Large-scale Training of Foundation Models for Wearable Biosignals
- Large-Vocabulary 3D Diffusion Model with Transformer
- Latent 3D Graph Diffusion
- Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Video
- Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck
- Latent Trajectory Learning for Limited Timestamps under Distribution Shift over Time
- Layer-wise linear mode connectivity
- LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models
- LCOT: Linear Circular Optimal Transport
- LDReg: Local Dimensionality Regularized Self-Supervised Learning
- LEAD: Min-Max Optimization from a Physical Perspective
- LEAP: Liberate Sparse-View 3D Modeling from Camera Poses
- Learning 3D Particle-based Simulators from RGB-D Videos
- Learning Adaptive Multiresolution Transforms via Meta-Framelet-based Graph Convolutional Network
- Learning Conditional Invariances through Non-Commutativity
- Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior
- Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings
- Learning dynamic representations of the functional connectome in neurobiological networks
- Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihood
- Learning Energy Decompositions for Partial Inference in GFlowNets
- Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer
- Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
- Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation
- Learning From Simplicial Data Based on Random Walks and 1D Convolutions
- Learning from Sparse Offline Datasets via Conservative Density Estimation
- Learning Grounded Action Abstractions from Language
- Learning Hierarchical Image Segmentation For Recognition and By Recognition
- Learning Hierarchical Polynomials with Three-Layer Neural Networks
- Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics
- Learning Implicit Representation for Reconstructing Articulated Objects
- Learning in reverse causal strategic environments with ramifications on two sided markets
- Learning Interactive Real-World Simulators
- Learning interpretable control inputs and dynamics underlying animal locomotion
- Learning invariant representations of time-homogeneous stochastic dynamical systems
- Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG
- Learning Mean Field Games on Sparse Graphs: A Hybrid Graphex Approach
- Learning model uncertainty as variance-minimizing instance weights
- Learning Multi-Agent Communication from Graph Modeling Perspective
- Learning Multi-Agent Communication with Contrastive Learning
- Learning Multi-Faceted Prototypical User Interests
- Learning Nash Equilibria in Rank-1 Games
- Learning No-Regret Sparse Generalized Linear Models with Varying Observation(s)
- Learning Optimal Contracts: How to Exploit Small Action Spaces
- Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks
- Learning Performance-Improving Code Edits
- Learning Personalized Causally Invariant Representations for Heterogeneous Federated Clients
- Learning Planning Abstractions from Language
- Learning Polynomial Problems with $SL(2, \mathbb{R})$-Equivariance
- Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation
- Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning
- Learning semilinear neural operators: A unified recursive framework for prediction and data assimilation.
- Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling
- Learning the greatest common divisor: explaining transformer predictions
- Learning Thresholds with Latent Values and Censored Feedback
- Learning through AI’s winters and springs: unexpected truths on the road to AGI
- Learning through AI’s winters and springs: unexpected truths on the road to AGI
- Learning through AI’s winters and springs: unexpected truths on the road to AGI
- Learning through AI’s winters and springs: unexpected truths on the road to AGI
- Learning to Act from Actionless Videos through Dense Correspondences
- Learning to Act without Actions
- Learning to Compose: Improving Object Centric Learning by Injecting Compositionality
- Learning to design protein-protein interactions with enhanced generalization
- Learning to Embed Time Series Patches Independently
- Learning to Jointly Understand Visual and Tactile Signals
- Learning to Make Adherence-aware Advice
- Learning to reconstruct signals from binary measurements alone
- Learning to Reject Meets Long-tail Learning
- Learning to Reject with a Fixed Predictor: Application to Decontextualization
- Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
- Learning to Solve Bilevel Programs with Binary Tender
- Learning to solve Class-Constrained Bin Packing Problems via Encoder-Decoder Model
- Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction
- Learning with Language-Guided State Abstractions
- Learning with Mixture of Prototypes for Out-of-Distribution Detection
- Leave-one-out Distinguishability in Machine Learning
- Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models
- LEGO-Prover: Neural Theorem Proving with Growing Libraries
- LEMON: Lossless model expansion
- Lemur: Harmonizing Natural Language and Code for Language Agents
- Lemur: Integrating Large Language Models in Automated Program Verification
- Less is More: Fewer Interpretable Region via Submodular Subset Selection
- Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs
- Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation
- Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation
- Let Models Speak Ciphers: Multiagent Debate through Embeddings
- Let's do the time-warp-attend: Learning topological invariants of dynamical systems
- Let's Verify Step by Step
- Leveraging augmented-Lagrangian techniques for differentiating over infeasible quadratic programs in machine learning
- Leveraging Generative Models for Unsupervised Alignment of Neural Time Series Data
- Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design
- Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control
- Leveraging Optimization for Adaptive Attacks on Image Watermarks
- Leveraging Uncertainty Estimates To Improve Classifier Performance
- Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency
- Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments
- LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection
- LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
- Lie Group Decompositions for Equivariant Neural Networks
- Lifting Architectural Constraints of Injective Flows
- LightHGNN: Distilling Hypergraph Neural Networks into MLPs for 100x Faster Inference
- Light-MILPopt: Solving Large-scale Mixed Integer Linear Programs with Lightweight Optimizer and Small-scale Training Dataset
- Light Schrödinger Bridge
- Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps
- Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds
- LILO: Learning Interpretable Libraries by Compressing and Documenting Code
- Linear attention is (maybe) all you need (to understand Transformer optimization)
- Linearity of Relation Decoding in Transformer Language Models
- Linear Log-Normal Attention with Unbiased Concentration
- Lion Secretly Solves a Constrained Optimization: As Lyapunov Predicts
- Lipschitz Singularities in Diffusion Models
- LipSim: A Provably Robust Perceptual Similarity Metric
- Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance
- LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading
- Listen, Think, and Understand
- LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses
- LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zero-initialized Attention
- LLCP: Learning Latent Causal Processes for Reasoning-based Video Question Answer
- Llemma: An Open Language Model for Mathematics
- LLM-Assisted Code Cleaning For Training Accurate Code Generators
- LLM Augmented LLMs: Expanding Capabilities through Composition
- LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts
- LLMCarbon: Modeling the End-to-End Carbon Footprint of Large Language Models
- LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation
- LLM-grounded Video Diffusion Models
- LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors
- LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset
- LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units
- Local Composite Saddle Point Optimization
- Local Graph Clustering with Noisy Labels
- Locality-Aware Graph Rewiring in GNNs
- Locality Sensitive Sparse Encoding for Learning World Models Online
- Localizing and Editing Knowledge In Text-to-Image Generative Models
- Local Search GFlowNets
- LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language Models
- Logical Languages Accepted by Transformer Encoders with Hard Attention
- LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints
- LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
- Long-Short-Range Message-Passing: A Physics-Informed Framework to Capture Non-Local Interaction for Scalable Molecular Dynamics Simulation
- Long-tailed Diffusion Models with Oriented Calibration
- Long-Term Typhoon Trajectory Prediction: A Physics-Conditioned Approach Without Reanalysis Data
- Look, Remember and Reason: Grounded Reasoning in Videos with Language Models
- Looped Transformers are Better at Learning Learning Algorithms
- LOQA: Learning with Opponent Q-Learning Awareness
- LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents
- Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time
- lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning
- LQ-LoRA: Low-rank plus Quantized Matrix Decomposition for Efficient Language Model Finetuning
- LRM: Large Reconstruction Model for Single Image to 3D
- LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
- LUM-ViT: Learnable Under-sampling Mask Vision Transformer for Bandwidth Limited Optical Signal Acquisition
- LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
- M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering
- Machine Learning for Genomics Explorations (MLGenX)
- Machine Learning for Remote Sensing (ML4RS)
- Machine Learning in Prescient Design's Lab-in-the-Loop Antibody Design
- Machine Unlearning for Image-to-Image Generative Models
- Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
- MagicDrive: Street View Generation with Diverse 3D Geometry Control
- MaGIC: Multi-modality Guided Image Completion
- Magnitude Invariant Parametrizations Improve Hypernetwork Learning
- Magnushammer: A Transformer-Based Approach to Premise Selection
- Making LLaMA SEE and Draw with SEED Tokenizer
- Making Pre-trained Language Models Great on Tabular Prediction
- Making Retrieval-Augmented Language Models Robust to Irrelevant Context
- Making RL with Preference-based Feedback Efficient via Randomization
- MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
- MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning
- Manifold Diffusion Fields
- Manifold Preserving Guided Diffusion
- Manipulating dropout reveals an optimal balance of efficiency and robustness in biological and machine visual systems
- MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding
- MAP IT to Visualize Representations
- Mask-Based Modeling for Neural Radiance Fields
- Masked Audio Generation using a Single Non-Autoregressive Transformer
- Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners
- Masked Completion via Structured Diffusion with White-Box Transformers
- Masked Distillation Advances Self-Supervised Transformer Architecture Search
- Masked Structural Growth for 2x Faster Language Model Pre-training
- Masks, Signs, And Learning Rate Rewinding
- Massive Editing for Large Language Models via Meta Learning
- Massively Scalable Inverse Reinforcement Learning in Google Maps
- Mastering Memory Tasks with World Models
- Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks
- Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
- MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
- Mathematical Justification of Hard Negative Mining via Isometric Approximation Theorem
- MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
- Matrix Manifold Neural Networks++
- Matryoshka Diffusion Models
- Maximum Entropy Heterogeneous-Agent Reinforcement Learning
- Maximum Entropy Model Correction in Reinforcement Learning
- Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift
- Mayfly: a Neural Data Structure for Graph Stream Summarization
- MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods
- MCM: Masked Cell Modeling for Anomaly Detection in Tabular Data
- Mean Field Theory in Deep Metric Learning
- Meaning Representations from Trajectories in Autoregressive Models
- Measuring Vision-Language STEM Skills of Neural Models
- Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks
- Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games
- Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis
- Memorization Capacity of Multi-Head Attention in Transformers
- Memorization in Self-Supervised Learning Improves Downstream Generalization
- Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation
- Memory-Consistent Neural Networks for Imitation Learning
- MEND: Meta Demonstration Distillation for Efficient and Effective In-Context Learning
- Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
- MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
- MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation
- Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction
- Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer
- MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
- Meta Inverse Constrained Reinforcement Learning: Convergence Guarantee and Generalization Analysis
- Meta-Learning Priors Using Unrolled Proximal Networks
- MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
- MetaPhysiCa: Improving OOD Robustness in Physics-informed Machine Learning
- MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
- Meta-VBO: Utilizing Prior Tasks in Optimizing Risk Measures with Gaussian Processes
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction
- MgNO: Efficient Parameterization of Linear Operators via Multigrid
- MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process
- MINDE: Mutual Information Neural Diffusion Estimation
- Mind Your Augmentation: The Key to Decoupling Dense Self-Supervised Learning
- MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
- MiniLLM: Knowledge Distillation of Large Language Models
- Minimax optimality of convolutional neural networks for infinite dimensional input-output problems and separation from kernel methods
- Minimum width for universal approximation using ReLU networks on compact domain
- MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
- MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations
- Mirage: Model-agnostic Graph Distillation for Graph Classification
- Mitigating Emergent Robustness Degradation while Scaling Graph Learning
- Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning
- Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing
- Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space
- MixSATGEN: Learning Graph Mixing for SAT Instance Generation
- MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection
- Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models
- Mixture of LoRA Experts
- Mixture of Weak and Strong Experts on Graphs
- MMD Graph Kernel: Effective Metric Learning for Graphs via Maximum Mean Discrepancy
- MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
- Modeling Boundedly Rational Agents with Latent Inference Budgets
- Modeling state-dependent communication between brain regions with switching nonlinear dynamical systems
- Modelling complex vector drawings with stroke-clouds
- Model Merging by Uncertainty-Based Gradient Matching
- Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
- ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis
- Modulated Phase Diffusor: Content-Oriented Feature Synthesis for Detecting Unknown Objects
- Modulate Your Spectrum in Self-Supervised Learning
- ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers
- MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework Design
- MOFI: Learning Image Representations from Noisy Entity Annotated Images
- MogaNet: Multi-order Gated Aggregation Network
- Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models
- Momentum Benefits Non-iid Federated Learning Simply and Provably
- Monte Carlo guided Denoising Diffusion models for Bayesian linear inverse problems.
- More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
- Most discriminative stimuli for functional cell type clustering
- Motif: Intrinsic Motivation from Artificial Intelligence Feedback
- Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators
- MOTOR: A Time-to-Event Foundation Model For Structured Medical Records
- MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Field
- MT-Ranker: Reference-free machine translation evaluation by inter-system ranking
- MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction Following
- Multi-granularity Correspondence Learning from Long-term Noisy Videos
- Multilinear Operator Networks
- Multilingual Jailbreak Challenges in Large Language Models
- Multimarginal Generative Modeling with Stochastic Interpolants
- Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral Data
- Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications
- Multimodal Molecular Pretraining via Modality Blending
- Multimodal Patient Representation Learning with Missing Modalities and Labels
- Multimodal Web Navigation with Instruction-Finetuned Foundation Models
- Multi-Resolution Diffusion Models for Time Series Forecasting
- Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction
- Multiscale Positive-Unlabeled Detection of AI-Generated Texts
- Multi-Scale Representations by Varying Window Attention for Semantic Segmentation
- Multisize Dataset Condensation
- Multi-Source Diffusion Models for Simultaneous Music Generation and Separation
- Multi-task Learning with 3D-Aware Regularization
- Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts
- Multi-View Causal Representation Learning with Partial Observability
- Multi-View Representation is What You Need for Point-Cloud Pre-Training
- MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images
- MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
- MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data
- MVDream: Multi-view Diffusion for 3D Generation
- MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo
- NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
- Navigating and Addressing Data Problems for Foundation Models (DPFM)
- Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on HuggingFace
- Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation
- Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation
- Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization
- Near-Optimal Quantum Algorithm for Minimizing the Maximal Loss
- Near-Optimal Solutions of Constrained Learning Problems
- NECO: NEural Collapse Based Out-of-distribution detection
- NEFTune: Noisy Embeddings Improve Instruction Finetuning
- Negative Label Guided OOD Detection with Pretrained Vision-Language Models
- Negatively Correlated Ensemble Reinforcement Learning for Online Diverse Game Level Generation
- Nemesis: Normalizing the Soft-prompt Vectors of Vision-Language Models
- NeRM: Learning Neural Representations for High-Framerate Human Motion Synthesis
- NetInfoF Framework: Measuring and Exploiting Network Usable Information
- Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings
- Neur2RO: Neural Two-Stage Robust Optimization
- Neural Active Learning Beyond Bandits
- Neural Architecture Retrieval
- Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel
- Neural Auto-designer for Enhanced Quantum Kernels
- Neural Common Neighbor with Completion for Link Prediction
- Neural Contractive Dynamical Systems
- Neural Field Classifiers via Target Encoding and Classification Loss
- Neural Fine-Tuning Search for Few-Shot Learning
- Neural Fourier Transform: A General Approach to Equivariant Representation Learning
- Neural Language of Thought Models
- Neural Monge Map estimation and its applications
- Neural Neighborhood Search for Multi-agent Path Finding
- Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization
- Neural Optimal Transport with General Cost Functionals
- Neural Ordinary Differential Equations for Modeling Epidemic Spreading
- Neural Polynomial Gabor Fields for Macro Motion Analysis
- Neural Processing of Tri-Plane Hybrid Neural Fields
- Neural Rate Control for Learned Video Compression
- Neural SDF Flow for 3D Reconstruction of Dynamic Scenes
- Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries
- Neural Spectral Methods: Self-supervised learning in the spectral domain
- Neural structure learning with stochastic differential equations
- Neural-Symbolic Recursive Machine for Systematic Generalization
- NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
- Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data
- Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning
- Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization
- Neuron-Enhanced AutoEncoder Matrix Completion and Collaborative Filtering: Theory and Practice
- Neurosymbolic Grounding for Compositional World Models
- NeurRev: Train Better Sparse Neural Network Practically via Neuron Revitalization
- Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors
- Nevis'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research
- New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions
- NfgTransformer: Equivariant Representation Learning for Normal-form Games
- Node2ket: Efficient High-Dimensional Network Embedding in Quantum Hilbert Space
- NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear Interpolation
- Noise-free Score Distillation
- Noise Map Guidance: Inversion with Spatial Context for Real Image Editing
- Noisy Interpolation Learning with Shallow Univariate ReLU Networks
- NOLA: Compressing LoRA using Linear Combination of Random Basis
- Non-Exchangeable Conformal Risk Control
- Non-negative Contrastive Learning
- Nougat: Neural Optical Understanding for Academic Documents
- Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations
- Numerical Accounting in the Shuffle Model of Differential Privacy
- NuwaDynamics: Discovering and Updating in Causal Spatio-Temporal Modeling
- Object-Aware Inversion and Reassembly for Image Editing
- Object centric architectures enable efficient causal representation learning
- Object-Centric Learning with Slot Mixture Module
- Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE
- OctoPack: Instruction Tuning Code Large Language Models
- ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inference
- ODEFormer: Symbolic Regression of Dynamical Systems with Transformers
- ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update
- Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees
- Offline RL with Observation Histories: Analyzing and Improving Sample Complexity
- Off-Policy Primal-Dual Safe Reinforcement Learning
- OmniControl: Control Any Joint at Any Time for Human Motion Generation
- OMNI: Open-endedness via Models of human Notions of Interestingness
- OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
- On Accelerating Diffusion-Based Sampling Processes via Improved Integration Approximation
- On Adversarial Training without Perturbing all Examples
- On Bias-Variance Alignment in Deep Models
- On Characterizing the Trade-off in Invariant Representation Learning
- On Differentially Private Federated Linear Contextual Bandits
- On Diffusion Modeling for Anomaly Detection
- On Double Descent in Reinforcement Learning with LSTD and Random Features
- One For All: Towards Training One Graph Model For All Classification Tasks
- One Forward is Enough for Neural Network Training via Likelihood Ratio Method
- One-hot Generalized Linear Model for Switching Brain State Discovery
- On Error Propagation of Diffusion Models
- One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models
- One-shot Empirical Privacy Estimation for Federated Learning
- One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention
- On gauge freedom, conservativity and intrinsic dimensionality estimation in diffusion models
- On Harmonizing Implicit Subpopulations
- Online Continual Learning for Interactive Instruction Following Agents
- Online GNN Evaluation Under Test-time Graph Distribution Shifts
- Online Information Acquisition: Hiring Multiple Agents
- Online Stabilization of Spiking Neural Networks
- Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling
- On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- On Representation Complexity of Model-based and Model-free Reinforcement Learning
- On Stationary Point Convergence of PPO-Clip
- On the Analysis of GAN-based Image-to-Image Translation with Gaussian Noise Injection
- On the Effect of Batch Size in Byzantine-Robust Distributed Learning
- On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning
- On the Fairness ROAD: Robust Optimization for Adversarial Debiasing
- On the Foundations of Shortcut Learning
- On the Generalization and Approximation Capacities of Neural Controlled Differential Equations
- On the generalization capacity of neural networks during generic multimodal reasoning
- On the Hardness of Constrained Cooperative Multi-Agent Reinforcement Learning
- On the hardness of learning under symmetries
- On the Hardness of Online Nonconvex Optimization with Single Oracle Feedback
- On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMs
- On the Joint Interaction of Models, Data, and Features
- On the Learnability of Watermarks for Language Models
- On the Limitations of Temperature Scaling for Distributions with Overlaps
- On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods
- On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
- On the Parameterization of Second-Order Optimization Effective towards the Infinite Width
- On the Posterior Distribution in Denoising: Application to Uncertainty Quantification
- On the Power of the Weisfeiler-Leman Test for Graph Motif Parameters
- On the Provable Advantage of Unsupervised Pretraining
- On the Reliability of Watermarks for Large Language Models
- On the Role of Discrete Tokenization in Visual Representation Learning
- On the Role of General Function Approximation in Offline Reinforcement Learning
- On the Sample Complexity of Lipschitz Constant Estimation
- On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks
- On the Stability of Expressive Positional Encodings for Graphs
- On the Stability of Iterative Retraining of Generative Models on their own Data
- On the Variance of Neural Network Training with respect to Test Sets and Distributions
- On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks
- On Trajectory Augmentations for Off-Policy Evaluation
- OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
- Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy
- OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views
- OpenTab: Advancing Large Language Models as Open-domain Table Reasoners
- Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning
- OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text
- Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime
- OPTIMAL ROBUST MEMORIZATION WITH RELU NEURAL NETWORKS
- Optimal Sample Complexity for Average Reward Markov Decision Processes
- Optimal Sample Complexity of Contrastive Learning
- Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms
- Optimal transport based adversarial patch to leverage large scale attack transferability
- Optimistic Bayesian Optimization with Unknown Constraints
- Oracle Efficient Algorithms for Groupwise Regret
- Orbit-Equivariant Graph Neural Networks
- Order-Preserving GFlowNets
- Outlier-Robust Subsampling Techniques for Persistent Homology
- Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization
- Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness
- Out-of-Distribution Detection with Negative Prompts
- Out-Of-Domain Unlabeled Data Improves Generalization
- Out-of-Variable Generalisation for Discriminative Models
- Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization
- Overthinking the Truth: Understanding how Language Models Process False Demonstrations
- OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
- OWL: A Large Language Model for IT Operations
- P$^2$OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering
- P2Seg: Pointly-supervised Segmentation via Mutual Distillation
- PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images
- PAC Prediction Sets Under Label Shift
- PAE: Reinforcement Learning from External Knowledge for Efficient Exploration
- PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
- PanoDiffusion: 360-degree Panorama Outpainting via Diffusion
- Parallelizing non-linear sequential models over the sequence length
- Parameter-Efficient Multi-Task Model Fusion with Partial Linearization
- Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
- Parametric Augmentation for Time Series Contrastive Learning
- Pareto Deep Long-Tailed Recognition: A Conflict-Averse Solution
- PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback
- Parsing neural dynamics with infinite recurrent switching linear dynamical systems
- Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models
- Partitioning Message Passing for Graph Fraud Detection
- Patched Denoising Diffusion Models For High-Resolution Image Synthesis
- Patches Are All You Need?
- Path Choice Matters for Clear Attributions in Path Methods
- Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting
- Pathologies of Predictive Diversity in Deep Ensembles
- PBADet: A One-Stage Anchor-Free Approach for Part-Body Association
- PB-LLM: Partially Binarized Large Language Models
- Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models
- PeFLL: Personalized Federated Learning by Learning to Learn
- PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts
- Perceptual Group Tokenizer: Building Perception with Iterative Grouping
- Perceptual Scales Predicted by Fisher Information Metrics
- Performance Gaps in Multi-view Clustering under the Nested Matrix-Tensor Model
- Periodicity Decoupling Framework for Long-term Series Forecasting
- Personalize Segment Anything Model with One Shot
- Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning
- PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction
- Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
- PhyloGFN: Phylogenetic inference with generative flow networks
- Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings
- Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning
- PILOT: An $\mathcal{O}(1/K)$-Convergent Approach for Policy Evaluation with Nonlinear Function Approximation
- PINNACLE: PINN Adaptive ColLocation and Experimental points selection
- PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural Networks
- PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
- Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
- PlaSma: Procedural Knowledge Models for Language-based Planning and Re-Planning
- Plug-and-Play: An Efficient Post-training Pruning Method for Large Language Models
- Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents
- Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
- Plugin estimators for selective classification with out-of-distribution detection
- PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
- Point2SSM: Learning Morphological Variations of Anatomies from Point Clouds
- Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
- Policy Rehearsing: Training Generalizable Policies for Reinforcement Learning
- PolyGCL: GRAPH CONTRASTIVE LEARNING via Learnable Spectral Polynomial Filters
- Polynomial Width is Sufficient for Set Representation with High-dimensional Features
- Polynormer: Polynomial-Expressive Graph Transformer in Linear Time
- Poly-View Contrastive Learning
- PolyVoice: Language Models for Speech to Speech Translation
- Pooling Image Datasets with Multiple Covariate Shift and Imbalance
- PORF: POSE RESIDUAL FIELD FOR ACCURATE NEURAL SURFACE RECONSTRUCTION
- PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
- Pose Modulated Avatars from Video
- Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
- Post-hoc bias scoring is optimal for fair classification
- Predicting Emergent Abilities with Infinite Resolution Evaluation
- Prediction Error-based Classification for Class-Incremental Learning
- Prediction without Preclusion: Recourse Verification with Reachable Sets
- Predictive auxiliary objectives in deep RL mimic learning in the brain
- Predictive, scalable and interpretable knowledge tracing on structured domains
- PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks
- Pre-Training and Fine-Tuning Generative Flow Networks
- Pre-Training Goal-based Models for Sample-Efficient Reinforcement Learning
- Pre-training LiDAR-based 3D Object Detectors through Colorization
- Pre-training Sequence, Structure, and Surface Features for Comprehensive Protein Representation Learning
- Pre-training with Random Orthogonal Projection Image Modeling
- Pre-training with Synthetic Data Helps Offline Reinforcement Learning
- PRIME: Prioritizing Interpretability in Failure Mode Extraction
- Principled Architecture-aware Scaling of Hyperparameters
- Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting
- Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning
- Privacy Amplification for Matrix Mechanisms
- Privacy-Preserving In-Context Learning for Large Language Models
- Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
- Privacy Regulation and Protection in Machine Learning
- Privately Aligning Language Models with Reinforcement Learning
- Private Zeroth-Order Nonsmooth Nonconvex Optimization
- Privileged Sensing Scaffolds Reinforcement Learning
- Probabilistic Adaptation of Black-Box Text-to-Video Models
- Probabilistically Rewired Message-Passing Neural Networks
- Probabilistic Self-supervised Representation Learning via Scoring Rules Minimization
- Procedural Fairness Through Decoupling Objectionable Data Generating Components
- PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation
- Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts
- Progressive Fourier Neural Representation for Sequential Video Compilation
- Project and Probe: Sample-Efficient Adaptation by Interpolating Orthogonal Features
- Prometheus: Inducing Fine-Grained Evaluation Capability in Language Models
- PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization
- Prompt Gradient Projection for Continual Learning
- Prompt Learning with Quaternion Networks
- Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models
- PromptTTS 2: Describing and Generating Voices with Text Prompt
- Proper Laplacian Representation Learning
- Protein Discovery with Discrete Walk-Jump Sampling
- Protein-ligand binding representation learning from fine-grained interactions
- Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion Models
- Protein Multimer Structure Prediction via Prompt Learning
- Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction
- Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
- Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes
- Provable Compositional Generalization for Object-Centric Learning
- Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning
- Provable Offline Preference-Based Reinforcement Learning
- Provable Reward-Agnostic Preference-Based Reinforcement Learning
- Provable Robust Watermarking for AI-Generated Text
- Provably Efficient CVaR RL in Low-rank MDPs
- Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback
- Provably Efficient UCB-type Algorithms For Learning Predictive State Representations
- Provably Robust Conformal Prediction with Improved Efficiency
- Proving Test Set Contamination in Black-Box Language Models
- Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning
- Pseudo-Generalized Dynamic View Synthesis from a Video
- PTaRL: Prototype-based Tabular Representation Learning via Space Calibration
- PubDef: Defending Against Transfer Attacks From Public Models
- Pushing Boundaries: Mixup's Influence on Neural Collapse
- Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning
- QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
- Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision
- QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
- Quadratic models for understanding catapult dynamics of neural networks
- Quality-Diversity through AI Feedback
- Quantifying and Enhancing Multi-modal Robustness with Modality Preference
- Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
- Quantifying Network Similarity using Graph Cumulants
- Quantifying the Plausibility of Context Reliance in Neural Machine Translation
- Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification
- Quasi-Monte Carlo for 3D Sliced Wasserstein
- Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL
- Querying Easily Flip-flopped Samples for Deep Active Learning
- Query-Policy Misalignment in Preference-Based Reinforcement Learning
- Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How
- RA-DIT: Retrieval-Augmented Dual Instruction Tuning
- Raidar: geneRative AI Detection viA Rewriting
- RAIN: Your Language Models Can Align Themselves without Finetuning
- Random Feature Amplification: Feature Learning and Generalization in Neural Networks
- Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks
- RAPPER: Reinforced Rationale-Prompted Paradigm for Natural Language Explanation in Visual Question Answering
- RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
- Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection
- R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation
- RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design
- Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
- Real-Fake: Effective Training Data Synthesis Through Distribution Matching
- Realistic Evaluation of Semi-supervised Learning Algorithms in Open Environments
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting
- Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
- Reasoning with Latent Diffusion in Offline Reinforcement Learning
- REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning
- Reclaiming the Source of Programmatic Policies: Programmatic versus Latent Spaces
- RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations
- RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation
- Reconciling Spatial and Temporal Abstractions for Goal Representation
- Recursive Generalization Transformer for Image Super-Resolution
- R-EDL: Relaxing Nonessential Settings of Evidential Deep Learning
- REFACTOR: Learning to Extract Theorems from Proofs
- ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion
- Reinforcement Symbolic Regression Machine
- Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization
- Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
- ReLoRA: High-Rank Training Through Low-Rank Updates
- ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
- ReMasker: Imputing Tabular Data with Masked Autoencoding
- Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment
- Removing Biases from Molecular Representations via Information Maximization
- Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning
- Repelling Random Walks
- Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
- Replay across Experiments: A Natural Extension of Off-Policy RL
- RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems
- Representation Deficiency in Masked Language Modeling
- ResFields: Residual Neural Fields for Spatiotemporal Signals
- ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation
- Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition
- ReTaSA: A Nonparametric Functional Estimation Approach for Addressing Continuous Target Shift
- Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
- Rethinking and Extending the Probabilistic Inference Capacity of GNNs
- Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
- Rethinking Branching on Exact Combinatorial Optimization Solver: The First Deep Symbolic Discovery Framework
- Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators
- Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models
- Rethinking CNN’s Generalization to Backdoor Attack from Frequency Domain
- Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors
- Rethinking Information-theoretic Generalization: Loss Entropy Induced PAC Bounds
- Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
- Rethinking Model Ensemble in Transfer-based Adversarial Attacks
- Rethinking the Benefits of Steerable Features in 3D Equivariant Graph Neural Networks
- Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability
- Rethinking the symmetry-preserving circuits for constrained variational quantum algorithms
- Rethinking the Uniformity Metric in Self-Supervised Learning
- Retrieval-based Disentangled Representation Learning with Natural Language Supervision
- Retrieval-Enhanced Contrastive Vision-Text Models
- Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization
- Retrieval is Accurate Generation
- Retrieval meets Long Context Large Language Models
- RetroBridge: Modeling Retrosynthesis with Markov Bridges
- Retro-fallback: retrosynthetic planning in an uncertain world
- Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
- RETSim: Resilient and Efficient Text Similarity
- REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes
- Reverse Diffusion Monte Carlo
- Reverse Forward Curriculum Learning for Extreme Sample and Demo Efficiency
- Revisit and Outstrip Entity Alignment: A Perspective of Generative Models
- Revisiting Data Augmentation in Deep Reinforcement Learning
- Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation
- Revisiting Link Prediction: a data perspective
- Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages
- Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods
- Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning
- Reward Design for Justifiable Sequential Decision-Making
- Reward-Free Curricula for Training Robust World Models
- Reward Model Ensembles Help Mitigate Overoptimization
- Rigid Protein-Protein Docking via Equivariant Elliptic-Paraboloid Interface Prediction
- Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?
- RingAttention with Blockwise Transformers for Near-Infinite Context
- Risk Bounds of Accelerated SGD for Overparameterized Linear Regression
- RLCD: Reinforcement Learning from Contrastive Distillation for LM Alignment
- RLIF: Interactive Imitation Learning as Reinforcement Learning
- R-MAE: Regions Meet Masked Autoencoders
- Robot Fleet Learning via Policy Merging
- Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula
- Robust agents learn causal world models
- Robust Angular Synchronization via Directed Graph Neural Networks
- Robust Classification via Regression for Learning with Noisy Labels
- Robustifying and Boosting Training-Free Neural Architecture Search
- Robustifying State-space Models for Long Sequences via Approximate Diagonalization
- Robust Model-Based Optimization for Challenging Fitness Landscapes
- Robust Model Based Reinforcement Learning Using $\mathcal{L}_1$ Adaptive Control
- Robust NAS under adversarial training: benchmark, theory, and beyond
- Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
- Robust Similarity Learning with Difference Alignment Regularization
- Robust Training of Federated Models with Extremely Label Deficiency
- RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomalies
- Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs
- Rotation Has Two Sides: Evaluating Data Augmentation for Deep One-class Classification
- RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation
- RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches
- S$2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic
- Safe and Robust Watermark Injection with a Single OoD Image
- Safe Collaborative Filtering
- SafeDreamer: Safe Reinforcement Learning with World Models
- Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model
- Safe RLHF: Safe Reinforcement Learning from Human Feedback
- Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
- SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
- SALMONN: Towards Generic Hearing Abilities for Large Language Models
- SALMON: Self-Alignment with Instructable Reward Models
- SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
- Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity
- Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation
- Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight
- Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data
- Sample-Efficient Multi-Agent RL: An Optimization Perspective
- Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks
- Sample-Efficient Quality-Diversity by Cooperative Coevolution
- Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based Initialization
- SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer
- SaNN: Simple Yet Powerful Simplicial-aware Neural Networks
- SaProt: Protein Language Modeling with Structure-aware Vocabulary
- SAS: Structured Activation Sparsification
- Scalable and Effective Implicit Graph Neural Networks on Large Graphs
- Scalable Diffusion for Materials Generation
- Scalable Language Model with Generalized Continual Learning
- Scalable Modular Network: A Framework for Adaptive Learning via Agreement Routing
- Scalable Monotonic Neural Networks
- Scalable Neural Network Kernels
- Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks
- Scale-Adaptive Diffusion Model for Complex Sketch Synthesis
- ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models
- Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
- Scaling Convex Neural Networks with Burer-Monteiro Factorization
- Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement
- Scaling Laws for Associative Memories
- Scaling Laws for Sparsely-Connected Foundation Models
- Scaling Laws of RoPE-based Extrapolation
- Scaling physics-informed hard constraints with mixture-of-experts
- Scaling Supervised Local Learning with Augmented Auxiliary Networks
- SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos
- Score-based generative models break the curse of dimensionality in learning a family of sub-Gaussian distributions
- Score Models for Offline Goal-Conditioned Reinforcement Learning
- Score Regularized Policy Optimization through Diffusion Behavior
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
- SE(3)-Stochastic Flow Matching for Protein Backbone Generation
- SEABO: A Simple Search-Based Method for Offline Imitation Learning
- SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution
- Searching for High-Value Molecules Using Reinforcement Learning and Transformers
- SEA: Sparse Linear Attention with Estimated Attention Mask
- Secure and Trustworthy Large Language Models
- Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective
- Seer: Language Instructed Video Prediction with Latent Diffusion Models
- SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases
- SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction
- Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives
- Selective Visual Representations Improve Convergence and Generalization for Embodied AI
- Select to Perfect: Imitating desired behavior from large multi-agent data
- Self-Alignment with Instruction Backtranslation
- SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning
- Self-Consuming Generative Models Go MAD
- Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
- Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
- Self-Supervised Contrastive Learning for Long-term Forecasting
- Self-Supervised Dataset Distillation for Transfer Learning
- Self-Supervised Heterogeneous Graph Learning: a Homophily and Heterogeneity View
- Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes
- Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment
- Self-supervised Representation Learning from Random Data Projectors
- Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech
- Semantic Flow: Learning Semantic Fields of Dynamic Scenes from Monocular Videos
- SemiReward: A General Reward Model for Semi-supervised Learning
- Sentence-level Prompts Benefit Composed Image Retrieval
- Separate and Diffuse: Using a Pretrained Diffusion Model for Better Source Separation
- Separating common from salient patterns with Contrastive Representation Learning
- SEPT: Towards Efficient Scene Representation Learning for Motion Prediction
- SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking
- SetCSE: Set Operations using Contrastive Learning of Sentence Embeddings
- Set Learning for Accurate and Calibrated Models
- SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation
- SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem
- Shadow Cones: A Generalized Framework for Partial Order Embeddings
- Sharpness-Aware Data Poisoning Attack
- Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning
- Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
- Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation
- SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
- Simple Hierarchical Planning with Diffusion
- Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient Heterogeneity
- Simplicial Representation Learning with Neural $k$-Forms
- Simplifying Transformer Blocks
- Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape
- SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations
- Single Motion Diffusion
- Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
- Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning
- SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models
- Skill or Luck? Return Decomposition via Advantage Functions
- Skip-Attention: Improving Vision Transformers by Paying Less Attention
- Sliced Denoising: A Physics-Informed Molecular Pre-Training Method
- Sliced Wasserstein Estimation with Control Variates
- SliceGPT: Compress Large Language Models by Deleting Rows and Columns
- SLiMe: Segment Like Me
- Small-scale proxies for large-scale Transformer training instabilities
- SmartPlay : A Benchmark for LLMs as Intelligent Agents
- Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing
- SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training
- Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community
- Social-Transmotion: Promptable Human Trajectory Prediction
- SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series
- Soft Contrastive Learning for Time Series
- Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models
- Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity
- SOHES: Self-supervised Open-world Hierarchical Entity Segmentation
- SOInter: A Novel Deep Energy-Based Interpretation Method for Explaining Structured Output Models
- SolidGen: An Autoregressive Model for Direct B-rep Synthesis
- Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
- Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution
- Solving High Frequency and Multi-Scale PDEs with Gaussian Processes
- Solving Homogeneous and Heterogeneous Cooperative Tasks with Greedy Sequential Execution
- Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency
- Some Fundamental Aspects about Lipschitz Continuity of Neural Networks
- Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
- SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
- Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation
- Space and time continuous physics simulation from partial observations
- Space Group Constrained Crystal Generation
- SpaCE: The Spatial Confounding Environment
- SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation
- SparseFormer: Sparse Visual Recognition via Limited Latent Tokens
- Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging
- Sparse MoE with Language Guided Routing for Multilingual Machine Translation
- Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN
- Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning
- Sparsistency for inverse optimal transport
- Spatially-Aware Transformers for Embodied Agents
- Spatio-Temporal Approximation: A Training-Free SNN Conversion for Transformers
- Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generation
- SPDER: Semiperiodic Damping-Enabled Object Representation
- Spectrally Transformed Kernel Regression
- SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models
- Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips
- SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition
- Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM
- SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
- SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning
- Spurious Feature Diversification Improves Out-of-distribution Generalization
- sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows
- SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores
- Stabilizing Backpropagation Through Time to Learn Complex Physics
- Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data
- Stable Anisotropic Regularization
- Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data
- Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns
- STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction
- STARC: A General Framework For Quantifying Differences Between Reward Functions
- State Representation Learning Using an Unbalanced Atlas
- Statistically Optimal $K$-means Clustering via Nonnegative Low-rank Semidefinite Programming
- Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts
- Statistical Rejection Sampling Improves Preference Optimization
- Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds
- Stochastic Controlled Averaging for Federated Learning with Communication Compression
- Stochastic Gradient Descent for Gaussian Processes Done Right
- Stochastic Modified Equations and Dynamics of Dropout Algorithm
- Stories from my life
- Stories from my life
- Stories from my life
- Stories from my life
- Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling
- Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects
- STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models
- StructComp: Substituting propagation with Structural Compression in Training Graph Contrastive Learning
- Structural Estimation of Partially Observed Linear Non-Gaussian Acyclic Model: A Practical Approach with Identifiability
- Structural Fairness-aware Active Learning for Graph Neural Networks
- Structural Inference with Dynamics Encoding and Partial Correlation Coefficients
- Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding
- Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning
- Stylized Offline Reinforcement Learning: Extracting Diverse High-Quality Behaviors from Heterogeneous Datasets
- Submodular Reinforcement Learning
- Subtractive Mixture Models via Squaring: Representation and Learning
- Successor Heads: Recurring, Interpretable Attention Heads In The Wild
- Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
- Sufficient conditions for offline reactivation in recurrent neural networks
- Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs
- Supervised Knowledge Makes Large Language Models Better In-context Learners
- SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs
- SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NAS
- SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning
- SWE-bench: Can Language Models Resolve Real-world Github Issues?
- SweetDreamer: Aligning Geometric Priors in 2D diffusion for Consistent Text-to-3D
- Symbol as Points: Panoptic Symbol Spotting via Point-based Representation
- SYMBOL: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning
- Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanics
- Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems
- Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching
- Symmetric Single Index Learning
- Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation
- Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
- Synaptic Weight Distributions Depend on the Geometry of Plasticity
- SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
- Synergistic Patch Pruning for Vision Transformer: Unifying Intra- & Inter-Layer Patch Importance
- TabR: Tabular Deep Learning Meets Nearest Neighbors
- TAB: Temporal Accumulated Batch Normalization in Spiking Neural Networks
- Tackling Climate Change with Machine Learning: Fostering the Maturity of ML Applications for Climate Change
- Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update Calibration
- TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series
- Tag2Text: Guiding Vision-Language Model via Image Tagging
- Tailoring Self-Rationalizers with Multi-Reward Distillation
- TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
- Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
- Talk like a Graph: Encoding Graphs for Large Language Models
- Tangent Transformers for Composition,Privacy and Removal
- TapMo: Shape-aware Motion Generation of Skeleton-free Characters
- Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning
- Task Planning for Visual Room Rearrangement under Partial Observability
- Task structure and nonlinearity jointly determine learned representational geometry
- TD-MPC2: Scalable, Robust World Models for Continuous Control
- Teaching Arithmetic to Small Transformers
- Teaching Language Models to Hallucinate Less with Synthetic Tasks
- Teaching Large Language Models to Self-Debug
- Teach LLMs to Phish: Stealing Private Information from Language Models
- TEDDY: Trimming Edges with Degree-based Discrimination Strategy
- Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
- TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
- Temporal Generalization Estimation in Evolving Graphs
- Tensor Programs VI: Feature Learning in Infinite Depth Neural Networks
- Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
- TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts
- TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series
- Test-time Adaptation against Multi-modal Reliability Bias
- Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
- Test-Time Training on Nearest Neighbors for Large Language Models
- Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
- TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields
- Text-to-3D with Classifier Score Distillation
- The Alignment Problem from a Deep Learning Perspective
- The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World
- The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing
- The ChatGLM's Road to AGI
- The ChatGLM's Road to AGI
- The ChatGLM's Road to AGI
- The ChatGLM's Road to AGI
- The Consensus Game: Language Model Generation via Equilibrium Search
- The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning
- The Curse of Diversity in Ensemble-Based Exploration
- The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models
- The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation using Foundation Models
- The Effective Horizon Explains Deep RL Performance in Stochastic Environments
- The Effectiveness of Random Forgetting for Robust Generalization
- The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images
- The emerging science of benchmarks
- The emerging science of benchmarks
- The emerging science of benchmarks
- The emerging science of benchmarks
- The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks.
- The Expressive Power of Low-Rank Adaptation
- The Expressive Power of Transformers with Chain of Thought
- The False Promise of Imitating Proprietary Language Models
- The Generalization Gap in Offline Reinforcement Learning
- The Generative AI Paradox: “What It Can Create, It May Not Understand”
- The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry
- The Hidden Language of Diffusion Models
- The Human-AI Substitution game: active learning from a strategic labeler
- The importance of feature preprocessing for differentially private linear optimization
- The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting — An Analytical Model
- The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing
- The LLM Surgeon
- The Marginal Value of Momentum for Small Learning Rate SGD
- The mechanistic basis of data dependence and abrupt learning in an in-context classification task
- The Need for Speed: Pruning Transformers with One Recipe
- The optimality of kernel classifiers in Sobolev space
- Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach
- Theoretical Understanding of Learning from Adversarial Perturbations
- The Reasonableness Behind Unreasonable Translation Capability of Large Language Model
- The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A”
- The Trickle-down Impact of Reward Inconsistency on RLHF
- The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
- The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
- The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric
- The Update-Equivalence Framework for Decision-Time Planning
- The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models
- Think before you speak: Training Language Models With Pause Tokens
- Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
- Thin-Shell Object Manipulations With Differentiable Physics Simulations
- THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS
- Threaten Spiking Neural Networks through Combining Rate and Temporal Information
- Threshold-Consistent Margin Loss for Open-World Deep Metric Learning
- TiC-CLIP: Continual Training of CLIP Models
- Tight Rates in Supervised Outlier Transfer Learning
- Time-Efficient Reinforcement Learning with Stochastic Stateful Policies
- Time Fairness in Online Knapsack Problems
- Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
- TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting
- Time Travel in LLMs: Tracing Data Contamination in Large Language Models
- Time-Varying Propensity Score to Bridge the Gap between the Past and Present
- T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
- To Grok or not to Grok: Disentangling Generalization and Memorization on Corrupted Algorithmic Datasets
- TokenFlow: Consistent Diffusion Features for Consistent Video Editing
- Tool-Augmented Reward Modeling
- ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
- Topic Modeling as Multi-Objective Contrastive Optimization
- Topological data analysis on noisy quantum computers
- TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning
- ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
- TorchRL: A data-driven decision-making library for PyTorch
- TOSS: High-quality Text-guided Novel View Synthesis from a Single Image
- To the Cutoff... and Beyond? A Longitudinal Perspective on LLM Data Contamination
- Toward effective protection against diffusion-based mimicry through score distillation
- Toward Optimal Policy Population Growth in Two-Player Zero-Sum Games
- Towards 3D Molecule-Text Interpretation in Language Models
- Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints
- Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation
- Towards a statistical theory of data selection under weak supervision
- Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
- Towards Category Unification of 3D Single Object Tracking on Point Clouds
- Towards Characterizing Domain Counterfactuals for Invertible Latent Causal Models
- Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators
- Towards Codable Watermarking for Injecting Multi-Bits Information to LLMs
- Towards Cross Domain Generalization of Hamiltonian Representation via Meta Learning
- Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations
- Towards domain-invariant Self-Supervised Learning with Batch Styles Standardization
- Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
- Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning Framework
- Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach
- Towards Establishing Guaranteed Error for Learned Database Operations
- Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery
- Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark
- Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning
- Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets
- Towards Foundation Models for Knowledge Graph Reasoning
- Towards Generative Abstract Reasoning: Completing Raven’s Progressive Matrix via Rule Abstraction and Selection
- Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
- Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach
- Towards image compression with perfect realism at ultra-low bitrates
- Towards Imitation Learning to Branch for MIP: A Hybrid Reinforcement Learning based Sample Augmentation Approach
- Towards LLM4QPE: Unsupervised Pretraining of Quantum Property Estimation and A Benchmark
- Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching
- Towards Meta-Pruning via Optimal Transport
- Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models
- Towards Offline Opponent Modeling with In-context Learning
- Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection
- Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback
- Towards Poisoning Fair Representations
- Towards Principled Representation Learning from Videos for Reinforcement Learning
- Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features
- Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation
- Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks
- Towards Robust Multi-Modal Reasoning via Model Selection
- Towards Robust Offline Reinforcement Learning under Diverse Data Corruption
- Towards Robust Out-of-Distribution Generalization Bounds via Sharpness
- Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition
- Towards the Fundamental Limits of Knowledge Transfer over Finite Domains
- Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion
- Towards Transparent Time Series Forecasting
- Toward Student-oriented Teacher Network Training for Knowledge Distillation
- Towards Understanding Factual Knowledge of Large Language Models
- Towards Understanding Sycophancy in Language Models
- Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond
- Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy
- Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks
- Training Bayesian Neural Networks with Sparse Subspace Variational Inference
- Training Diffusion Models with Reinforcement Learning
- Training-free Multi-objective Diffusion Model for 3D Molecule Generation
- Training Graph Transformers via Curriculum-Enhanced Attention Distillation
- Training Socially Aligned Language Models on Simulated Social Interactions
- Training Unbiased Diffusion Models From Biased Dataset
- Trajeglish: Traffic Modeling as Next-Token Prediction
- TRAM: Bridging Trust Regions and Sharpness Aware Minimization
- Transferring Labels to Solve Annotation Mismatches Across Object Detection Datasets
- Transferring Learning Trajectories of Neural Networks
- Transformer Fusion with Optimal Transport
- Transformer-Modulated Diffusion Models for Probabilistic Multivariate Time Series Forecasting
- Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining
- Transformers can optimally learn regression mixture models
- Transformer-VQ: Linear-Time Transformers via Vector Quantization
- Transport meets Variational Inference: Controlled Monte Carlo Diffusions
- Traveling Waves Encode The Recent Past and Enhance Sequence Learning
- Treatment Effects Estimation By Uniform Transformer
- Tree Cross Attention
- Tree-Planner: Efficient Close-loop Task Planning with Large Language Models
- Tree Search-Based Policy Optimization under Stochastic Execution Delay
- T-Rep: Representation Learning for Time Series using Time-Embeddings
- True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement Learning
- Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning
- Turning large language models into cognitive models
- TUVF: Learning Generalizable Texture UV Radiance Fields
- Two-stage LLM Fine-tuning with Less Specialization and More Generalization
- Two-timescale Extragradient for Finding Local Minimax Points
- UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous Driving
- Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation
- Unbiased Watermark for Large Language Models
- Uncertainty-aware Constraint Inference in Inverse Constrained Reinforcement Learning
- Uncertainty-aware Graph-based Hyperspectral Image Classification
- Uncertainty Quantification via Stable Distribution Propagation
- Unconstrained Stochastic CCA: Unifying Multiview and Self-Supervised Learning
- Understanding Addition in Transformers
- Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
- Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression
- Understanding Catastrophic Forgetting in Language Models via Implicit Inference
- Understanding Certified Training with Interval Bound Propagation
- Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory
- Understanding Domain Generalization: A Noise Robustness Perspective
- Understanding Expressivity of GNN in Rule Learning
- Understanding In-Context Learning from Repetitions
- Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions
- Understanding prompt engineering may not require rethinking generalization
- Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation
- Understanding the Effects of RLHF on LLM Generalisation and Diversity
- Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods
- Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift
- Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
- Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP
- Understanding when Dynamics-Invariant Data Augmentations Benefit Model-free Reinforcement Learning Updates
- Uni3D: Exploring Unified 3D Representation at Scale
- UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling
- Unified Generative Modeling of 3D Molecules with Bayesian Flow Networks
- Unified Human-Scene Interaction via Prompted Chain-of-Contacts
- Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
- Unified Projection-Free Algorithms for Adversarial DR-Submodular Optimization
- Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence
- Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization
- Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback
- UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science
- Universal Backdoor Attacks
- Universal Guidance for Diffusion Models
- Universal Humanoid Motion Representations for Physics-Based Control
- Universal Jailbreak Backdoors from Poisoned Human Feedback
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition
- Unknown Domain Inconsistency Minimization for Domain Generalization
- Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation
- Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND
- Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning
- Unlocking the Power of Representations in Long-term Novelty-based Exploration
- Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models
- Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation
- Unpaired Image-to-Image Translation via Neural Schrödinger Bridge
- Unprocessing Seven Years of Algorithmic Fairness
- Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space
- Unraveling the Key Components of OOD Generalization via Diversification
- UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models
- Unsupervised Order Learning
- Unsupervised Pretraining for Fact Verification by Language Model Distillation
- Unveiling and Manipulating Prompt Influence in Large Language Models
- Unveiling Options with Neural Network Decomposition
- Unveiling the Pitfalls of Knowledge Editing for Large Language Models
- Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels
- USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields
- ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation
- Vanishing Gradients in Reinforcement Finetuning of Language Models
- Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits
- Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled Data
- Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions
- Variational Bayesian Last Layers
- Variational Inference for SDEs Driven by Fractional Noise
- VBH-GNN: Variational Bayesian Heterogeneous Graph Neural Networks for Cross-subject Emotion Recognition
- VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections
- VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models
- V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection
- VDT: General-purpose Video Diffusion Transformers via Mask Modeling
- VeRA: Vector-based Random Matrix Adaptation
- VersVideo: Leveraging Enhanced Temporal Diffusion Models for Versatile Video Generation
- VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarks
- VFLAIR: A Research Library and Benchmark for Vertical Federated Learning
- ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
- Video Decomposition Prior: Editing Videos Layer by Layer
- Video Language Planning
- Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation
- ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
- Vision-by-Language for Training-Free Compositional Image Retrieval
- Vision-Language Foundation Models as Effective Robot Imitators
- Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning
- Vision Transformers Need Registers
- Visual Data-Type Understanding does not emerge from scaling Vision-Language Models
- Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
- VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE
- VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
- VQ-TR: Vector Quantized Attention for Time Series Forecasting
- Waxing-and-Waning: a Generic Similarity-based Framework for Efficient Self-Supervised Learning
- Weaker MVI Condition: Extragradient Methods with Multi-Step Exploration
- Weakly-supervised Audio Separation via Bi-modal Semantic Similarity
- Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images
- Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency
- WebArena: A Realistic Web Environment for Building Autonomous Agents
- What Algorithms can Transformers Learn? A Study in Length Generalization
- "What Data Benefits My Classifier?" Enhancing Model Performance and Interpretability through Influence-Based Data Selection
- What does automatic differentiation compute for neural networks?
- What does the Knowledge Neuron Thesis Have to do with Knowledge?
- What Makes a Good Prune? Maximal Unstructured Pruning for Maximal Cosine Similarity
- What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
- What Matters to You? Towards Visual Representation Alignment for Robot Learning
- What's in a Prior? Learned Proximal Networks for Inverse Problems
- What's In My Big Data?
- When can transformers reason with abstract symbols?
- When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
- When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method
- When Semantic Segmentation Meets Frequency Aliasing
- When should we prefer Decision Transformers for Offline Reinforcement Learning?
- Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in DNNs
- Whittle Index with Multiple Actions and State Constraint for Inventory Management
- Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models
- Why is SAM Robust to Label Noise?
- Why your work matters for climate in more ways than you think
- Why your work matters for climate in more ways than you think
- Why your work matters for climate in more ways than you think
- Why your work matters for climate in more ways than you think
- WildChat: 1M ChatGPT Interaction Logs in the Wild
- WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space
- Window Attention is Bugged: How not to Interpolate Position Embeddings
- Win-Win: Training High-Resolution Vision Transformers from Two Windows
- WizardCoder: Empowering Code Large Language Models with Evol-Instruct
- WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions
- WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series
- Workflow Discovery from Dialogues in the Low Data Regime
- Workshop on Large Language Models for Agents
- Workshop on Learning from Time Series for Health
- Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models
- Xformer: Hybrid X-Shaped Transformer for Image Denoising
- YaRN: Efficient Context Window Extension of Large Language Models
- Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML
- You Only Query Once: An Efficient Label-Only Membership Inference Attack
- Zero and Few-shot Semantic Parsing with Ambiguous Inputs
- Zero Bubble (Almost) Pipeline Parallelism
- ZeRO++: Extremely Efficient Collective Communication for Large Model Training
- ZeroFlow: Scalable Scene Flow via Distillation
- Zero-Mean Regularized Spectral Contrastive Learning: Implicitly Mitigating Wrong Connections in Positive-Pair Graphs
- Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models
- Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models
- Zero-Shot Robustification of Zero-Shot Models
- Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles
- Zipformer: A faster and better encoder for automatic speech recognition
- ZipIt! Merging Models from Different Tasks without Training
- Zoology: Measuring and Improving Recall in Efficient Language Models