Skip to yearly menu bar
Skip to main content
Main Navigation
NeurIPS
Help/FAQ
Contact NeurIPS
Code of Ethics
Code of Conduct
Create Profile
Journal To Conference Track
Diversity & Inclusion
Proceedings
Future Meetings
Press
Exhibitor Information
Privacy Policy
Downloads
My Stuff
Login
Select Year: (2024)
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
2012
2011
2010
2009
2008
2007
2006
Start Here
Schedule
Tutorials
Main Conference
Invited Talks
Orals
Papers
Paper Visualization
Competitions
Datasets & Benchmarks
Journal Track
Creative AI Track
Outstanding Paper Awards
Affinity Workshops
Community
Affinity Events
Mentorship Event
Bridging the Future
Socials
Careers
Workshops
Exhibitors
Help
FAQ
Helpdesk in RocketChat
Organizers
Browse
mini
compact
topic
detail
Showing papers for
.
×
×
title
author
topic
session
shuffle
by
serendipity
bookmarked first
visited first
not visited first
bookmarked but not visited
Enable Javascript in your browser to see the papers page.
Visual Perception by Large Language Model’s Weights
No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO
Are Language Models Actually Useful for Time Series Forecasting?
LIVE: Learnable In-Context Vector for Visual Question Answering
RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions
Metric from Human: Zero-shot Monocular Metric Depth Estimation via Test-time Adaptation
Recognize Any Regions
AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis
Needle In A Multimodal Haystack
SurgicAI: A Fine-grained Platform for Data Collection and Benchmarking in Surgical Policy Learning
InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD
Universal Exact Compression of Differentially Private Mechanisms
Fair Kernel K-Means: from Single Kernel to Multiple Kernel
Fetch and Forge: Efficient Dataset Condensation for Object Detection
A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences
OccFusion: Rendering Occluded Humans with Generative Diffusion Priors
CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition
A Single-Step, Sharpness-Aware Minimization is All You Need to Achieve Efficient and Accurate Sparse Training
Evaluating Copyright Takedown Methods for Language Models
xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
ODRL: A Benchmark for Off-Dynamics Reinforcement Learning
Scene Graph Generation with Role-Playing Large Language Models
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization
SureMap: Simultaneous mean estimation for single-task and multi-task disaggregated evaluation
Truncated Variance Reduced Value Iteration
Ask, Attend, Attack: An Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models
Multi-Group Proportional Representation in Retrieval
Safe and Sparse Newton Method for Entropic-Regularized Optimal Transport
VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks
EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching
Many-Shot In-Context Learning
DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning
TorchOpt: An Efficient Library for Differentiable Optimization
Bayesian Online Natural Gradient (BONG)
Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss
Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured training
Aligning Large Language Models with Representation Editing: A Control Perspective
Simple and Fast Distillation of Diffusion Models
Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
Exploiting LLM Quantization
Unveiling the Tapestry of Consistency in Large Vision-Language Models
Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond
Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models
CLIPCEIL: Domain Generalization through CLIP via Channel rEfinement and Image-text aLignment
Flexible task abstractions emerge in linear networks with fast and bounded units
A Careful Examination of Large Language Model Performance on Grade School Arithmetic
PhyRecon: Physically Plausible Neural Scene Reconstruction
GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs
Scalable and Effective Arithmetic Tree Generation for Adder and Multiplier Designs
Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models
Expectile Regularization for Fast and Accurate Training of Neural Optimal Transport
MTGS: A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze Prediction
InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint
Optimal Transport-based Labor-free Text Prompt Modeling for Sketch Re-identification
Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study
Can large language models explore in-context?
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
Transferable Adversarial Attacks on SAM and Its Downstream Models
Compositional 3D-aware Video Generation with LLM Director
Aligning Model Properties via Conformal Risk Control
Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation
Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model
Preference Learning of Latent Decision Utilities with a Human-like Model of Preferential Choice
Globally Convergent Variational Inference
Efficient Large Multi-modal Models via Visual Context Compression
Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited Modalities
Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models
TableRAG: Million-Token Table Understanding with Language Models
FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model
Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Scary
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
Learning Social Welfare Functions
Worst-Case Offline Reinforcement Learning with Arbitrary Data Support
One-shot Federated Learning via Synthetic Distiller-Distillate Communication
Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
Reproducibility study of “LICO: Explainable Models with Language-Image Consistency"
Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure
Copycats: the many lives of a publicly available medical imaging dataset
Efficient Centroid-Linkage Clustering
Improving Context-Aware Preference Modeling for Language Models
When are dynamical systems learned from time series data statistically accurate?
Regularized Q-Learning
What is my quantum computer good for? Quantum capability learning with physics-aware neural networks
The Dormant Neuron Phenomenon in Multi-Agent Reinforcement Learning Value Factorization
Long-form factuality in large language models
Unsupervised Discovery of Formulas for Mathematical Constants
One-Shot Safety Alignment for Large Language Models via Optimal Dualization
Higher-Order Causal Message Passing for Experimentation with Complex Interference
D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup
Predicting the Performance of Foundation Models via Agreement-on-the-Line
Rethinking LLM Memorization through the Lens of Adversarial Compression
Stylus: Automatic Adapter Selection for Diffusion Models
Graph Structure Inference with BAM: Neural Dependency Processing via Bilinear Attention
Fast Best-of-N Decoding via Speculative Rejection
Towards Understanding Extrapolation: a Causal Lens
Differentially Private Reinforcement Learning with Self-Play
Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations
On the Worst Prompt Performance of Large Language Models
Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization
Mini-Sequence Transformers: Optimizing Intermediate Memory for Long Sequences Training
You Only Cache Once: Decoder-Decoder Architectures for Language Models
VFIMamba: Video Frame Interpolation with State Space Models
Generalized Tensor Decomposition for Understanding Multi-Output Regression under Combinatorial Shifts
TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning
Mesa-Extrapolation: A Weave Position Encoding Method for Enhanced Extrapolation in LLMs
FineStyle: Fine-grained Controllable Style Personalization for Text-to-image Models
Non-parametric classification via expand-and-sparsify representation
ScaleKD: Strong Vision Transformers Could Be Excellent Teachers
When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL
Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games
SeafloorGenAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey
Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
MEQA: A Benchmark for Multi-hop Event-centric Question Answering with Explanations
Constructing Semantics-Aware Adversarial Examples with Probabilistic Perspective
CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence
OccamLLM: Fast and Exact Language Model Arithmetic in a Single Step
RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes
CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding
RedPajama: an Open Dataset for Training Large Language Models
ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons
A New Multi-Source Light Detection Benchmark and Semi-Supervised Focal Light Detection
VideoGUI: A Benchmark for GUI Automation from Instructional Videos
IllumiNeRF: 3D Relighting Without Inverse Rendering
STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics
Learning Superconductivity from Ordered and Disordered Material Structures
DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks
NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noise
Implicit Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
BEACON: Benchmark for Comprehensive RNA Tasks and Language Models
A benchmark for prediction of transcriptomic responses to chemical perturbations across cell types
BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval
PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques
FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models
VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark
The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection Benchmark
MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction
Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning
Newswire: A Large-Scale Structured Database of a Century of Historical News
E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
MOTI$\mathcal{V}\mathcal{E}$: A Drug-Target Interaction Graph For Inductive Link Prediction
MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
LVD-2M: A Long-take Video Dataset with Temporally Dense Captions
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos
TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning
UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations
Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning
ClevrSkills: Compositional Language And Visual Understanding in Robotics
PageRank Bandits for Link Prediction
Vript: A Video Is Worth Thousands of Words
WildPPG: A Real-World PPG Dataset of Long Continuous Recordings
Towards Explainable Evaluation Metrics for Machine Translation
Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment
VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding
Statistical Inference for Fairness Auditing
Plant-and-Steal: Truthful Fair Allocations via Predictions
Semantic Feature Learning for Universal Unsupervised Cross-Domain Retrieval
Reproducibility study of FairAC
ResAD: A Simple Framework for Class Generalizable Anomaly Detection
A teacher-teacher framework for clinical language representation learning
Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame
XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation
MutaPLM: Protein Language Modeling for Mutation Explanation and Engineering
Federated Ensemble-Directed Offline Reinforcement Learning
Neural Concept Binder
PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecasting
ReGS: Reference-based Controllable Scene Stylization with Gaussian Splatting
Information-theoretic Generalization Analysis for Expected Calibration Error
Predicting Ground State Properties: Constant Sample Complexity and Deep Learning Algorithms
Toward a Stable, Fair, and Comprehensive Evaluation of Object Hallucination in Large Vision-Language Models
Stepping Forward on the Last Mile
Proving Theorems Recursively
Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
Causal Discovery from Event Sequences by Local Cause-Effect Attribution
MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts
Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters
Learning diffusion at lightspeed
On the Use of Anchoring for Training Vision Models
Measuring Mutual Policy Divergence for Multi-Agent Sequential Exploration
CIFD: Controlled Information Flow to Enhance Knowledge Distillation
FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
Combining Statistical Depth and Fermat Distance for Uncertainty Quantification
Simplified and Generalized Masked Diffusion for Discrete Data
From Unstructured Data to In-Context Learning: Exploring What Tasks Can Be Learned and When
Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation
Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model
Stress-Testing Capability Elicitation With Password-Locked Models
IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation
SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution
FLAME : Factuality-Aware Alignment for Large Language Models
FedNE: Surrogate-Assisted Federated Neighbor Embedding for Dimensionality Reduction
Gated Inference Network: Inference and Learning State-Space Models
Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization
GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations
Diffusion-based Curriculum Reinforcement Learning
In Pursuit of Causal Label Correlations for Multi-label Image Recognition
Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration
HEPrune: Fast Private Training of Deep Neural Networks With Encrypted Data Pruning
Reasons and Solutions for the Decline in Model Performance after Editing
ReVideo: Remake a Video with Motion and Content Control
Universal Online Convex Optimization with $1$ Projection per Round
Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network
Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation
The Many Faces of Optimal Weak-to-Strong Learning
Deep Correlated Prompting for Visual Recognition with Missing Modalities
DiffusionPDE: Generative PDE-Solving under Partial Observation
Personalized Federated Learning with Mixture of Models for Adaptive Prediction and Model Fine-Tuning
CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition
Accelerating ERM for data-driven algorithm design using output-sensitive techniques
Learning Bregman Divergences with Application to Robustness
Random Function Descent
OxonFair: A Flexible Toolkit for Algorithmic Fairness
Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation
ChronoEpilogi: Scalable Time Series Selection with Multiple Solutions
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
Unified Lexical Representation for Interpretable Visual-Language Alignment
Communication-Efficient Federated Group Distributionally Robust Optimization
Hybrid Top-Down Global Causal Discovery with Local Search for Linear and Nonlinear Additive Noise Models
Multi-modal Transfer Learning between Biological Foundation Models
Controlled maximal variability along with reliable performance in recurrent neural networks
Inference of Neural Dynamics Using Switching Recurrent Neural Networks
A Polar coordinate system represents syntax in large language models
Focus On What Matters: Separated Models For Visual-Based RL Generalization
LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
Automated Multi-level Preference for MLLMs
Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation
Linear Causal Representation Learning from Unknown Multi-node Interventions
Video Token Merging for Long Video Understanding
RoPINN: Region Optimized Physics-Informed Neural Networks
A Sober Look at the Robustness of CLIPs to Spurious Features
Neural Experts: Mixture of Experts for Implicit Neural Representations
Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs
Space-Time Continuous PDE Forecasting using Equivariant Neural Fields
Diffusion Models are Certifiably Robust Classifiers
Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling
High Rank Path Development: an approach to learning the filtration of stochastic processes
Low Precision Local Training is Enough for Federated Learning
Curriculum Fine-tuning of Vision Foundation Model for Medical Image Classification Under Label Noise
Supra-Laplacian Encoding for Transformer on Dynamic Graphs
Large Pre-trained time series models for cross-domain Time series analysis tasks
The Benefits of Balance: From Information Projections to Variance Reduction
The Space Complexity of Approximating Logistic Loss
Optimal deep learning of holomorphic operators between Banach spaces
Analysing the Generalisation and Reliability of Steering Vectors
Measuring Dejavu Memorization Efficiently
Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks
Learning to Cooperate with Humans using Generative Agents
Achieving Domain-Independent Certified Robustness via Knowledge Continuity
Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment
On the Necessity of Collaboration for Online Model Selection with Decentralized Data
Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios
DOFEN: Deep Oblivious Forest ENsemble
FIFO-Diffusion: Generating Infinite Videos from Text without Training
Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval
Convergence Analysis of Split Federated Learning on Heterogeneous Data
Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction
Motif-oriented influence maximization for viral marketing in large-scale social networks
Hierarchical Selective Classification
On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions
Stochastic Optimal Control Matching
Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective
S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule Search
Learning Structured Representations with Hyperbolic Embeddings
Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation
$\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise
Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs
Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication
Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation
A Neural Network Approach for Efficiently Answering Most Probable Explanation Queries in Probabilistic Models
Sample-Efficient Agnostic Boosting
Energy-Based Modelling for Discrete and Mixed Data via Heat Equations on Structured Spaces
Unsupervised Object Detection with Theoretical Guarantees
Iterative Methods via Locally Evolving Set Process
Learning from Uncertain Data: From Possible Worlds to Possible Models
Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations
Implicit Bias of Mirror Flow on Separable Data
FasMe: Fast and Sample-efficient Meta Estimator for Precision Matrix Learning in Small Sample Settings
Optimization Can Learn Johnson Lindenstrauss Embeddings
Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms
Learning to Edit Visual Programs with Self-Supervision
Unifying Homophily and Heterophily for Spectral Graph Neural Networks via Triple Filter Ensembles
Learning Segmentation from Point Trajectories
Multi-turn Reinforcement Learning with Preference Human Feedback
Average gradient outer product as a mechanism for deep neural collapse
Can Language Models Learn to Skip Steps?
Learning Human-like Representations to Enable Learning Human Values
SILENCE: Protecting privacy in offloaded speech understanding on resource-constrained devices
3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability
Hamiltonian Monte Carlo Inference of Marginalized Linear Mixed-Effects Models
PACE: Pacing Operator Learning to Accurate Optical Field Simulation for Complicated Photonic Devices
Automatic Outlier Rectification via Optimal Transport
Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generation
Protecting Your LLMs with Information Bottleneck
Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers
YOLOv10: Real-Time End-to-End Object Detection
Derandomizing Multi-Distribution Learning
Transductive Active Learning: Theory and Applications
Improving Equivariant Model Training via Constraint Relaxation
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models
Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness
Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models
ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
Physics-Informed Regularization for Domain-Agnostic Dynamical System Modeling
Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference
Interpolating Item and User Fairness in Multi-Sided Recommendations
Toward Efficient Inference for Mixture of Experts
DeepLag: Discovering Deep Lagrangian Dynamics for Intuitive Fluid Prediction
Beware of Road Markings: A New Adversarial Patch Attack to Monocular Depth Estimation
SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model
Preferential Normalizing Flows
UniGAD: Unifying Multi-level Graph Anomaly Detection
HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach
Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKA
EnsIR: An Ensemble Algorithm for Image Restoration via Gaussian Mixture Models
Face2QR: A Unified Framework for Aesthetic, Face-Preserving, and Scannable QR Code Generation
FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
OwMatch: Conditional Self-Labeling with Consistency for Open-world Semi-Supervised Learning
Distributed Least Squares in Small Space via Sketching and Bias Reduction
Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit
Semidefinite Relaxations of the Gromov-Wasserstein Distance
Activating Self-Attention for Multi-Scene Absolute Pose Regression
GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping
Episodic Future Thinking Mechanism for Multi-agent Reinforcement Learning
Model Based Inference of Synaptic Plasticity Rules
Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery
BAKU: An Efficient Transformer for Multi-Task Policy Learning
SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning
DRACO: A Denoising-Reconstruction Autoencoder for Cryo-EM
RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness
DisCEdit: Model Editing by Identifying Discriminative Components
AirSketch: Generative Motion to Sketch
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
Improved Distribution Matching Distillation for Fast Image Synthesis
Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series
Gorilla: Large Language Model Connected with Massive APIs
Optimal Algorithms for Augmented Testing of Discrete Distributions
Exploring the Precise Dynamics of Single-Layer GAN Models: Leveraging Multi-Feature Discriminators for High-Dimensional Subspace Learning
GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats
On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation
MIDGArD: Modular Interpretable Diffusion over Graphs for Articulated Designs
Interaction-Force Transport Gradient Flows
Verified Code Transpilation with LLMs
Nonconvex Federated Learning on Compact Smooth Submanifolds With Heterogeneous Data
Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits
Stochastic contextual bandits with graph feedback: from independence number to MAS number
Interpretable Generalized Additive Models for Datasets with Missing Values
Reranking Laws for Language Generation: A Communication-Theoretic Perspective
Multi-Label Learning with Stronger Consistency Guarantees
Graph Coarsening with Message-Passing Guarantees
Moving Off-the-Grid: Scene-Grounded Video Representations
Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context
Verified Safe Reinforcement Learning for Neural Network Dynamic Models
Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions
ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination
Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation
Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis
Sample Complexity of Algorithm Selection Using Neural Networks and Its Applications to Branch-and-Cut
A Universal Growth Rate for Learning with Smooth Surrogate Losses
Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs
One-Step Diffusion Distillation through Score Implicit Matching
Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer
Learning Successor Features the Simple Way
KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge
From Causal to Concept-Based Representation Learning
Cardinality-Aware Set Prediction and Top-$k$ Classification
Variational Multi-scale Representation for Estimating Uncertainty in 3D Gaussian Splatting
SocraticLM: Exploring Socratic Personalized Teaching with Large Language Models
Time-MMD: A New Multi-Domain Multimodal Dataset for Time Series Analysis
MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
GRANOLA: Adaptive Normalization for Graph Neural Networks
Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation
4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities
HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning
Dynamic Neural Regeneration: Enhancing Deep Learning Generalization on Small Datasets
Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates
Self-Play Fine-tuning of Diffusion Models for Text-to-image Generation
Abstracted Shapes as Tokens - A Generalizable and Interpretable Model for Time-series Classification
Efficient Combinatorial Optimization via Heat Diffusion
AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection
Multi-Stage Predict+Optimize for (Mixed Integer) Linear Programs
Learning Partitions from Context
Smoothie: Label Free Language Model Routing
Refusal in Language Models Is Mediated by a Single Direction
Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models
Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba
Zipfian Whitening
Learning to Solve Quadratic Unconstrained Binary Optimization in a Classification Way
OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation
Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization
Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space
Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recovery
Efficient Discrepancy Testing for Learning with Distribution Shift
Classifier-guided Gradient Modulation for Enhanced Multimodal Learning
Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model
Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass
Symmetry Discovery Beyond Affine Transformations
Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning
Adaptive Proximal Gradient Method for Convex Optimization
Expert-level protocol translation for self-driving labs
Empowering Visible-Infrared Person Re-Identification with Large Foundation Models
Persistence Homology Distillation for Semi-supervised Continual Learning
Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching
ReMoDetect: Reward Models Recognize Aligned LLM's Generations
$\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling
Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration
Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought
From Dictionary to Tensor: A Scalable Multi-View Subspace Clustering Framework with Triple Information Enhancement
Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data
Exploration by Learning Diverse Skills through Successor State Representations
CALANet: Cheap All-Layer Aggregation for Human Activity Recognition
Sharing Key Semantics in Transformer Makes Efficient Image Restoration
Algorithmic Capabilities of Random Transformers
A Globally Optimal Portfolio for m-Sparse Sharpe Ratio Maximization
HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid
MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training
KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization
Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models
CSPG: Crossing Sparse Proximity Graphs for Approximate Nearest Neighbor Search
GSDF: 3DGS Meets SDF for Improved Neural Rendering and Reconstruction
Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing
Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Generation
Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning
PromptFix: You Prompt and We Fix the Photo
Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning
The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure
Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning
Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines
Universal Sample Coding
Learning-Augmented Approximation Algorithms for Maximum Cut and Related Problems
Directional Smoothness and Gradient Methods: Convergence and Adaptivity
Soft Tensor Product Representations for Fully Continuous, Compositional Visual Representations
Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators
Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems
AdaPKC: PeakConv with Adaptive Peak Receptive Field for Radar Semantic Segmentation
NeuralSteiner: Learning Steiner Tree for Overflow-avoiding Global Routing in Chip Design
GAVEL: Generating Games via Evolution and Language Models
Constrained Binary Decision Making
SS1: Accelerating Inference with Fast and Expressive Sketch Structured Transform
The Representation Landscape of Few-Shot Learning and Fine-Tuning in Large Language Models
A Layer-Wise Natural Gradient Optimizer for Training Deep Neural Networks
HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization
On conditional diffusion models for PDE simulations
UniTS: A Unified Multi-Task Time Series Model
Recurrent Reinforcement Learning with Memoroids
Hyperbolic Embeddings of Supervised Models
BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference
Interpret Your Decision: Logical Reasoning Regularization for Generalization in Visual Classification
Learning De-Biased Representations for Remote-Sensing Imagery
Validating Climate Models with Spherical Convolutional Wasserstein Distance
FreeSplat: Generalizable 3D Gaussian Splatting Towards Free View Synthesis of Indoor Scenes
Explanations that reveal all through the definition of encoding
Reciprocal Learning
Dueling over Dessert, Mastering the Art of Repeated Cake Cutting
Learning Cooperative Trajectory Representations for Motion Forecasting
SeeA*: Efficient Exploration-Enhanced A* Search by Selective Sampling
Improving the Training of Rectified Flows
In-Trajectory Inverse Reinforcement Learning: Learn Incrementally From An Ongoing Trajectory
MaNo: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
Interventional Causal Discovery in a Mixture of DAGs
Generalization Error Bounds for Two-stage Recommender Systems with Tree Structure
Towards a "Universal Translator" for Neural Dynamics at Single-Cell, Single-Spike Resolution
RTify: Aligning Deep Neural Networks with Human Behavioral Decisions
DiffSF: Diffusion Models for Scene Flow Estimation
Boosting the Potential of Large Language Models with an Intelligent Information Assistant
Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
Reactzyme: A Benchmark for Enzyme-Reaction Prediction
Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model
LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate
Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models
Graph Neural Networks Do Not Always Oversmooth
SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functions
Learning the Latent Causal Structure for Modeling Label Noise
Generating Highly Designable Proteins with Geometric Algebra Flow Matching
Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models
Evidential Mixture Machines: Deciphering Multi-Label Correlations for Active Learning Sensitivity
Task-oriented Time Series Imputation Evaluation via Generalized Representers
Non-asymptotic Global Convergence Analysis of BFGS with the Armijo-Wolfe Line Search
Semantics and Spatiality of Emergent Communication
AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties
Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems
Should We Really Edit Language Models? On the Evaluation of Edited Language Models
FineCLIP: Self-distilled Region-based CLIP for Better Fine-grained Understanding
Bayesian Adaptive Calibration and Optimal Design
3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction
HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation
Penalty-based Methods for Simple Bilevel Optimization under Hölderian Error Bounds
Fight Back Against Jailbreaking via Prompt Adversarial Tuning
Identification of Analytic Nonlinear Dynamical Systems with Non-asymptotic Guarantees
Crafting Interpretable Embeddings for Language Neuroscience by Asking LLMs Questions
P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics
Once Read is Enough: Domain-specific Pretraining-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain Knowledge
Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks
DiffPO: A causal diffusion model for learning distributions of potential outcomes
Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions
Exploring Adversarial Robustness of Deep State Space Models
Deep Learning in Medical Image Registration: Magic or Mirage?
MotionCraft: Physics-Based Zero-Shot Video Generation
Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
Be Confident in What You Know: Bayesian Parameter Efficient Fine-Tuning of Vision Foundation Models
Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow
OPEL: Optimal Transport Guided ProcedurE Learning
Order-Independence Without Fine Tuning
Perplexity-aware Correction for Robust Alignment with Noisy Preferences
SPEAR: Exact Gradient Inversion of Batches in Federated Learning
Efficient and Private Marginal Reconstruction with Local Non-Negativity
On the Role of Attention Masks and LayerNorm in Transformers
Unitary Convolutions for Learning on Graphs and Groups
Replicable Uniformity Testing
Bandits with Abstention under Expert Advice
LP-3DGS: Learning to Prune 3D Gaussian Splatting
Operator World Models for Reinforcement Learning
Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Space
Adaptive Passive-Aggressive Framework for Online Regression with Side Information
Text-Infused Attention and Foreground-Aware Modeling for Zero-Shot Temporal Action Detection
Advancing Spiking Neural Networks for Sequential Modeling with Central Pattern Generators
QGFN: Controllable Greediness with Action Values
Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model
Solving Sparse \& High-Dimensional-Output Regression via Compression
An Analysis of Elo Rating Systems via Markov Chains
On the Saturation Effects of Spectral Algorithms in Large Dimensions
Towards Flexible Visual Relationship Segmentation
Diffusion-Reward Adversarial Imitation Learning
Unveiling the Potential of Robustness in Selecting Conditional Average Treatment Effect Estimators
Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks
Improved Bayes Regret Bounds for Multi-Task Hierarchical Bayesian Bandit Algorithms
Efficient Temporal Action Segmentation via Boundary-aware Query Voting
FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
Small coresets via negative dependence: DPPs, linear statistics, and concentration
Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning
Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity
ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images
EEGPT: Pretrained Transformer for Universal and Reliable Representation of EEG Signals
Black-Box Forgetting
Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models
FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training
Clustering with Non-adaptive Subset Queries
(FL)$^2$: Overcoming Few Labels in Federated Semi-Supervised Learning
Towards Universal Mesh Movement Networks
Full-Distance Evasion of Pedestrian Detectors in the Physical World
MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space
Global Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers
On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models
Metric Transforms and Low Rank Representations of Kernels for Fast Attention
Beyond Optimism: Exploration With Partially Observable Rewards
Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models
Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification
LT-Defense: Searching-free Backdoor Defense via Exploiting the Long-tailed Effect
Bridge the Points: Graph-based Few-shot Segment Anything Semantically
Certified Adversarial Robustness via Randomized $\alpha$-Smoothing for Regression Models
Exploring Behavior-Relevant and Disentangled Neural Dynamics with Generative Diffusion Models
Towards Croppable Implicit Neural Representations
Latent Intrinsics Emerge from Training to Relight
VISA: Variational Inference with Sequential Sample-Average Approximations
Accelerated Regularized Learning in Finite N-Person Games
Statistical Multicriteria Benchmarking via the GSD-Front
Contextual Linear Optimization with Bandit Feedback
Thought of Search: Planning with Language Models Through The Lens of Efficiency
Mitigating Covariate Shift in Behavioral Cloning via Robust Stationary Distribution Correction
Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
Normal-GS: 3D Gaussian Splatting with Normal-Involved Rendering
Real-time Core-Periphery Guided ViT with Smart Data Layout Selection on Mobile Devices
Sparsity-Agnostic Linear Bandits with Adaptive Adversaries
Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention
INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
In-Context Learning with Representations: Contextual Generalization of Trained Transformers
Theoretical guarantees in KL for Diffusion Flow Matching
UDON: Universal Dynamic Online distillatioN for generic image representations
Your contrastive learning problem is secretly a distribution alignment problem
Are Self-Attentions Effective for Time Series Forecasting?
Improved Algorithms for Contextual Dynamic Pricing
Interpretable Lightweight Transformer via Unrolling of Learned Graph Smoothness Priors
Causal language modeling can elicit search and reasoning capabilities on logic puzzles
Learning to Predict Structural Vibrations
RGFN: Synthesizable Molecular Generation Using GFlowNets
Inverse M-Kernels for Linear Universal Approximators of Non-Negative Functions
BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling
CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization
Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
Attack-Aware Noise Calibration for Differential Privacy
Provable Benefits of Complex Parameterizations for Structured State Space Models
Loss Landscape Characterization of Neural Networks without Over-Parametrization
End-To-End Causal Effect Estimation from Unstructured Natural Language Data
Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources
Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment
Amortizing intractable inference in diffusion models for vision, language, and control
Wormhole Loss for Partial Shape Matching
Agent Planning with World Knowledge Model
S-SOS: Stochastic Sum-Of-Squares for Parametric Polynomial Optimization
How to Use Diffusion Priors under Sparse Views?
Interpretable Image Classification with Adaptive Prototype-based Vision Transformers
Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning
Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning
Autobidder's Dilemma: Why More Sophisticated Autobidders Lead to Worse Auction Efficiency
Dual Cone Gradient Descent for Training Physics-Informed Neural Networks
Alias-Free Mamba Neural Operator
Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNs
Accurate and Steady Inertial Pose Estimation through Sequence Structure Learning and Modulation
Panacea: Pareto Alignment via Preference Adaptation for LLMs
AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback
MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Images
UniTox: Leveraging LLMs to Curate a Unified Dataset of Drug-Induced Toxicity from FDA Labels
Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis
Pre-trained Large Language Models Use Fourier Features to Compute Addition
Boosting Vision-Language Models with Transduction
CigTime: Corrective Instruction Generation Through Inverse Motion Editing
Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity
Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
Generalization Bound and Learning Methods for Data-Driven Projections in Linear Programming
Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling
Spiking Token Mixer: A event-driven friendly Former structure for spiking neural networks
Learn To be Efficient: Build Structured Sparsity in Large Language Models
Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts
Generalizable and Animatable Gaussian Head Avatar
SARAD: Spatial Association-Aware Anomaly Detection and Diagnosis for Multivariate Time Series
Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model
Rethinking Optimal Transport in Offline Reinforcement Learning
Fairness and Efficiency in Online Class Matching
Belief-State Query Policies for User-Aligned Planning under Partial Observability
No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery
Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD
Large Language Model Unlearning via Embedding-Corrupted Prompts
Optimal Multi-Fidelity Best-Arm Identification
DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion
GFlowNet Assisted Biological Sequence Editing
SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection
DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators
Active Sequential Posterior Estimation for Sample-Efficient Simulation-Based Inference
Persistent Test-time Adaptation in Recurring Testing Scenarios
Exploiting Descriptive Completeness Prior for Cross Modal Hashing with Incomplete Labels
Metric Flow Matching for Smooth Interpolations on the Data Manifold
AdjointDEIS: Efficient Gradients for Diffusion Models
Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal
Leveraging Drift to Improve Sample Complexity of Variance Exploding Diffusion Models
Neur2BiLO: Neural Bilevel Optimization
Overcoming Brittleness in Pareto-Optimal Learning Augmented Algorithms
Mixture of Experts Meets Prompt-Based Continual Learning
Discovering Preference Optimization Algorithms with and for Large Language Models
Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
Stochastic Optimization Schemes for Performative Prediction with Nonconvex Loss
Confidence Calibration of Classifiers with Many Classes
The Expressive Capacity of State Space Models: A Formal Language Perspective
Who's asking? User personas and the mechanics of latent misalignment
Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning
Representation Noising: A Defence Mechanism Against Harmful Finetuning
Selective Generation for Controllable Language Models
PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
First-Order Methods for Linearly Constrained Bilevel Optimization
Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models
Learning Structure-Aware Representations of Dependent Types
Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy
Robust Graph Neural Networks via Unbiased Aggregation
Hardness of Learning Neural Networks under the Manifold Hypothesis
A Simple and Optimal Approach for Universal Online Learning with Gradient Variations
Geometric Exploitation for Indoor Panoramic Semantic Segmentation
Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient
DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Docking
ReMAP: Neural Model Reprogramming with Network Inversion and Retrieval-Augmented Mapping for Adaptive Motion Forecasting
CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models
Speculative Monte-Carlo Tree Search
Rethinking Imbalance in Image Super-Resolution for Efficient Inference
Back to the Continuous Attractor
PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference
Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation
SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion
LaKD: Length-agnostic Knowledge Distillation for Trajectory Prediction with Any Length Observations
A PID Controller Approach for Adaptive Probability-dependent Gradient Decay in Model Calibration
Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation
Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments
Foundation Inference Models for Markov Jump Processes
A Simple Image Segmentation Framework via In-Context Examples
Functional Bilevel Optimization for Machine Learning
SpeAr: A Spectral Approach for Zero-Shot Node Classification
AutoPSV: Automated Process-Supervised Verifier
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Play
Attack-Resilient Image Watermarking Using Stable Diffusion
Approximately Equivariant Neural Processes
QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation
Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
CountGD: Multi-Modal Open-World Counting
TrAct: Making First-layer Pre-Activations Trainable
Breaking the curse of dimensionality in structured density estimation
Decision-Focused Learning with Directional Gradients
Localized Adaptive Risk Control
Flatten Anything: Unsupervised Neural Surface Parameterization
AutoMix: Automatically Mixing Language Models
Exponential Quantum Communication Advantage in Distributed Inference and Learning
Graph Convolutions Enrich the Self-Attention in Transformers!
The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better
The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations
Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks
LoFiT: Localized Fine-tuning on LLM Representations
Poisson Variational Autoencoder
How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval
OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning
Constrained Diffusion with Trust Sampling
Neural Model Checking
Probabilistic size-and-shape functional mixed models
Contextual Bilevel Reinforcement Learning for Incentive Alignment
Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens
RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier
LeDex: Training LLMs to Better Self-Debug and Explain Code
Online Weighted Paging with Unknown Weights
FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification
Unrolled denoising networks provably learn to perform optimal Bayesian inference
Community Detection Guarantees using Embeddings Learned by Node2Vec
SplitNeRF: Split Sum Approximation Neural Field for Joint Geometry, Illumination, and Material Estimation
Discretely beyond $1/e$: Guided Combinatorial Algortihms for Submodular Maximization
BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models
Generative Forests
Credit Attribution and Stable Compression
Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn
Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming
Optimal Design for Human Preference Elicitation
Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity
Decoupled Kullback-Leibler Divergence Loss
ChatQA: Surpassing GPT-4 on Conversational QA and RAG
Guiding a Diffusion Model with a Bad Version of Itself
DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ
Learning Discrete Concepts in Latent Hierarchical Models
Entropy testing and its application to testing Bayesian networks
VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization
VisMin: Visual Minimal-Change Understanding
NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing
Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps
Streaming Long Video Understanding with Large Language Models
Logical characterizations of recurrent graph neural networks with reals and floats
A Unified Framework for 3D Scene Understanding
Context-Aware Testing: A New Paradigm for Model Testing with Large Language Models
InversionView: A General-Purpose Method for Reading Information from Neural Activations
Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation
On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)
Soft Superpixel Neighborhood Attention
Self-Labeling the Job Shop Scheduling Problem
Revealing Distribution Discrepancy by Sampling Transfer in Unlabeled Data
Multistable Shape from Shading Emerges from Patch Diffusion
Robust Sleep Staging over Incomplete Multimodal Physiological Signals via Contrastive Imagination
An engine not a camera: Measuring performative power of online search
Causal Contrastive Learning for Counterfactual Regression Over Time
VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
BAN: Detecting Backdoors Activated by Neuron Noise
A Non-parametric Direct Learning Approach to Heterogeneous Treatment Effect Estimation under Unmeasured Confounding
Neural Krylov Iteration for Accelerating Linear System Solving
Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation
A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration
Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions
Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control
EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models
Long-range Meta-path Search on Large-scale Heterogeneous Graphs
Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences
IF-Font: Ideographic Description Sequence-Following Font Generation
Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptation
Discovering Creative Behaviors through DUPLEX: Diverse Universal Features for Policy Exploration
Extending Video Masked Autoencoders to 128 frames
Fair Allocation in Dynamic Mechanism Design
FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods
No-Regret Bandit Exploration based on Soft Tree Ensemble Model
Pipeline Parallelism with Controllable Memory
Can neural operators always be continuously discretized?
Aligning LLM Agents by Learning Latent Preference from User Edits
Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance
Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning
On Differentially Private U Statistics
Cell ontology guided transcriptome foundation model
Learning World Models for Unconstrained Goal Navigation
Learning 3D Equivariant Implicit Function with Patch-Level Pose-Invariant Representation
Adaptive Labeling for Efficient Out-of-distribution Model Evaluation
Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood
Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
Improved Regret for Bandit Convex Optimization with Delayed Feedback
Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication
SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data
Understanding Hallucinations in Diffusion Models through Mode Interpolation
Mechanism design augmented with output advice
Enhancing Preference-based Linear Bandits via Human Response Time
The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks
Diffusion PID: Interpreting Diffusion via Partial Information Decomposition
Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient
Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE
Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality
Approximation Rate of the Transformer Architecture for Sequence Modeling
Measuring Goal-Directedness
Prospective Representation Learning for Non-Exemplar Class-Incremental Learning
DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning
Discovering plasticity rules that organize and maintain neural circuits
MemVLT: Vision-Language Tracking with Adaptive Memory-based Prompts
Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees
Cross-Device Collaborative Test-Time Adaptation
DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models
GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent
In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial Trajectories
Practical $0.385$-Approximation for Submodular Maximization Subject to a Cardinality Constraint
MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence
TreeVI: Reparameterizable Tree-structured Variational Inference for Instance-level Correlation Capturing
Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation
Dimension-free Private Mean Estimation for Anisotropic Distributions
Physics-Regularized Multi-Modal Image Assimilation for Brain Tumor Localization
Convergence of $\text{log}(1/\epsilon)$ for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis
Multi-Agent Domain Calibration with a Handful of Offline Data
Is O(log N) practical? Near-Equivalence Between Delay Robustness and Bounded Regret in Bandits and RL
Understanding the Gains from Repeated Self-Distillation
Can Learned Optimization Make Reinforcement Learning Less Difficult?
SPARKLE: A Unified Single-Loop Primal-Dual Framework for Decentralized Bilevel Optimization
Knowledge Circuits in Pretrained Transformers
ReFT: Representation Finetuning for Language Models
Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time
Exploring Token Pruning in Vision State Space Models
Synergistic Dual Spatial-aware Generation of Image-to-text and Text-to-image
SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification
Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments
Using Noise to Infer Aspects of Simplicity Without Learning
Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations
TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy
Capturing the denoising effect of PCA via compression ratio
Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading
IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
DeTrack: In-model Latent Denoising Learning for Visual Object Tracking
A Full-duplex Speech Dialogue Scheme Based On Large Language Model
CriticEval: Evaluating Large-scale Language Model as Critic
TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives
Wasserstein convergence of Cech persistence diagrams for samplings of submanifolds
DiGRAF: Diffeomorphic Graph-Adaptive Activation Function
Latent Diffusion for Neural Spiking Data
NeoRL: Efficient Exploration for Nonepisodic RL
Direct Unlearning Optimization for Robust and Safe Text-to-Image Models
Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)
Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos
Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model
OSLO: One-Shot Label-Only Membership Inference Attacks
FastSurvival: Hidden Computational Blessings in Training Cox Proportional Hazards Models
FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning
The tree autoencoder model, with application to hierarchical data visualization
Discrete-state Continuous-time Diffusion for Graph Generation
Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees
Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models
Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuli
Cross-model Control: Improving Multiple Large Language Models in One-time Training
Transformers Represent Belief State Geometry in their Residual Stream
Conformal Inverse Optimization
MeLLoC: Lossless Compression with High-order Mechanism Learning
Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization
Parameterized Approximation Schemes for Fair-Range Clustering
MotionTTT: 2D Test-Time-Training Motion Estimation for 3D Motion Corrected MRI
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
Evaluating the World Model Implicit in a Generative Model
Acoustic Volume Rendering for Neural Impulse Response Fields
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models
eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling
Multi-Object Hallucination in Vision Language Models
Score-based generative models are provably robust: an uncertainty quantification perspective
Randomized Strategic Facility Location with Predictions
Energy-Guided Continuous Entropic Barycenter Estimation for General Costs
Non-convolutional graph neural networks.
Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
Preference-based Pure Exploration
pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization
Nonparametric Evaluation of Noisy ICA Solutions
Nimbus: Secure and Efficient Two-Party Inference for Transformers
Foundations of Multivariate Distributional Reinforcement Learning
Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data
Efficient Prompt Optimization Through the Lens of Best Arm Identification
Spectral Learning of Shared Dynamics Between Generalized-Linear Processes
GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes
Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in LLMs
The Surprising Effectiveness of SP Voting with Partial Preferences
QWO: Speeding Up Permutation-Based Causal Discovery in LiGAMs
Optimizing the coalition gain in Online Auctions with Greedy Structured Bandits
Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
Visual Prompt Tuning in Null Space for Continual Learning
Robust Reinforcement Learning with General Utility
On the Expressivity and Sample Complexity of Node-Individualized Graph Neural Networks
Prediction-Powered Ranking of Large Language Models
ContactField: Implicit Field Representation for Multi-Person Interaction Geometry
B$\oplus$LD: Boolean Logic Deep Learning
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models
Universal Rates of Empirical Risk Minimization
Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback
Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks
SIRIUS : Contexual Sparisty with Correction for Efficient LLMs
Grammar-Aligned Decoding
Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity
Bias Detection via Signaling
SimPO: Simple Preference Optimization with a Reference-Free Reward
Replicability in Learning: Geometric Partitions and KKM-Sperner Lemma
A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem
Continual Learning in the Frequency Domain
When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models
How does Gradient Descent Learn Features --- A Local Analysis for Regularized Two-Layer Neural Networks
Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts
MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank Experts
RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation
Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex.
Are Large Language Models Good Statisticians?
Indoor Air Quality Dataset with Activities of Daily Living in Low to Middle-income Communities
Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving
Continuous Product Graph Neural Networks
SPO: Sequential Monte Carlo Policy Optimisation
Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin Walk
Why Transformers Need Adam: A Hessian Perspective
Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks
MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encoding
Can Simple Averaging Defeat Modern Watermarks?
DetectEval: Benchmarking LLM-Generated Text Detection in Real-World Scenarios
Invariant subspaces and PCA in nearly matrix multiplication time
CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities
Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis
MathPile: A Billion-Token-Scale Pretraining Corpus for Math
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
BertaQA: How Much Do Language Models Know About Local Culture?
Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning
Streaming Detection of Queried Event Start
Disentangling Linear Quadratic Control with Untrusted ML Predictions
Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithm
Embedding-Aligned Language Models
Safety through feedback in Constrained RL
Estimating Epistemic and Aleatoric Uncertainty with a Single Model
IPO: Interpretable Prompt Optimization for Vision-Language Models
Exploiting Representation Curvature for Boundary Detection in Time Series
Achieving Tractable Minimax Optimal Regret in Average Reward MDPs
Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers
Interpretable Concept-Based Memory Reasoning
Instruction Embedding: Latent Representations of Instructions Towards Task Identification
Adversarially Robust Decision Transformer
MILP-StuDio: MILP Instance Generation via Block Structure Decomposition
Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning
Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation
Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm
Nonparametric Instrumental Variable Regression through Stochastic Approximate Gradients
Critically Assessing the State of the Art in Neural Network Verification
Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
Reproducibility of predictive networks for mouse visual cortex
Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers
What If the Input is Expanded in OOD Detection?
Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics
Gradient Guidance for Diffusion Models: An Optimization Perspective
Conjugate Bayesian Two-step Change Point Detection for Hawkes Process
Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning
Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning
Stepwise Alignment for Constrained Language Model Policy Optimization
Balancing Context Length and Mixing Times for Reinforcement Learning at Scale
SafeWorld: Geo-Diverse Safety Alignment
MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning
PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging
Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations
Fairness-Aware Estimation of Graphical Models
Derivative-enhanced Deep Operator Network
Adaptive Sampling for Efficient Softmax Approximation
Pure Message Passing Can Estimate Common Neighbor for Link Prediction
Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL
MMSite: A Multi-modal Framework for the Identification of Active Sites in Proteins
Prospective Learning: Learning for a Dynamic Future
Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers
The Prevalence of Neural Collapse in Neural Multivariate Regression
Learning to Assist Humans without Inferring Rewards
LoRA-GA: Low-Rank Adaptation with Gradient Approximation
Personalized Federated Learning via Feature Distribution Adaptation
Graph Learning for Numeric Planning
Mixture of Link Predictors on Graphs
No Free Delivery Service: Epistemic limits of passive data collection in complex social systems
Semi-Random Matrix Completion via Flow-Based Adaptive Reweighting
Unraveling the Gradient Descent Dynamics of Transformers
Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents
L4GM: Large 4D Gaussian Reconstruction Model
Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images
Exploring the trade-off between deep-learning and explainable models for brain-machine interfaces
Data Acquisition via Experimental Design for Data Markets
Weak Supervision Performance Evaluation via Partial Identification
Autoregressive Image Generation without Vector Quantization
Learning Better Representations From Less Data For Propositional Satisfiability
BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning
EMVP: Embracing Visual Foundation Model for Visual Place Recognition with Centroid-Free Probing
G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models
QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion
Renovating Names in Open-Vocabulary Segmentation Benchmarks
Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning
End-to-End Ontology Learning with Large Language Models
No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models
ProTransformer: Robustify Transformers via Plug-and-Play Paradigm
Ad Auctions for LLMs via Retrieval Augmented Generation
Improving Environment Novelty Quantification for Effective Unsupervised Environment Design
AverNet: All-in-one Video Restoration for Time-varying Unknown Degradations
State Space Models on Temporal Graphs: A First-Principles Study
Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization
The Value of Reward Lookahead in Reinforcement Learning
Improved learning rates in multi-unit uniform price auctions
Frequency-aware Generative Models for Multivariate Time Series Imputation
Targeted Sequential Indirect Experiment Design
Ordered Momentum for Asynchronous SGD
Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation
Boosted Conformal Prediction Intervals
Inversion-based Latent Bayesian Optimization
In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization
Hyper-opinion Evidential Deep Learning for Out-of-Distribution Detection
A two-scale Complexity Measure for Deep Learning Models
Multi-times Monte Carlo Rendering for Inter-reflection Reconstruction
From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach
B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
Learning from Offline Foundation Features with Tensor Augmentations
Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces
Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis
Spiking Graph Neural Network on Riemannian Manifolds
ImageNet++: A Large-Scale Benchmark of Data Curation Strategies
PRODuctive bandits: Importance Weighting No More
Outlier-Robust Distributionally Robust Optimization via Unbalanced Optimal Transport
Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models
FairWire: Fair Graph Generation
Regression under demographic parity constraints via unlabeled post-processing
TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks
AGILE: A Novel Reinforcement Learning Framework of LLM Agents
Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization
Toward a Well-Calibrated Discrimination via Survival Outcome-Aware Contrastive Learning
D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models
LLM-based Skill Diffusion for Zero-shot Policy Adaptation
Enhancing Graph Transformers with Hierarchical Distance Structural Encoding
Optimal Algorithms for Online Convex Optimization with Adversarial Constraints
DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain
Unveiling The Matthew Effect Across Channels: Assessing Layer Width Sufficiency via Weight Norm Variance
Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection
Trade-Offs of Diagonal Fisher Information Matrix Estimators
CAT3D: Create Anything in 3D with Multi-View Diffusion Models
GACL: Exemplar-Free Generalized Analytic Continual Learning
Confident Natural Policy Gradient for Local Planning in $q_\pi$-realizable Constrained MDPs
CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming
Interventionally Consistent Surrogates for Complex Simulation Models
Variational Flow Matching for Graph Generation
RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models
DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation
Generated and Pseudo Content guided Prototype Refinement for Few-shot Point Cloud Segmentation
Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction
Uncovering Safety Risks of Large Language Models through Concept Activation Vector
Federated Graph Learning for Cross-Domain Recommendation
FEEL-SNN: Robust Spiking Neural Networks with Frequency Encoding and Evolutionary Leak Factor
Randomized Truthful Auctions with Learning Agents
Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models
FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving
Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibration
MetaCURL: Non-stationary Concave Utility Reinforcement Learning
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
Learning Distinguishable Trajectory Representation with Contrastive Loss
Pseudo-Siamese Blind-spot Transformers for Self-Supervised Real-World Denoising
Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting
Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability
MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers
STONE: A Submodular Optimization Framework for Active 3D Object Detection
Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
What makes unlearning hard and what to do about it
Predicting Future Actions of Reinforcement Learning Agents
Simplifying Constraint Inference with Inverse Reinforcement Learning
The ALCHEmist: Automated Labeling 500x CHEaper than LLM Data Annotators
Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation
Learning Goal-Conditioned Representations for Language Reward Models
Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement
Unscrambling disease progression at scale: fast inference of event permutations with optimal transport
Dual Encoder GAN Inversion for High-Fidelity 3D Head Reconstruction from Single Images
UniAR: A Unified model for predicting human Attention and Responses on visual content
Inexact Augmented Lagrangian Methods for Conic Optimization: Quadratic Growth and Linear Convergence
FUGAL: Feature-fortified Unrestricted Graph Alignment
DisC-GS: Discontinuity-aware Gaussian Splatting
On the Identifiability of Hybrid Deep Generative Models: Meta-Learning as a Solution
A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis
ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling
Diffusing Differentiable Representations
Parameter-free Clipped Gradient Descent Meets Polyak
4Diffusion: Multi-view Video Diffusion Model for 4D Generation
Stepping on the Edge: Curvature Aware Learning Rate Tuners
PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyond
Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras
A Closer Look at AUROC and AUPRC under Class Imbalance
DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors
Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning
SSA-Seg: Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentation
Bridging the Divide: Reconsidering Softmax and Linear Attention
CoSW: Conditional Sample Weighting for Smoke Segmentation with Label Noise
Image Understanding Makes for A Good Tokenizer for Image Generation
Gradients of Functions of Large Matrices
What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration
Qualitative Mechanism Independence
Bayes-optimal learning of an extensive-width neural network from quadratically many samples
Parallelizing Model-based Reinforcement Learning Over the Sequence Length
CoSy: Evaluating Textual Explanations of Neurons
Provable Tempered Overfitting of Minimal Nets and Typical Nets
Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
Safe Exploitative Play with Untrusted Type Beliefs
Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
Learning Plaintext-Ciphertext Cryptographic Problems via ANF-based SAT Instance Representation
A Gradient Accumulation Method for Dense Retriever under Memory Constraint
Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models
Monte Carlo Tree Search based Space Transfer for Black Box Optimization
Deep Equilibrium Algorithmic Reasoning
Single Image Reflection Separation via Dual-Stream Interactive Transformers
Information Re-Organization Improves Reasoning in Large Language Models
Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers
Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
Sample Efficient Bayesian Learning of Causal Graphs from Interventions
Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor
Virtual Scanning: Unsupervised Non-line-of-sight Imaging from Irregularly Undersampled Transients
LLMDFA: Analyzing Dataflow in Code with Large Language Models
Generate Universal Adversarial Perturbations for Few-Shot Learning
Iteration Head: A Mechanistic Study of Chain-of-Thought
An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning
Provably Safe Neural Network Controllers via Differential Dynamic Logic
Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
VeXKD: The Versatile Integration of Cross-Modal Fusion and Knowledge Distillation for 3D Perception
Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
Your Diffusion Model is Secretly a Noise Classifier and Benefits from Contrastive Training
Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective
Learning Optimal Tax Design in Nonatomic Congestion Games
GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulation
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory
Coarse-to-Fine Concept Bottleneck Models
Facilitating Multimodal Classification via Dynamically Learning Modality Gap
Leveraging partial stragglers within gradient coding
Data-Efficient Learning with Neural Programs
Trading Place for Space: Increasing Location Resolution Reduces Contextual Capacity in Hippocampal Codes
Selective Attention: Enhancing Transformer through Principled Context Control
TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Models
Artemis: Towards Referential Understanding in Complex Videos
Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach
On the Power of Small-size Graph Neural Networks for Linear Programming
Algebraic Positional Encodings
FashionR2R: Texture-preserving Rendered-to-Real Image Translation with Diffusion Models
Near-Optimality of Contrastive Divergence Algorithms
On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets
AutoManual: Generating Instruction Manuals by LLM Agents via Interactive Environmental Learning
Fundamental Convergence Analysis of Sharpness-Aware Minimization
Extending Multi-modal Contrastive Representations
LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment
Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers
Elo Uncovered: Robustness and Best Practices in Language Model Evaluation
Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition
Continual Audio-Visual Sound Separation
Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding
No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations
Accelerating Transformers with Spectrum-Preserving Token Merging
Transfer Learning for Latent Variable Network Models
SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training
Credal Deep Ensembles for Uncertainty Quantification
Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
QueST: Self-Supervised Skill Abstractions for Learning Continuous Control
DenoiseRep: Denoising Model for Representation Learning
Cost-aware Bayesian Optimization via the Pandora's Box Gittins Index
Questioning the Survey Responses of Large Language Models
Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach
Zero-Shot Transfer of Neural ODEs
Mitigating Spurious Correlations via Disagreement Probability
Amortized Eigendecomposition for Neural Networks
MonkeySee: Space-time-resolved reconstructions of natural images from macaque multi-unit activity
Data Augmentation with Diffusion for Open-Set Semi-Supervised Learning
Stochastic Extragradient with Flip-Flop Shuffling & Anchoring: Provable Improvements
Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning
Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity
Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes
How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?
UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction
When does perceptual alignment benefit vision representations?
Just Add $100 More: Augmenting Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem
MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits
MADiff: Offline Multi-agent Learning with Diffusion Models
Second-order forward-mode optimization of recurrent neural networks for neuroscience
Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference
SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning
Memory-Efficient LLM Training with Online Subspace Descent
Monoculture in Matching Markets
HGDL: Heterogeneous Graph Label Distribution Learning
HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction
CLUES: Collaborative Private-domain High-quality Data Selection for LLMs via Training Dynamics
Ordering-Based Causal Discovery for Linear and Nonlinear Relations
DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning
Suitable is the Best: Task-Oriented Knowledge Fusion in Vulnerability Detection
Barely Random Algorithms and Collective Metrical Task Systems
Graphcode: Learning from multiparameter persistent homology using graph neural networks
No Free Lunch Theorem and Black-Box Complexity Analysis for Adversarial Optimisation
An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval
LoQT: Low-Rank Adapters for Quantized Pretraining
Who’s Gaming the System? A Causally-Motivated Approach for Detecting Strategic Adaptation
3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors
Improved Sample Complexity Bounds for Diffusion Model Training
Multi-Instance Partial-Label Learning with Margin Adjustment
Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation
Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training
On scalable oversight with weak LLMs judging strong LLMs
No-Regret M${}^{\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and NP-Hardness of Adversarial Full-Information Setting
GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting
When is Multicalibration Post-Processing Necessary?
Improved Guarantees for Fully Dynamic $k$-Center Clustering with Outliers in General Metric Spaces
The Impact of Geometric Complexity on Neural Collapse in Transfer Learning
Towards Global Optimal Visual In-Context Learning Prompt Selection
IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering
Quantifying the Gain in Weak-to-Strong Generalization
Why are Visually-Grounded Language Models Bad at Image Classification?
A Concept-Based Explainability Framework for Large Multimodal Models
Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning
A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
Beyond Slow Signs in High-fidelity Model Extraction
Intrinsic Robustness of Prophet Inequality to Strategic Reward Signaling
Covariate Shift Corrected Conditional Randomization Test
ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization
Aligning Diffusion Models by Optimizing Human Utility
Reinforcement Learning with Adaptive Regularization for Safe Control of Critical Systems
Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization
Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data
Approximately Pareto-optimal Solutions for Bi-Objective k-Clustering
Improving robustness to corruptions with multiplicative weight perturbations
Perceptual Fairness in Image Restoration
Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?
Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation
Paths to Equilibrium in Games
Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning
Opponent Modeling based on Subgoal Inference
Tolerant Algorithms for Learning with Arbitrary Covariate Shift
An Improved Empirical Fisher Approximation for Natural Gradient Descent
Decompose, Analyze and Rethink: Solving Intricate Problems with Human-like Reasoning Cycle
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
Why Warmup the Learning Rate? Underlying Mechanisms and Improvements
Meta-Diffu$B$: A Contextualized Sequence-to-Sequence Text Diffusion Model with Meta-Exploration
Dual-Diffusion for Binocular 3D Human Pose Estimation
SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain
Neural Residual Diffusion Models for Deep Scalable Vision Generation
Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking
The Power of Hard Attention Transformers on Data Sequences: A formal language theoretic perspective
Natural Counterfactuals With Necessary Backtracking
AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning
Geometry of naturalistic object representations in recurrent neural network models of working memory
Universality in Transfer Learning for Linear Models
Taming Generative Diffusion Prior for Universal Blind Image Restoration
WildGaussians: 3D Gaussian Splatting In the Wild
Discrete Dictionary-based Decomposition Layer for Structured Representation Learning
Mirror and Preconditioned Gradient Descent in Wasserstein Space
MO-DDN: A Coarse-to-Fine Attribute-based Exploration Agent for Multi-Object Demand-driven Navigation
LRM-Zero: Training Large Reconstruction Models with Synthesized Data
Differential Privacy in Scalable General Kernel Learning via $K$-means Nystr{\"o}m Random Features
Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learning
Online Composite Optimization Between Stochastic and Adversarial Environments
BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
Marrying Causal Representation Learning with Dynamical Systems for Science
Probing Social Bias in Labor Market Text Generation by ChatGPT: A Masked Language Model Approach
Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
How to Boost Any Loss Function
Identifiability Guarantees for Causal Disentanglement from Purely Observational Data
PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning
The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning
Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following
Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation
Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads
Adaptive Depth Networks with Skippable Sub-Paths
Parameter-Inverted Image Pyramid Networks
DEPrune: Depth-wise Separable Convolution Pruning for Maximizing GPU Parallelism
DePLM: Denoising Protein Language Models for Property Optimization
Probabilistic Graph Rewiring via Virtual Nodes
Integrating Suboptimal Human Knowledge with Hierarchical Reinforcement Learning for Large-Scale Multiagent Systems
Towards a theory of how the structure of language is acquired by deep neural networks
Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond
Policy Improvement using Language Feedback Models
Geometric-Averaged Preference Optimization for Soft Preference Labels
Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression
Dealing with Synthetic Data Contamination in Online Continual Learning
Towards Effective Planning Strategies for Dynamic Opinion Networks
Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space
Robot Policy Learning with Temporal Optimal Transport Reward
Pessimistic Backward Policy for GFlowNets
Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning
ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models
How to Solve Contextual Goal-Oriented Problems with Offline Datasets?
Poseidon: Efficient Foundation Models for PDEs
DiffuPac: Contextual Mimicry in Adversarial Packets Generation via Diffusion Model
Deep Homomorphism Networks
TopoFR: A Closer Look at Topology Alignment on Face Recognition
Banded Square Root Matrix Factorization for Differentially Private Model Training
Model-Based Transfer Learning for Contextual Reinforcement Learning
Oracle-Efficient Reinforcement Learning for Max Value Ensembles
SpaceByte: Towards Deleting Tokenization from Large Language Modeling
Image Reconstruction Via Autoencoding Sequential Deep Image Prior
D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models
REDUCR: Robust Data Downsampling using Class Priority Reweighting
Semantic Routing via Autoregressive Modeling
VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
Mutual Information Estimation via Normalizing Flows
Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model
Shape analysis for time series
SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models
Large language model validity via enhanced conformal prediction methods
SimGen: Simulator-conditioned Driving Scene Generation
On the Stability and Generalization of Meta-Learning
Causal Temporal Representation Learning with Nonstationary Sparse Transition
State Chrono Representation for Enhancing Generalization in Reinforcement Learning
Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning
Why the Metric Backbone Preserves Community Structure
Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering
LLM-Check: Investigating Detection of Hallucinations in Large Language Models
Cross-Modality Perturbation Synergy Attack for Person Re-identification
LoCo: Learning 3D Location-Consistent Image Features with a Memory-Efficient Ranking Loss
Adversarial Schrödinger Bridge Matching
CondTSF: One-line Plugin of Dataset Condensation for Time Series Forecasting
Decentralized Noncooperative Games with Coupled Decision-Dependent Distributions
DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge
SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models
An Analytical Study of Utility Functions in Multi-Objective Reinforcement Learning
Online Control with Adversarial Disturbance for Continuous-time Linear Systems
Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
Counterfactual Fairness by Combining Factual and Counterfactual Predictions
SSDM: Scalable Speech Dysfluency Modeling
Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems
The Minimax Rate of HSIC Estimation for Translation-Invariant Kernels
BackTime: Backdoor Attacks on Multivariate Time Series Forecasting
On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models
Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control
Accelerating Blockwise Parallel Language Models with Draft Refinement
Few-Shot Diffusion Models Escape the Curse of Dimensionality
On provable privacy vulnerabilities of graph representations
MAC Advice for facility location mechanism design
Proximal Causal Inference With Text Data
Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale
Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight
Causal Imitation for Markov Decision Processes: a Partial Identification Approach
Progressive Exploration-Conformal Learning for Sparsely Annotated Object Detection in Aerial Images
The Implicit Bias of Gradient Descent on Separable Multiclass Data
LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Control and Rendering
ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field
Information-theoretic Limits of Online Classification with Noisy Labels
Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
ProxyFusion: Face Feature Aggregation Through Sparse Experts
ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings
Randomized Sparse Matrix Compression for Large-Scale Constrained Optimization in Cancer Radiotherapy
Smoke and Mirrors in Causal Downstream Tasks
Dense Connector for MLLMs
Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning
DMesh: A Differentiable Mesh Representation
LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model
DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity
Rethinking Decoders for Transformer-based Semantic Segmentation: Compression is All You Need
FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation
ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model
Mixture of Adversarial LoRAs: Boosting Robust Generalization in Meta-Tuning
Beyond Single Stationary Policies: Meta-Task Players as Naturally Superior Collaborators
Transferring disentangled representations: bridging the gap between synthetic and real images
Initializing Services in Interactive ML Systems for Diverse Users
Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach
ESPACE: Dimensionality Reduction of Activations for Model Compression
Achieving Linear Convergence with Parameter-Free Algorithms in Decentralized Optimization
Ultrafast classical phylogenetic method beats large protein language models on variant effect prediction
ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users
Learning from Snapshots of Discrete and Continuous Data Streams
Skill-aware Mutual Information Optimisation for Zero-shot Generalisation in Reinforcement Learning
Sparse Bayesian Generative Modeling for Compressive Sensing
Abductive Reasoning in Logical Credal Networks
Latent Learning Progress Drives Autonomous Goal Selection in Human Reinforcement Learning
Simulation-Free Training of Neural ODEs on Paired Data
Language Models as Hierarchy Encoders
L-TTA: Lightweight Test-Time Adaptation Using a Versatile Stem Layer
Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation
ARC: A Generalist Graph Anomaly Detector with In-Context Learning
On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization
Putting Gale & Shapley to Work: Guaranteeing Stability Through Learning
Inflationary Flows: Calibrated Bayesian Inference with Diffusion-Based Models
Principled Bayesian Optimization in Collaboration with Human Experts
Full-Atom Peptide Design with Geometric Latent Diffusion
Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network
NVRC: Neural Video Representation Compression
Hierarchical Object-Aware Dual-Level Contrastive Learning for Domain Generalized Stereo Matching
HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data
LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language
MVSDet: Multi-View Indoor 3D Object Detection via Efficient Plane Sweeps
Neuronal Competition Groups with Supervised STDP for Spike-Based Classification
BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction
Relational Concept Bottleneck Models
Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction
Periodic agent-state based Q-learning for POMDPs
Structured flexibility in recurrent neural networks via neuromodulation
Noisy Label Learning with Instance-Dependent Outliers: Identifiability via Crowd Wisdom
Finding good policies in average-reward Markov Decision Processes without prior knowledge
First-Order Minimax Bilevel Optimization
Linguistic Collapse: Neural Collapse in (Large) Language Models
On the Convergence of Loss and Uncertainty-based Active Learning Algorithms
Piecewise deterministic generative models
How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective
Neural Embeddings Rank: Aligning 3D latent dynamics with movements
BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens
Dual Critic Reinforcement Learning under Partial Observability
Sample Selection via Contrastive Fragmentation for Noisy Label Regression
Knowledge Composition using Task Vectors with Learned Anisotropic Scaling
AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment
Learning Image Priors Through Patch-Based Diffusion Models for Solving Inverse Problems
Approximating mutual information of high-dimensional variables using learned representations
Blind Image Restoration via Fast Diffusion Inversion
MiSO: Optimizing brain stimulation to create neural activity states
Rethinking the Capacity of Graph Neural Networks for Branching Strategy
Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity
Robust and Faster Zeroth-Order Minimax Optimization: Complexity and Applications
LLaNA: Large Language and NeRF Assistant
Elliptical Attention
Last-Iterate Convergence for Generalized Frank-Wolfe in Monotone Variational Inequalities
QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation
CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object Detection
Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting
Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions
Efficient Streaming Algorithms for Graphlet Sampling
SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow
RAGraph: A General Retrieval-Augmented Graph Learning Framework
Federated Black-Box Adaptation for Semantic Segmentation
How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad
When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search
The Challenges of the Nonlinear Regime for Physics-Informed Neural Networks
Consistency Diffusion Bridge Models
3D Structure Prediction of Atomic Systems with Flow-based Direct Preference Optimization
Kernel PCA for Out-of-Distribution Detection
Search for Efficient Large Language Models
Data subsampling for Poisson regression with pth-root-link
FM-Delta: Lossless Compression for Storing Massive Fine-tuned Foundation Models
Meta-Learning Universal Priors Using Non-Injective Change of Variables
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
Divergences between Language Models and Human Brains
Is Knowledge Power? On the (Im)possibility of Learning from Strategic Interactions
Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning
Multiple Physics Pretraining for Spatiotemporal Surrogate Models
GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling
FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection
Neural Network Reparametrization for Accelerated Optimization in Molecular Simulations
Identifying Spatio-Temporal Drivers of Extreme Events
Designing Cell-Type-Specific Promoter Sequences Using Conservative Model-Based Optimization
Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers
Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution
Make Continual Learning Stronger via C-Flat
Approaching Human-Level Forecasting with Language Models
MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling
shapiq: Shapley Interactions for Machine Learning
SAM-Guided Masked Token Prediction for 3D Scene Understanding
Unsupervised Hierarchy-Agnostic Segmentation: Parsing Semantic Image Structure
Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images
EASI: Evolutionary Adversarial Simulator Identification for Sim-to-Real Transfer
UniMTS: Unified Pre-training for Motion Time Series
Contextual Decision-Making with Knapsacks Beyond the Worst Case
Policy Learning from Tutorial Books via Understanding, Rehearsing and Introspecting
Conditioning non-linear and infinite-dimensional diffusion processes
Matching the Statistical Query Lower Bound for $k$-Sparse Parity Problems with Sign Stochastic Gradient Descent
On Socially Fair Low-Rank Approximation and Column Subset Selection
Exactly Minimax-Optimal Locally Differentially Private Sampling
FT-AED: Benchmark Dataset for Early Freeway Traffic Anomalous Event Detection
Grokking of Implicit Reasoning in Transformers: A Mechanistic Journey to the Edge of Generalization
Can Large Language Model Agents Simulate Human Trust Behavior?
emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation
Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning
A Metalearned Neural Circuit for Nonparametric Bayesian Inference
Fast Proxy Experiment Design for Causal Effect Identification
Reward Machines for Deep RL in Noisy and Uncertain Environments
Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently
Self-Supervised Adversarial Training via Diverse Augmented Queries and Self-Supervised Double Perturbation
Inferring stochastic low-rank recurrent neural networks from neural data
Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand Avatars
VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought
Stratified Prediction-Powered Inference for Effective Hybrid Evaluation of Language Models
Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem
Are nuclear masks all you need for improved out-of-domain generalisation? A closer look at cancer classification in histopathology
Causal Inference in the Closed-Loop: Marginal Structural Models for Sequential Excursion Effects
InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction
AdanCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer
Locally Private and Robust Multi-Armed Bandits
Model-based Diffusion for Trajectory Optimization
A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention
Efficiently Learning Significant Fourier Feature Pairs for Statistical Independence Testing
Toward Semantic Gaze Target Detection
Generative Fractional Diffusion Models
The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection
Towards Accurate and Fair Cognitive Diagnosis via Monotonic Data Augmentation
DeformableTST: Transformer for Time Series Forecasting without Over-reliance on Patching
Instance-Optimal Private Density Estimation in the Wasserstein Distance
AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields
Learning Identifiable Factorized Causal Representations of Cellular Responses
First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs
SpelsNet: Surface Primitive Elements Segmentation by B-Rep Graph Structure Supervision
Probabilistic Conformal Distillation for Enhancing Missing Modality Robustness
Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations
Optimal Batched Best Arm Identification
xLSTM: Extended Long Short-Term Memory
Semi-Open 3D Object Retrieval via Hierarchical Equilibrium on Hypergraph
UDPM: Upsampling Diffusion Probabilistic Models
Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory
Credal Learning Theory
Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases
DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms
Scaling Law for Time Series Forecasting
Distributional Reinforcement Learning with Regularized Wasserstein Loss
Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces
SceneCraft: Layout-Guided 3D Scene Generation
Cross-Scale Self-Supervised Blind Image Deblurring via Implicit Neural Representation
An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models
Stabilizing Zero-Shot Prediction: A Novel Antidote to Forgetting in Continual Vision-Language Tasks
Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler
SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization
A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization
BERTs are Generative In-Context Learners
Oracle-Efficient Differentially Private Learning with Public Data
Rethinking Fourier Transform from A Basis Functions Perspective for Long-term Time Series Forecasting
Improving Neural ODE Training with Temporal Adaptive Batch Normalization
Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification
Feint Behaviors and Strategies: Formalization, Implementation and Evaluation
Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression
Vector Quantization Prompting for Continual Learning
Testing Semantic Importance via Betting
Linking In-context Learning in Transformers to Human Episodic Memory
Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs
Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization
Unchosen Experts Can Contribute Too: Unleashing MoE Models’ Power by Self-Contrast
FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning
From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
MOTE-NAS: Multi-Objective Training-based Estimate for Efficient Neural Architecture Search
To Believe or Not to Believe Your LLM: IterativePrompting for Estimating Epistemic Uncertainty
SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
SLowcalSGD : Slow Query Points Improve Local-SGD for Stochastic Convex Optimization
DEFT: Efficient Fine-tuning of Diffusion Models by Learning the Generalised $h$-transform
FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification
Disentangling Interpretable Factors with Supervised Independent Subspace Principal Component Analysis
Enhancing Robustness of Last Layer Two-Stage Fair Model Corrections
Coherence-free Entrywise Estimation of Eigenvectors in Low-rank Signal-plus-noise Matrix Models
Addressing Bias in Online Selection with Limited Budget of Comparisons
One Sample Fits All: Approximating All Probabilistic Values Simultaneously and Efficiently
Score-based 3D molecule generation with neural fields
SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
UMB: Understanding Model Behavior for Open-World Object Detection
Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis
Noise-Aware Differentially Private Regression via Meta-Learning
Graph Diffusion Policy Optimization
Efficient Sketches for Training Data Attribution and Studying the Loss Landscape
BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO
Extensive-Form Game Solving via Blackwell Approachability on Treeplexes
Optimal and Approximate Adaptive Stochastic Quantization
Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms
Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level
Saliency-driven Experience Replay for Continual Learning
ReplaceAnything3D: Text-Guided Object Replacement in 3D Scenes with Compositional Scene Representations
Large Language Model Unlearning
Unified Insights: Harnessing Multi-modal Data for Phenotype Imputation via View Decoupling
Benign overfitting in leaky ReLU networks with moderate input dimension
Self-supervised Transformation Learning for Equivariant Representations
Online Posterior Sampling with a Diffusion Prior
Navigable Graphs for High-Dimensional Nearest Neighbor Search: Constructions and Limits
Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels
Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality
Doubly Mild Generalization for Offline Reinforcement Learning
Learning Place Cell Representations and Context-Dependent Remapping
Right this way: Can VLMs Guide Us to See More to Answer Questions?
Is Your LiDAR Placement Optimized for 3D Scene Understanding?
Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation
Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
An Autoencoder-Like Nonnegative Matrix Co-Factorization for Improved Student Cognitive Modeling
Pearls from Pebbles: Improved Confidence Functions for Auto-labeling
IPM-LSTM: A Learning-Based Interior Point Method for Solving Nonlinear Programs
Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation
Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs
Conformalized Multiple Testing after Data-dependent Selection
GO4Align: Group Optimization for Multi-Task Alignment
Improving Neural Network Surface Processing with Principal Curvatures
Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms
Score-Optimal Diffusion Schedules
Schrodinger Bridge Flow for Unpaired Data Translation
Evaluating alignment between humans and neural network representations in image-based learning tasks
Distributional Successor Features Enable Zero-Shot Policy Optimization
Adjust Pearson's $r$ to Measure Arbitrary Monotone Dependence
Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization
Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff
Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning
Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features
Revisiting Ensembling in One-Shot Federated Learning
Progressive Entropic Optimal Transport Solvers
JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images
Towards Harmless Rawlsian Fairness Regardless of Demographic Prior
COLD: Causal reasOning in cLosed Daily activities
Error Correction Output Codes for Robust Neural Networks against Weight-errors: A Neural Tangent Kernel Point of View
Harnessing Multiple Correlated Networks for Exact Community Recovery
Group and Shuffle: Efficient Structured Orthogonal Parametrization
Analytically deriving Partial Information Decomposition for affine systems of stable and convolution-closed distributions
Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning
Temporal-Difference Learning Using Distributed Error Signals
Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition
Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning
Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Controlling Continuous Relaxation for Combinatorial Optimization
Evaluating the design space of diffusion-based generative models
DeltaDEQ: Exploiting Heterogeneous Convergence for Accelerating Deep Equilibrium Iterations
Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformation
Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration
Asynchronous Perception Machine for Efficient Test Time Training
Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
QTIP: Quantization with Trellises and Incoherence Processing
Great Minds Think Alike: The Universal Convergence Trend of Input Salience
ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
An Efficient High-dimensional Gradient Estimator for Stochastic Differential Equations
Sample-Efficient Private Learning of Mixtures of Gaussians
Fast Rates for Bandit PAC Multiclass Classification
Block Transformer: Global-to-Local Language Modeling for Fast Inference
Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs
Understanding the Transferability of Representations via Task-Relatedness
Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games
Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms
Improved Regret of Linear Ensemble Sampling
Fair and Welfare-Efficient Constrained Multi-Matchings under Uncertainty
Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning
Separations in the Representational Capabilities of Transformers and Recurrent Architectures
MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures
SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation
Exploring Molecular Pretraining Model at Scale
Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models
ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models
DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph
Fast Encoder-Based 3D from Casual Videos via Point Track Processing
DiTFastAttn: Attention Compression for Diffusion Transformer Models
SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
Motion Graph Unleashed: A Novel Approach to Video Prediction
Continual Learning with Global Alignment
Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting
Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language Models
Linear Regression using Heterogeneous Data Batches
Score Distillation via Reparametrized DDIM
LLM Evaluators Recognize and Favor Their Own Generations
DataStealing: Steal Data from Diffusion Models in Federated Learning with Multiple Trojans
Adaptive Visual Scene Understanding: Incremental Scene Graph Generation
Robust Neural Contextual Bandit against Adversarial Corruptions
HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning
How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers
Federated Model Heterogeneous Matryoshka Representation Learning
Algorithmic progress in language models
HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis
Categorical Flow Matching on Statistical Manifolds
A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints
Conditional Density Estimation with Histogram Trees
FIDE: Frequency-Inflated Conditional Diffusion Model for Extreme-Aware Time Series Generation
Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
CausalStock: Deep End-to-end Causal Discovery for News-driven Multi-stock Movement Prediction
Iterative Reasoning Preference Optimization
iVideoGPT: Interactive VideoGPTs are Scalable World Models
Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem
Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classification
Treeffuser: probabilistic prediction via conditional diffusions with gradient-boosted trees
Scalable DP-SGD: Shuffling vs. Poisson Subsampling
Learning Macroscopic Dynamics from Partial Microscopic Observations
PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
Minimizing UCB: a Better Local Search Strategy in Local Bayesian Optimization
MeMo: Meaningful, Modular Controllers via Noise Injection
Molecule Generation with Fragment Retrieval Augmentation
Private Edge Density Estimation for Random Graphs: Optimal, Efficient and Robust
Linear Time Approximation Algorithm for Column Subset Selection with Local Search
Transfer Learning for Diffusion Models
Diffusion Imitation from Observation
ROIDICE: Offline Return on Investment Maximization for Efficient Decision Making
LION: Linear Group RNN for 3D Object Detection in Point Clouds
Toxicity Detection for Free
Computerized Adaptive Testing via Collaborative Ranking
Allegator: Alleviating Attention Bias for Visual-Informed Text Generation
Consensus Learning with Deep Sets for Essential Matrix Estimation
Gaussian Process Bandits for Top-k Recommendations
Real-Time Recurrent Learning using Trace Units in Reinforcement Learning
On the Complexity of Teaching a Family of Linear Behavior Cloning Learners
Is Cross-validation the Gold Standard to Estimate Out-of-sample Model Performance?
Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering
Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training
Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention
LaSe-E2V: Towards Language-guided Semantic-aware Event-to-Video Reconstruction
Low Degree Hardness for Broadcasting on Trees
Decoding-Time Language Model Alignment with Multiple Objectives
Learning-Augmented Algorithms for the Bahncard Problem
On the Inductive Bias of Stacking Towards Improving Reasoning
Handling Learnwares from Heterogeneous Feature Spaces with Explicit Label Exploitation
Generative Adversarial Model-Based Optimization via Source Critic Regularization
Flexible Context-Driven Sensory Processing in Dynamical Vision Models
Enhancing Large Language Models through Adaptive Tokenizers
Aggregating Quantitative Relative Judgments: From Social Choice to Ranking Prediction
X-Ray: A Sequential 3D Representation For Generation
BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
Retrieval & Fine-Tuning for In-Context Tabular Models
Instance-adaptive Zero-shot Chain-of-Thought Prompting
RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar
DEL: Discrete Element Learner for Learning 3D Particle Dynamics with Neural Rendering
MambaLRP: Explaining Selective State Space Sequence Models
Adaptive Experimentation When You Can't Experiment
Beyond task diversity: provable representation transfer for sequential multitask linear bandits
Revisiting Score Propagation in Graph Out-of-Distribution Detection
Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images
Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model
Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series
Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights
Temporal Graph Neural Tangent Kernel with Graphon-Guaranteed
Drones Help Drones: A Collaborative Framework for Multi-Drone Object Trajectory Prediction and Beyond
Reparameterization invariance in approximate Bayesian inference
HOPE: Shape Matching Via Aligning Different K-hop Neighbourhoods
MotionBooth: Motion-Aware Customized Text-to-Video Generation
Language-Driven Interactive Traffic Trajectory Generation
Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks
Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf
ActionAtlas: A VideoQA Benchmark for Fine-grained Action Recognition
MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization
An Adaptive Approach for Infinitely Many-armed Bandits under Generalized Rotting Constraints
Multidimensional Fractional Programming for Normalized Cuts
Better by default: Strong pre-tuned MLPs and boosted trees on tabular data
Efficiency of the First-Price Auction in the Autobidding World
How Does Black-Box Impact the Learning Guarantee of Stochastic Compositional Optimization?
Equivariant Neural Diffusion for Molecule Generation
Efficient Multi-task Reinforcement Learning with Cross-Task Policy Guidance
Learning to Decouple the Lights for 3D Face Texture Modeling
SEA: State-Exchange Attention for High-Fidelity Physics Based Transformers
The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning
EGonc : Energy-based Open-Set Node Classification with substitute Unknowns
Faster Local Solvers for Graph Diffusion Equations
Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning
Dendritic Integration Inspired Artificial Neural Networks Capture Data Correlation
Graph Classification via Reference Distribution Learning: Theory and Practice
Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
Evidential Stochastic Differential Equations for Time-Aware Sequential Recommendation
Can Transformers Smell Like Humans?
Externally Valid Policy Evaluation from Randomized Trials Using Additional Observational Data
NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutions
Not Just Object, But State: Compositional Incremental Learning without Forgetting
On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks
NovoBench: Benchmarking Deep Learning-based \emph{De Novo} Sequencing Methods in Proteomics
InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
Subsurface Scattering for Gaussian Splatting
Multi-language Diversity Benefits Autoformalization
Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data
A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement Learning
DECO-Bench: Unified Benchmark for Decoupled Task-Agnostic Synthetic Data Release
Multi-view Masked Contrastive Representation Learning for Endoscopic Video Analysis
RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from Scripts
Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
Trajectory Diffusion for ObjectGoal Navigation
SegVol: Universal and Interactive Volumetric Medical Image Segmentation
3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration
Accelerating Matroid Optimization through Fast Imprecise Oracles
Fair GLASSO: Estimating Fair Graphical Models with Unbiased Statistical Behavior
Tight Bounds for Learning RUMs from Small Slates
DeNetDM: Debiasing by Network Depth Modulation
Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning
Graph Neural Networks and Arithmetic Circuits
IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors
Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning
Quantum algorithm for large-scale market equilibrium computation
A Simple Framework for Generalization in Visual RL under Dynamic Scene Perturbations
Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations
FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
Testing Calibration in Nearly-Linear Time
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving
Data curation via joint example selection further accelerates multimodal learning
A Benchmark Suite for Evaluating Neural Mutual Information Estimators on Unstructured Datasets
$\texttt{ConflictBank}$: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMs
Fit for our purpose, not yours: Benchmark for a low-resource, Indigenous language
4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization
ComBack: A Versatile Dataset for Enhancing Compiler Backend Development Efficiency
Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking
Einsum Benchmark: Enabling the Development of Next-Generation Tensor Execution Engines
Melting Pot Contest: Charting the Future of Generalized Cooperative Intelligence
Benchmarking Out-of-Distribution Generalization and Adaptation for Electromyography
Game-Traversal-Benchmark: Evaluating Planning Abilities Of Large Language Models Via Traversing 2D Game Maps
SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset
Do Multimodal Foundation Models Understand Enterprise Workflows? A Benchmark for Business Process Management Tasks
WhodunitBench: Evaluating Large Multimodal Agents via Murder Mystery Games
EEVR: A Virtual Reality-Based Emotion Dataset Featuring Paired Physiological Signals and Textual Descriptions
Task Me Anything
MMM-RS: A Multi-modal, Multi-GSD, Multi-scene Remote Sensing Dataset and Benchmark for Text-to-Image Generation
A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data
Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming
AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery
Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and Toolbox
VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
UltraMedical: Building Specialized Generalists in Biomedicine
HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations
Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
Localized Zeroth-Order Prompt Optimization
Queueing Matching Bandits with Preference Feedback
Prejudice and Volatility: A Statistical Framework for Measuring Social Discrimination in Large Language Models
GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks
DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model
Topic-Conversation Relevance (TCR) Dataset and Benchmarks
BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack
DevBench: A multimodal developmental benchmark for language learning
DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA
Learning-Augmented Priority Queues
Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?
Maximizing utility in multi-agent environments by anticipating the behavior of other learners
Accelerating Non-Maximum Suppression: A Graph Theory Perspective
The Road Less Scheduled
Test-time Adaptation in Non-stationary Environments via Adaptive Representation Alignment
Promoting Fairness Among Dynamic Agents in Online-Matching Markets under Known Stationary Arrival Distributions
Symmetries in Overparametrized Neural Networks: A Mean Field View
Dense Associative Memory Through the Lens of Random Features
Sketching for Distributed Deep Learning: A Sharper Analysis
RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance
GFT: Graph Foundation Model with Transferable Tree Vocabulary
No-Regret Learning for Fair Multi-Agent Social Welfare Optimization
Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents
Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability, Reproducibility, and Practicality
The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
NN4SysBench: Characterizing Neural Network Verification for Computer Systems
RedCode: Multi-dimensional Safety Benchmark for Code Agents
AgentGym: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents
MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations
IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents
HEST-1k: A Dataset For Spatial Transcriptomics and Histology Image Analysis
Benchmarking Structural Inference Methods for Interacting Dynamical Systems with Synthetic Data
Image Textualization: An Automatic Framework for Generating Rich and Detailed Image Descriptions
Nuclear Fusion Diamond Polishing Dataset
MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack
NYU CTF Dataset: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security
Map It Anywhere: Empowering BEV Map Prediction using Large-scale Public Datasets
APEBench: A Benchmark for Autoregressive Neural Emulators of PDEs
Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays
CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence
II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models
PROSPECT PTMs: Rich Labeled Tandem Mass Spectrometry Dataset of Modified Peptides for Machine Learning in Proteomics
ConceptFactory: Facilitate 3D Object Knowledge Annotation with Object Conceptualization
Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models
A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes
ViLCo-Bench: VIdeo Language COntinual learning Benchmark
A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics
Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets
Advancing Video Anomaly Detection: A Concise Review and a New Dataset
μBench: A Microscopy Benchmark for Vision-Language Understanding
Semi-Truths: A Large-Scale Dataset for Testing Robustness of AI-Generated Image Detectors
Assemblage: Automatic Binary Dataset Construction for Machine Learning
HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning
DivSafe: Evaluating the Generalization of LLM Safety Training Across Diverse Tasks and Prompt Types
OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages
Croissant: A Metadata Format for ML-Ready Datasets
Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation
APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments
WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control
A Benchmark Dataset for Event-Guided Human Pose Estimation and Tracking in Extreme Conditions
Quantifying the Bitter Lesson: How Safety Benchmarks Measure Capabilities Instead of Safety
Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads
Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking
EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries
JaxMARL: Multi-Agent RL Environments and Algorithms in JAX
MultiOrg: A Multi-rater Organoid-detection Dataset
MmCows: A Multimodal Dataset for Dairy Cattle Monitoring
VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks
SolarCube: An Integrative Benchmark Dataset Harnessing Satellite and In-situ Observations for Large-scale Solar Energy Forecasting
Evaluating Numerical Reasoning in Text-to-Image Models
SustainDC: Benchmarking for Sustainable Data Center Control
TAPVid-3D: A Benchmark for Tracking Any Point in 3D
CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset
Multi-Chain Graphs of Graphs: A New Paradigm in Blockchain Dataset
DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents
VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
Norms for Managing Datasets: A Systematic Review of NeurIPS Datasets
WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences
HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
WikiDBs: A Large-Scale Corpus Of Relational Databases From Wikidata
Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control
kGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution
Benchmarking Complex Instruction-Following with Multiple Constraints Composition
ChronoMagic: A Benchmark for Metamorphic Evaluation of Time-lapse Text-to-Video Generation
Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets
SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagery
CryoBench: Datasets and Benchmarks for Heterogeneous Cryo-EM Reconstruction
VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images
BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices
BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages
Archaeoscape: Bringing Aerial Laser Scanning Archaeology to the Deep Learning Era
Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights
HelpSteer 2: Open-source dataset for training top-performing reward models
SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark
DreamCatcher: A Wearer-aware Multi-modal Sleep Event Dataset Based on Earables in Non-restrictive Environments
TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
ReFIR: Grounding Large Restoration Models with Retrieval Augmentation
LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling
WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks
SHDocs: A dataset, benchmark, and method to efficiently generate high-quality, real-world specular highlight data with near-perfect alignment
Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
A Cross-Domain Benchmark for Active Learning
Comprehensive Framework for Curating Speech Datasets and Evaluating ASR Systems: A Case Study for the Polish Language
SCRREAM : SCan, Register, REnder And Map: A Framework for Annotating Accurate and Dense 3D Indoor Scenes with a Benchmark
The State of Data Curation at NeurIPS: An Assessment of Dataset Development Practices in the Datasets and Benchmarks Track
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation
AFBench: A Large-scale Benchmark for Airfoil Design
emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography
Towards Visual Text Design Transfer Across Languages
GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI
When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models
Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation
A Practitioner's Guide to Real-World Continual Multimodal Pretraining
RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation
$\texttt{dattri}$: A Library for Efficient Data Attribution
Off to new Shores: A Dataset & Benchmark for (near-)coastal Flood Inundation Forecasting
OAM-TCD: A globally diverse dataset of high-resolution tree cover maps
Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation
IncomeSCM: From tabular data set to time-series simulator and causal estimation benchmark
GeoLife: Spacial Plant Species Prediction Dataset
DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models
Biomedical Visual Instruction Tuning with Clinician Preference Alignment
HourVideo: 1-Hour Video-Language Understanding
Muscles in Time: Learning to Understand Human Motion In-Depth by Simulating Muscle Activations
CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark
Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models
PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
GV-Rep: A Large-Scale Dataset for Genetic Variant Representation Learning
The Mamba in the Llama: Distilling and Accelerating Hybrid Models
Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias
StreamBench: Towards Benchmarking Continuous Improvement of Language Agents
A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era
LAVIB: A Large-scale Video Interpolation Benchmark
SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding
Through the Looking-Glass: Tracing Shifts in AI Data Consent across the Web
VastTrack: Vast Category Visual Object Tracking
TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs
SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation
The Multimodal Universe: Enabling Large-Scale Machine Learning with 100TBs of Astronomical Scientific Data
Arboretum: A Large Multimodal Dataset Enabling AI for Biodiversity
Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation
What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction
AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries
DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking
PUZZLES: A Benchmark for Neural Algorithmic Reasoning
WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation
FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Models
GAIA: Rethinking Action Quality Assessment for AI-Generated Videos
SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution
Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking
Benchmarking LLMs via Uncertainty Quantification
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions
Gradient Rewiring for Editable Graph Neural Network Training
Noisy Ostracods: A Fine-Grained, Imbalanced Real-World Dataset for Benchmarking Robust Machine Learning and Label Correction Methods
UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training
$\texttt{pfl-research}$: simulation framework for accelerating research in Private Federated Learning
Simple and Effective Masked Diffusion Language Models
CryoSPIN: Improving Ab-Initio Cryo-EM Reconstruction with Semi-Amortized Pose Inference
Proportional Fairness in Clustering: A Social Choice Perspective
Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark
cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Papers
DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation
Infusing Synthetic Data with Real-World Patterns for Zero-Shot Material State Segmentation
TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools
Continuous Temporal Domain Generalization
Intrinsic Self-Supervision for Data Quality Audits
LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low Resource and Extinct Languages
Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content
ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos
OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset
Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge
Benchmarking Estimators for Natural Experiments: A Novel Dataset and a Doubly Robust Algorithm
The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding
Muharaf: Manuscripts of Handwritten Arabic Dataset for Cursive Text Recognition
FindingEmo: An Image Dataset for Emotion Recognition in the Wild
A Synthetic Dataset for Personal Attribute Inference
DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs
Kuro Siwo: 33 billion $m^2$ under the water. A global multi-temporal satellite dataset for rapid flood mapping
Benchmarking Counterfactual Image Generation
Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition
GLBench: A Comprehensive Benchmark for Graph with Large Language Models
The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning
Inference on the Change Point under a High Dimensional Covariance Shift
Optimization-based Causal Estimation from Heterogeneous Environments
Causal Bandits for Linear Structural Equation Models
BenchMARL: Benchmarking Multi-Agent Reinforcement Learning
Pre-trained Gaussian Processes for Bayesian Optimization
Topological Hidden Markov Models
An Analysis of Robustness of Non-Lipschitz Networks
Label Alignment Regularization for Distribution Shift
Metrizing Weak Convergence with Maximum Mean Discrepancies
[Re] GNNInterpreter: A probabilistic generative model-level explanation for Graph Neural Networks
[Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models
Explaining RL Decisions with Trajectories': A Reproducibility Study
Reproducibility Study of "ITI-GEN: Inclusive Text-to-Image Generation"
Reproducibility study of "Robust Fair Clustering: A Novel Fairness Attack and Defense Framework"
[Re] Reproducibility Study of “Explaining Temporal Graph Models Through an Explorer-Navigator Framework"
Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
On the Reproducibility of: "Learning Perturbations to Explain Time Series Predictions"
"Studying How to Efficiently and Effectively Guide Models with Explanations" - A Reproducibility Study
Reproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentations
Coherent 3D Scene Diffusion From a Single RGB Image
Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions
PTQ4DiT: Post-training Quantization for Diffusion Transformers
FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making
FinBen: An Holistic Financial Benchmark for Large Language Models
Layer-Adaptive State Pruning for Deep State Space Models
Linear Uncertainty Quantification of Graphical Model Inference
Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control
Building Timeseries Dataset: Empowering Large-Scale Building Analytics
Images that Sound: Composing Images and Sounds on a Single Canvas
Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learner
EyeGraph: Modularity-aware Spatio Temporal Graph Clustering for Continuous Event-based Eye Tracking
UrbanDataLayer: A Unified Data Pipeline for Urban Science
Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
Learning Distributions on Manifolds with Free-Form Flows
Efficient Adversarial Training in LLMs with Continuous Attacks
How Diffusion Models Learn to Factorize and Compose
Mitigating Biases in Blackbox Feature Extractors for Image Classification Tasks
Vision Foundation Model Enables Generalizable Object Pose Estimation
Understanding Model Selection for Learning in Strategic Environments
Near-Optimal Distributionally Robust Reinforcement Learning with General $L_p$ Norms
A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays
Nearly Minimax Optimal Submodular Maximization with Bandit Feedback
DataComp-LM: In search of the next generation of training sets for language models
Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification
AudioMarkBench: Benchmarking Robustness of Audio Watermarking
Many-shot Jailbreaking
AlphaMath Almost Zero: Process Supervision without Process
FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference
2D-OOB: Attributing Data Contribution Through Joint Valuation Framework
MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
Goal Conditioned Reinforcement Learning for Photo Finishing Tuning
RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-Identification
A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective
HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting
Differentiable Quantum Computing for Large-scale Linear Control
GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
PAC-Bayes-Chernoff bounds for unbounded losses
WenMind: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Classical Literature and Language Arts
Scaling Continuous Latent Variable Models as Probabilistic Integral Circuits
ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation
V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark
CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs
Unsupervised Anomaly Detection Algorithms on Real-world Data: How Many Do We Need?
RETR: Multi-View Radar Detection Transformer for Indoor Perception
WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
Fine Tuning Out-of-Vocabulary Item Recommendation with User Sequence Imagination
What Makes Partial-Label Learning Algorithms Effective?
From Similarity to Superiority: Channel Clustering for Time Series Forecasting
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Unravelling in Collaborative Learning
Federated Learning over Connected Modes
Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting
Binary Search with Distributional Predictions
Active Classification with Few Queries under Misspecification
CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses
SpecExec: Massively Parallel Speculative Decoding For Interactive LLM Inference on Consumer Devices
Zero-Shot Reinforcement Learning from Low Quality Data
Identifiability Analysis of Linear ODE Systems with Hidden Confounders
Causal-learn: Causal Discovery in Python
Neural Collapse Inspired Feature Alignment for Out-of-Distribution Generalization
Improving Deep Learning Optimization through Constrained Parameter Regularization
CODA: A Correlation-Oriented Disentanglement and Augmentation Modeling Scheme for Better Resisting Subpopulation Shifts
ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty
Reinforcement Learning Guided Semi-Supervised Learning
Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
Empowering Active Learning for 3D Molecular Graphs with Geometric Graph Isomorphism
Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models
A probability contrastive learning framework for 3D molecular representation learning
Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning
Schur Nets: exploiting local structure for equivariance in higher order graph neural networks
Is Score Matching Suitable for Estimating Point Processes?
USCILab3D: A Large-scale, Long-term, Semantically Annotated Outdoor Dataset
LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion
Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
Instance-Specific Asymmetric Sensitivity in Differential Privacy
SciCode: A Research Coding Benchmark Curated by Scientists
Sim2Real-Fire: A Multi-modal Simulation Dataset for Forecast and Backtracking of Real-world Forest Fire
Infer Induced Sentiment of Comment Response to Video: A New Task, Dataset and Baseline
Aligner: Efficient Alignment by Learning to Correct
Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^\pi$-Realizability and Concentrability
TaskBench: Benchmarking Large Language Models for Task Automation
An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning
Learning from Noisy Labels via Conditional Distributionally Robust Optimization
OpenCDA-Loop: A Closed-loop Benchmarking Platform for End-to-end Evaluation of Cooperative Perception
Not All Tokens Are What You Need for Pretraining
Reproducibility Study: Equal Improvability: A New Fairness Notion Considering the Long-Term Impact
MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models
Unifying Generation and Prediction on Graphs with Latent Graph Diffusion
Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy
Learning to Understand: Identifying Interactions via the Möbius Transform
Learning Representations for Hierarchies with Minimal Support
DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
Identification and Estimation of the Bi-Directional MR with Some Invalid Instruments
AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
Using Unity to Help Solve Reinforcement Learning
Towards Learning Group-Equivariant Features for Domain Adaptive 3D Detection
WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia
Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting
Provably Efficient Interactive-Grounded Learning with Personalized Reward
The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
Time-Varying LoRA: Towards Effective Cross-Domain Fine-Tuning of Diffusion Models
Humanoid Locomotion as Next Token Prediction
Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time
The Limits of Differential Privacy in Online Learning
Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models
SongCreator: Lyrics-based Universal Song Generation
Chain-of-Thought Unfaithfulness as Disguised Accuracy
Learning Low-Rank Feature for Thorax Disease Classification
Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving
Active Set Ordering
Solving Zero-Sum Markov Games with Continous State via Spectral Dynamic Embedding
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
VideoTetris: Towards Compositional Text-to-Video Generation
LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding
Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare
HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
A StrongREJECT for Empty Jailbreaks
Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random
Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation
Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning
Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance
Can We Leave Deepfake Data Behind in Training Deepfake Detector?
KALM: Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts
Towards Editing Time Series
FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge
Optimal ablation for interpretability
Stochastic Optimal Control and Estimation with Multiplicative and Internal Noise
Label Delay in Online Continual Learning
Scaling White-Box Transformers for Vision
On the Scalability of GNNs for Molecular Graphs
A generalized neural tangent kernel for surrogate gradient learning
Time Makes Space: Emergence of Place Fields in Networks Encoding Temporally Continuous Sensory Experiences
Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis
Only Strict Saddles in the Energy Landscape of Predictive Coding Networks?
UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models
Zipper: Addressing Degeneracy in Algorithm-Agnostic Inference
A Simple yet Universal Framework for Depth Completion
Non-asymptotic Approximation Error Bounds of Parameterized Quantum Circuits
ALPINE: Unveiling The Planning Capability of Autoregressive Learning in Language Models
Improving Temporal Link Prediction via Temporal Walk Matrix Projection
LaSCal: Label-Shift Calibration without target labels
Optical Diffusion Models for Image Generation
Interpretable Mesomorphic Networks for Tabular Data
ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis
Sparse maximal update parameterization: A holistic approach to sparse training dynamics
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Beyond Accuracy: Tracking more like Human via Visual Search
Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models
Enhancing Large Vision Language Models with Self-Training on Image Comprehension
Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning
ReMI: A Dataset for Reasoning with Multiple Images
Pruning neural network models for gene regulatory dynamics using data and domain knowledge
A Theory of Optimistically Universal Online Learnability for General Concept Classes
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
Symbolic Regression with a Learned Concept Library
Learning the Expected Core of Strictly Convex Stochastic Cooperative Games
Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning
Why Go Full? Elevating Federated Learning Through Partial Network Updates
Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains
Automated Efficient Estimation using Monte Carlo Efficient Influence Functions
ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models
Adversarial Moment-Matching Distillation of Large Language Models
A General Protocol to Probe Large Vision Models for 3D Physical Understanding
Seshat Global History Databank Text Dataset and Benchmark of Large Language Models' History Knowledge
Arctique: An artificial histopathological dataset unifying realism and controllability for uncertainty quantification
CiteME: Can Language Models Accurately Cite Scientific Claims?
BeanCounter: A low-toxicity, large-scale, and open dataset of business-oriented text
PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition
ProgressGym: Alignment with a Millennium of Moral Progress
Generic Unsupervised Optimization for a Latent Variable Model With Exponential Family Observables
Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbations
Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
Structured Learning of Compositional Sequential Interventions
Diffusion Actor-Critic with Entropy Regulator
PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation
Learning Diffusion Priors from Observations by Expectation Maximization
Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data
PuLID: Pure and Lightning ID Customization via Contrastive Alignment
On Tractable $\Phi$-Equilibria in Non-Concave Games
Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms
Compact Language Models via Pruning and Knowledge Distillation
Provable Partially Observable Reinforcement Learning with Privileged Information
Neural Combinatorial Optimization for Robust Routing Problem with Uncertain Travel Times
Streaming Bayes GFlowNets
On Divergence Measures for Training GFlowNets
Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
Rethinking Deep Thinking: Stable Learning of Algorithms using Lipschitz Constraints
SubjECTive-QA: A dataset for the subjective evaluation of answers in Earnings Call Transcripts (ECTs)
MSA Generation with Seqs2Seqs Pretraining: Advancing Protein Structure Predictions
Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration
Density-based User Representation using Gaussian Process Regression for Multi-interest Personalized Retrieval
MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities
Limits of Transformer Language Models on Learning to Compose Algorithms
Toward Conditional Distribution Calibration in Survival Prediction
WikiDO: Evaluating Out-of-Distribution Generalization of Vision-Language Models in Cross-Modal Retrieval
Trajectory Flow Matching with Applications to Clinical Time Series Modelling
Improved off-policy training of diffusion samplers
Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization
Fairness-Aware Meta-Learning via Nash Bargaining
FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models
SETBENCH: Assessing the Analytical and Semantic Robustness of Language Models
PowerGraph: A power grid benchmark dataset for graph neural networks
Provably Efficient Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs
SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout
Out-Of-Distribution Detection with Diversification (Provably)
Interpreting Learned Feedback Patterns in Large Language Models
Structured Matrix Basis for Multivariate Time Series Forecasting with Interpretable Dynamics
Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification
RealMAN: A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization
AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks
Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems
PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics
MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
CALVIN: Improved Contextual Video Captioning via Instruction Tuning
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
Fixed points of nonnegative neural networks
EffiBench: Benchmarking the Efficiency of Automatically Generated Code
Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
Transformers Can Do Arithmetic with the Right Embeddings
Bayesian-guided Label Mapping for Visual Reprogramming
Enhancing vision-language models for medical imaging: bridging the 3D gap with innovative slice selection
Preference Alignment with Flow Matching
Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks
EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature
Doubly Hierarchical Geometric Representations for Strand-based Human Hairstyle Generation
Deep Support Vectors
Road Network Representation Learning with the Third Law of Geography
Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
[Re] CUDA: Curriculum of Data Augmentation for Long‐tailed Recognition
Geodesic Optimization for Predictive Shift Adaptation on EEG data
MALT Powers Up Adversarial Attacks
Is Your HD Map Constructor Reliable under Sensor Corruptions?
Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning
Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection
Generative Semi-supervised Graph Anomaly Detection
Unified Guidance for Geometry-Conditioned Molecular Generation
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
Mind the Graph When Balancing Data for Fairness or Robustness
Towards Multi-Domain Learning for Generalizable Video Anomaly Detection
User-Creator Feature Polarization in Recommender Systems with Dual Influence
Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion
Inverse Factorized Soft Q-Learning for Cooperative Multi-agent Imitation Learning
Is Programming by Example solved by LLMs?
Feedback control guides credit assignment in recurrent neural networks
Reinforcement Learning with Lookahead Information
Discovery of the Hidden World with Large Language Models
Adversarially Robust Multi-task Representation Learning
DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control
Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
Transformers are Minimax Optimal Nonparametric In-Context Learners
Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
Drago: Primal-Dual Coupled Variance Reduction for Faster Distributionally Robust Optimization
$\texttt{dopanim}$: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans
ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer
Training Compute-Optimal Protein Language Models
Graph Edit Distance with General Costs Using Neural Set Divergence
TinyLUT: Tiny Look-Up Table for Efficient Image Restoration at the Edge
SEL-BALD: Deep Bayesian Active Learning for Selective Labeling with Instance Rejection
Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness
DeBaRA: Denoising-Based 3D Room Arrangement Generation
How Control Information Influences Multilingual Text Image Generation and Editing?
Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification
Make Your LLM Fully Utilize the Context
Enhancing LLM’s Cognition via Structurization
Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process
LoTLIP: Improving Language-Image Pre-training for Long Text Understanding
Scalable Constrained Policy Optimization for Safe Multi-agent Reinforcement Learning
Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment
SparseLLM: Towards Global Pruning of Pre-trained Language Models
If You Want to Be Robust, Be Wary of Initialization
Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning
Time-Reversal Provides Unsupervised Feedback to LLMs
A hierarchical decomposition for explaining ML performance discrepancies
UGC: Universal Graph Coarsening
Text-Aware Diffusion for Policy Learning
Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
Evaluate calibration of language models with folktexts
Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge
Phased Consistency Models
SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers
A Compositional Atlas for Algebraic Circuits
A Simple yet Scalable Granger Causal Structural Learning Approach for Topological Event Sequences
START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
Practical Bayesian Algorithm Execution via Posterior Sampling
Association Pattern-aware Fusion for Biological Entity Relationship Prediction
Compressing Large Language Models using Low Rank and Low Precision Decomposition
SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet Knowledge
PaCE: Parsimonious Concept Engineering for Large Language Models
Deep Bayesian Active Learning for Preference Modeling in Large Language Models
RMLR: Extending Multinomial Logistic Regression into General Geometries
TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency Models
HydraViT: Stacking Heads for a Scalable ViT
Distributed-Order Fractional Graph Operating Network
Large Language Models Play StarCraft II:Benchmarks and A Chain of Summarization Approach
UQ-Guided Hyperparameter Optimization for Iterative Learners
Multi-Label Open Set Recognition
Solving Minimum-Cost Reach Avoid using Reinforcement Learning
Listenable Maps for Zero-Shot Audio Classifiers
Kermut: Composite kernel regression for protein variant effects
Identifiable Shared Component Analysis of Unpaired Multimodal Mixtures
Variational Distillation of Diffusion Policies into Mixture of Experts
Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch
$C^2M^3$: Cycle-Consistent Multi-Model Merging
Similarity-Navigated Conformal Prediction for Graph Neural Networks
$\textit{Read-ME}$: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
Low-Rank Optimal Transport through Factor Relaxation with Latent Coupling
Understanding Multi-Granularity for Open-Vocabulary Part Segmentation
Continuous Partitioning for Graph-Based Semi-Supervised Learning
Towards Scalable and Stable Parallelization of Nonlinear RNNs
Quasi-Bayes meets Vines
Diffeomorphic interpolation for efficient persistence-based topological optimization
DINTR: Tracking via Diffusion-based Interpolation
Diffusion Twigs with Loop Guidance for Conditional Graph Generation
Differentiable Modal Synthesis for Physical Modeling of Planar String Sound and Motion Simulation
Efficient Leverage Score Sampling for Tensor Train Decomposition
VHELM: A Holistic Evaluation of Vision Language Models
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
Grid4D: 4D Decomposed Hash Encoding for High-fidelity Dynamic Gaussian Splatting
A scalable generative model for dynamical system reconstruction from neuroimaging data
In-Context Symmetries: Self-Supervised Learning through Contextual World Models
AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation
Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes
Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials
Navigating the Effect of Parametrization for Dimensionality Reduction
Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution
Fair Secretaries with Unfair Predictions
Dissecting Query-Key Interaction in Vision Transformers
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shifts
Axioms for AI Alignment from Human Feedback
Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning
Terra: A Multimodal Spatio-Temporal Dataset Spanning the Earth
Extracting Training Data from Molecular Pre-trained Models
LibAMM: Empirical Insights into Approximate Computing for Accelerating Matrix Multiplication
PACE: marrying the generalization of PArameter-efficient fine-tuning with Consistency rEgularization
StepbaQ: Stepping backward as Correction for Quantized Diffusion Models
Splatter a Video: Video Gaussian Representation for Versatile Processing
Towards General Loop Invariant Generation: A Benchmark of Programs with Memory Manipulation
Don't Look Twice: Faster Video Transformers with Run-Length Tokenization
Fairness in Social Influence Maximization via Optimal Transport
ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generation
Differentially Private Graph Diffusion with Applications in Personalized PageRanks
Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniques
CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle Detectors
Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks
ContextGS : Compact 3D Gaussian Splatting with Anchor Level Context Model
Symmetric Linear Bandits with Hidden Symmetry
Unelicitable Backdoors via Cryptographic Transformer Circuits
Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models
OneBit: Towards Extremely Low-bit Large Language Models
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
Contextual Active Model Selection
Normalization and effective learning rates in reinforcement learning
Voila-A: Aligning Vision-Language Models with User's Gaze Attention
DiffHammer: Rethinking the Robustness of Diffusion-Based Adversarial Purification
IaC-Eval: A code generation benchmark for Infrastructure-as-Code programs
Flaws can be Applause: Unleashing Potential of Segmenting Ambiguous Objects in SAM
Minimum Entropy Coupling with Bottleneck
PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models
Linearly Decomposing and Recomposing Vision Transformers for Diverse-Scale Models
Is Function Similarity Over-Engineered? Building a Benchmark
GenRec: Unifying Video Generation and Recognition with Diffusion Models
Multi-modal Situated Reasoning in 3D Scenes
Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models
CARE: a Benchmark Suite for the Classification and Retrieval of Enzymes
Polyhedral Complex Derivation from Piecewise Trilinear Networks
WelQrate: Defining the Gold Standard in Small Molecule Drug Discovery Benchmarking
DF40: Toward Next-Generation Deepfake Detection
Maia-2: A Unified Model for Human-AI Alignment in Chess
GTA: A Benchmark for General Tool Agents
Learning to be Smooth: An End-to-End Differentiable Particle Smoother
I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token
EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes
Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline
Vocal Call Locator Benchmark (VCL'24) for localizing rodent vocalizations from multi-channel audio
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models
Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learner
A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning
REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR
Hierarchical Uncertainty Exploration via Feedforward Posterior Trees
Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms
Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections
Robust Mixture Learning when Outliers Overwhelm Small Groups
Random Representations Outperform Online Continually Learned Representations
Towards the Dynamics of a DNN Learning Symbolic Interactions
Detecting and Measuring Confounding Using Causal Mechanism Shifts
Improving Alignment and Robustness with Circuit Breakers
Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting
Activation Map Compression through Tensor Decomposition for Deep Learning
Zero-Shot Tokenizer Transfer
OTTER: Effortless Label Distribution Adaptation of Zero-shot Models
LACIE: Listener-Aware Finetuning for Calibration in Large Language Models
Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation
Parseval Regularization for Continual Reinforcement Learning
Accuracy is Not All You Need
From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $\alpha$-NeuS
Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
The GAN is dead; long live the GAN! A Modern GAN Baseline
A Fast Convoluted Story: Scaling Probabilistic Inference for Integer Arithmetics
Robustly overfitting latents for flexible neural image compression
Understanding the Role of Equivariance in Self-supervised Learning
Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics
Overcoming Common Flaws in the Evaluation of Selective Classification Systems
Self-Distilled Depth Refinement with Noisy Poisson Fusion
CoIN: A Benchmark of Continual Instruction Tuning for Multimodel Large Language Models
InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos
TrajCLIP: Pedestrian trajectory prediction method using contrastive learning and idempotent networks
Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits
Noise Contrastive Alignment of Language Models with Explicit Rewards
Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features
ImageNet3D: Towards General-Purpose Object-Level 3D Understanding
Proving Olympiad Algebraic Inequalities without Human Demonstrations
$\nabla^2$DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials
NanoBaseLib: A Multi-Task Benchmark Dataset for Nanopore Sequencing
A SARS-CoV-2 Interaction Dataset and VHH Sequence Corpus for Antibody Language Models
Human-level shape inferences: A benchmark for evaluating the 3D understanding of vision models
UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles
EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records
Beyond Aesthetics: Cultural Competence in Text-to-Image Models
Improving Decision Sparsity
Structured Unrestricted-Rank Matrices for Parameter Efficient Finetuning
Can LLMs Solve Molecule Puzzles? A Multimodal Benchmark for Molecular Structure Elucidation
Slot-VLM: Object-Event Slots for Video-Language Modeling
Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
Exclusively Penalized Q-learning for Offline Reinforcement Learning
LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation
Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
From Chaos to Clarity: 3DGS in the Dark
Multimodal Large Language Models Make Text-to-Image Generative Models Align Better
Boosting Text-to-Video Generative Model with MLLMs Feedback
To Err Like Human: Affective Bias-Inspired Measures for Visual Emotion Recognition Evaluation
Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
Mars: Situated Inductive Reasoning in an Open-World Environment
Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset
The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domains
Language Generation in the Limit
Model Collapse Demystified: The Case of Regression
Benchmarking the Attribution Quality of Vision Models
YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals
ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Ablation Capability for Large Vision-Language Models
LucidAction: A Hierarchical and Multi-model Dataset for Comprehensive Action Quality Assessment
StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words
Out-of-Distribution Detection with a Single Unconditional Diffusion Model
Dual-Perspective Activation: Efficient Channel Denoising via Joint Forward-Backward Criterion for Artificial Neural Networks
Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation
GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring
Learning to compute Gröbner bases
Attention boosted Individualized Regression
One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
The Implicit Bias of Adam on Separable Data
On the Comparison between Multi-modal and Single-modal Contrastive Learning
Revisiting Few-Shot Object Detection with Vision-Language Models
Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models
Global Convergence in Training Large-Scale Transformers
Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
Consistency Models for Scalable and Fast Simulation-Based Inference
Understanding Bias in Large-Scale Visual Datasets
HuRef: HUman-REadable Fingerprint for Large Language Models
Nearly Minimax Optimal Regret for Multinomial Logistic Bandit
Octopus: A Multi-modal LLM with Parallel Recognition and Sequential Understanding
Local and Adaptive Mirror Descents in Extensive-Form Games
MedJourney: Benchmark and Evaluation of Large Language Models over Patient Clinical Journey
StackEval: Benchmarking LLMs in Coding Assistance
Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections
A Benchmark Suite for Systematically Evaluating Reasoning Shortcuts
3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition
NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates
CRAG - Comprehensive RAG Benchmark
Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
Lean Workbook: A large-scale Lean problem set formalized from natural language math problems
Mercury: A Code Efficiency Benchmark for Code Large Language Models
RelBench: A Benchmark for Deep Learning on Relational Databases
Benchmark Repositories for Better Benchmarking
WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark
PEACE: A Dataset of Pharmaceutical Care for Cancer Pain Analgesia Evaluation and Medication Decision
EgoSim: An Egocentric Multi-view Simulator for Body-worn Cameras during Human Motion
einspace: Searching for Neural Architectures from Fundamental Operations
HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection
EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs
Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments
LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment
Paloma: A Benchmark for Evaluating Language Model Fit
Conditional Outcome Equivalence: A Quantile Alternative to CATE
Dynamic 3D Gaussian Fields for Urban Areas
A Continuous-time Stochastic Gradient Descent Method for Continuous Data
TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Series
On the Complexity of Identification in Linear Structural Causal Models
Fearless Stochasticity in Expectation Propagation
MassSpecGym: A benchmark for the discovery and identification of molecules
ShopBench: A Massive Multi-Task Online Shopping Benchmark for Large Language Models
Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world Corruptions
Can Large Language Models Analyze Graphs like Professionals? A Benchmark and Dataset
AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making
ReLIZO: Sample Reusable Linear Interpolation-based Zeroth-order Optimization
Stealth edits to large language models
UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-World Document Analysis
CAT: Coordinating Anatomical-Textual Prompts for Multi-Organ and Tumor Segmentation
Nonparametric Regression for 3D Point Cloud Learning
A Novel Benchmark for Decision-Making in Uncertain and Competitive Games
There is No Silver Bullet: Benchmarking Methods in Predictive Combinatorial Optimization
DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
Language Without Borders: A Dataset and Benchmark for Code-Switching Lip Reading
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
GC-Bench: An Open and Unified Benchmark for Graph Condensation
STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning
NeuralPlane: An Efficiently Parallelizable Platform for Fixed-wing Aircraft Control with Reinforcement Learning
SLICE-100K: A Multimodal Dataset for Extrusion-based 3D Printing
ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs
SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
The iNaturalist Sounds Dataset
Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?
PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs
MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
On the Effects of Data Scale on Computer Control Agents
MARPLE: A Benchmark for Long-Horizon Inference
BLURD: Benchmarking and Learning using a Unified Rendering and Diffusion Model
CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes
The Art of Saying No: Contextual Noncompliance in Language Models
Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks
MAN TruckScenes: A multimodal dataset for autonomous trucking in diverse conditions
WindsorML - High-Fidelity Computational Fluid Dynamics Dataset For Automotive Aerodynamics
OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Construction
TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs
Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models
Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models
Efficient Convex Algorithms for Universal Kernel Learning
ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction
Instruction Tuning Large Language Models to Understand Electronic Health Records
CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
Brain Treebank: Large-scale intracranial recordings from naturalistic language stimuli
FlexMol: A Flexible Toolkit for Benchmarking Molecular Relational Learning
Label Noise: Ignorance Is Bliss
ProG: A Graph Prompt Learning Benchmark
Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry
Rad-NeRF: Ray-decoupled Training of Neural Radiance Field
Geometric Analysis of Nonlinear Manifold Clustering
FastDrag: Manipulate Anything in One Step
On the Computational Landscape of Replicable Learning
CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs
M3LEO: A Multi-Modal, Multi-Label Earth Observation Dataset Integrating Interferometric SAR and RGB Data
BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity
GenAI Arena: An Open Evaluation Platform for Generative Models
Cooperative Hardware-Prompt Learning for Snapshot Compressive Imaging
RashomonGB: Analyzing the Rashomon Effect and Mitigating Predictive Multiplicity in Gradient Boosting
A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
Efficient Reinforcement Learning by Discovering Neural Pathways
GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction
MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
Neural Conditional Probability for Uncertainty Quantification
Entrywise error bounds for low-rank approximations of kernel matrices
Learning the Optimal Policy for Balancing Short-Term and Long-Term Rewards
Rethinking No-reference Image Exposure Assessment from Holism to Pixel: Models, Datasets and Benchmarks
Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models
Amortized Bayesian Experimental Design for Decision-Making
PURE: Prompt Evolution with Graph ODE for Out-of-distribution Fluid Dynamics Modeling
Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation
Decoupling Semantic Similarity from Spatial Alignment for Neural Networks.
Fair Wasserstein Coresets
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
Avoiding Undesired Future with Minimal Cost in Non-Stationary Environments
Color-Oriented Redundancy Reduction in Dataset Distillation
Noether's Razor: Learning Conserved Quantities
Policy Aggregation
Binarized Diffusion Model for Image Super-Resolution
APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets
Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
Exogenous Matching: Learning Good Proposals for Tractable Counterfactual Estimation
$SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation
Local Curvature Smoothing with Stein's Identity for Efficient Score Matching
AUC Maximization under Positive Distribution Shift
Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Model
MC-DiT: Contextual Enhancement via Clean-to-Clean Reconstruction for Masked Diffusion Models
Parallelizing Linear Transformers with the Delta Rule over Sequence Length
RobIR: Robust Inverse Rendering for High-Illumination Scenes
RCDN: Towards Robust Camera-Insensitivity Collaborative Perception via Dynamic Feature-based 3D Neural Modeling
On-Road Object Importance Estimation: A New Dataset and A Model with Multi-Fold Top-Down Guidance
Toward Approaches to Scalability in 3D Human Pose Estimation
SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization
Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning
SelfCodeAlign: Self-Alignment for Code Generation
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies
Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization
Med-Real2Sim: Non-Invasive Medical Digital Twins using Physics-Informed Self-Supervised Learning
Trading off Consistency and Dimensionality of Convex Surrogates for Multiclass Classification
A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness
On the Ability of Developers' Training Data Preservation of Learnware
The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks
KFNN: K-Free Nearest Neighbor For Crowdsourcing
Learning Infinitesimal Generators of Continuous Symmetries from Data
Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting
Learning Cortico-Muscular Dependence through Orthonormal Decomposition of Density Ratios
GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting
LiT: Unifying LiDAR "Languages" with LiDAR Translator
Real-Time Selection Under General Constraints via Predictive Inference
Incentivizing Quality Text Generation via Statistical Contracts
Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
CRAYM: Neural Field Optimization via Camera RAY Matching
Communication Efficient Distributed Training with Distributed Lion
Learning Spatially-Aware Language and Audio Embeddings
FactorSim: Generative Simulation via Factorized Representation
Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand
Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective
GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
UltraPixel: Advancing Ultra High-Resolution Image Synthesis to New Peaks
PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition
Homology Consistency Constrained Efficient Tuning for Vision-Language Models
Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis
Unveiling LoRA Intrinsic Ranks via Salience Analysis
AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models
Conformalized Credal Set Predictors
HAWK: Learning to Understand Open-World Video Anomalies
LG-VQ: Language-Guided Codebook Learning
CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework
Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models
GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields
Vision-Language Navigation with Energy-Based Policy
Du-IN: Discrete units-guided mask modeling for decoding speech from Intracranial Neural signals
The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning
BendVLM: Test-Time Debiasing of Vision-Language Embeddings
Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input
AlterMOMA: Fusion Redundancy Pruning for Camera-LiDAR Fusion Models with Alternative Modality Masking
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent
Disentangled Representation Learning in Non-Markovian Causal Systems
Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks
Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based Discrimination
Bayesian Optimization of Functions over Node Subsets in Graphs
Online Convex Optimisation: The Optimal Switching Regret for all Segmentations Simultaneously
Towards Estimating Bounds on the Effect of Policies under Unobserved Confounding
Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization
Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering
Revisiting the Integration of Convolution and Attention for Vision Backbone
Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework
Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions
From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection
EigenVI: score-based variational inference with orthogonal function expansions
Prediction with Action: Visual Policy Learning via Joint Denoising Process
Reimagining Mutual Information for Enhanced Defense against Data Leakage in Collaborative Inference
UPS: Unified Projection Sharing for Lightweight Single-Image Super-resolution and Beyond
Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
Reinforced Cross-Domain Knowledge Distillation on Time Series Data
SyncVIS: Synchronized Video Instance Segmentation
Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss
An Image is Worth 32 Tokens for Reconstruction and Generation
Microstructures and Accuracy of Graph Recall by Large Language Models
SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
What Matters in Graph Class Incremental Learning? An Information Preservation Perspective
DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization
SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models
UQE: A Query Engine for Unstructured Databases
C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory
Multi-LLM Debate: Framework, Principals, and Interventions
Off-Policy Selection for Initiating Human-Centric Experimental Design
Learning-Augmented Dynamic Submodular Maximization
DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model
Synthesize, Partition, then Adapt: Eliciting Diverse Samples from Foundation Models
The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information
Online Estimation via Offline Estimation: An Information-Theoretic Framework
SfPUEL: Shape from Polarization under Unknown Environment Light
OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling
Association of Objects May Engender Stereotypes: Mitigating Association-Engendered Stereotypes in Text-to-Image Generation
MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery
Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers
Boosting the Transferability of Adversarial Attack on Vision Transformer with Adaptive Token Tuning
CultureLLM: Incorporating Cultural Differences into Large Language Models
Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction
Generalizablity of Memorization Neural Network
Understanding Information Storage and Transfer in Multi-Modal Large Language Models
Optimal Parallelization of Boosting
Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator
Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction
DAPE: Data-Adaptive Positional Encoding for Length Extrapolation
Sequoia: Scalable and Robust Speculative Decoding
EM Distillation for One-step Diffusion Models
Loki: Low-rank Keys for Efficient Sparse Attention
Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs
Everyday Object Meets Vision-and-Language Navigation Agent via Backdoor
Learning from Highly Sparse Spatio-temporal Data
Regret Minimization in Stackelberg Games with Side Information
CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models
Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set
Bridging OOD Detection and Generalization: A Graph-Theoretic View
Fast samplers for Inverse Problems in Iterative Refinement models
CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
FactorizePhys: Matrix Factorization for Multidimensional Attention in Remote Physiological Sensing
On Softmax Direct Preference Optimization for Recommendation
Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention
Entity Alignment with Noisy Annotations from Large Language Models
Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
Tighter Convergence Bounds for Shuffled SGD via Primal-Dual Perspective
Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach
Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling
Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases
A Closer Look at the CLS Token for Cross-Domain Few-Shot Learning
Watermarking Makes Language Models Radioactive
Differentially Private Equivalence Testing for Continuous Distributions and Applications
FouRA: Fourier Low-Rank Adaptation
FlexPlanner: Flexible 3D Floorplanning via Deep Reinforcement Learning in Hybrid Action Space with Multi-Modality Representation
N-agent Ad Hoc Teamwork
NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory
Pseudo-Private Data Guided Model Inversion Attacks
Apathetic or Empathetic? Evaluating LLMs' Emotional Alignments with Humans
Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning
Task-Agnostic Machine-Learning-Assisted Inference
Spectral Editing of Activations for Large Language Model Alignment
Wasserstein Distributionally Robust Optimization through the Lens of Structural Causal Models and Individual Fairness
Near-Optimal Distributed Minimax Optimization under the Second-Order Similarity
On Causal Discovery in the Presence of Deterministic Relations
End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning
Causal Dependence Plots
Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
What Variables Affect Out-of-Distribution Generalization in Pretrained Models?
OT4P: Unlocking Effective Orthogonal Group Path for Permutation Relaxation
Learning on Large Graphs using Intersecting Communities
Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints
The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
Infinite Limits of Multi-head Transformer Dynamics
Direct Preference-Based Evolutionary Multi-Objective Optimization with Dueling Bandits
OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries
Shaping the distribution of neural responses with interneurons in a recurrent circuit model
Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction
RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
Recovering Complete Actions for Cross-dataset Skeleton Action Recognition
Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective
Identify Then Recommend: Towards Unsupervised Group Recommendation
Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis
Referencing Where to Focus: Improving Visual Grounding with Referential Query
Weight decay induces low-rank attention layers
Attention Temperature Matters in ViT-Based Cross-Domain Few-Shot Learning
Constrained Sampling with Primal-Dual Langevin Monte Carlo
Is Value Learning Really the Main Bottleneck in Offline RL?
Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models
Membership Inference Attacks against Large Vision-Language Models
Non-Euclidean Mixture Model for Social Network Embedding
ActAnywhere: Subject-Aware Video Background Generation
Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression
Wings: Learning Multimodal LLMs without Text-only Forgetting
NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes
Dual-Personalizing Adapter for Federated Foundation Models
Visual Fourier Prompt Tuning
DistrictNet: Decision-aware learning for geographical districting
Goal-Conditioned On-Policy Reinforcement Learning
On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
On the Power of Decision Trees in Auto-Regressive Language Modeling
Gradient-free Decoder Inversion in Latent Diffusion Models
Calibrated Self-Rewarding Vision Language Models
Active design of two-photon holographic stimulation for identifying neural population dynamics
Shared Autonomy with IDA: Interventional Diffusion Assistance
Few-Shot Adversarial Prompt Learning on Vision-Language Models
MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction
A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
Autonomous Agents for Collaborative Task under Information Asymmetry
DMNet: Self-comparison Driven Model for Subject-independent Seizure Detection
Tight Rates for Bandit Control Beyond Quadratics
Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus
Latent Functional Maps: a spectral framework for representation alignment
ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction
DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models
Quality-Improved and Property-Preserved Polarimetric Imaging via Complementarily Fusing
Long-tailed Object Detection Pretraining: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction
Deep Graph Mating
Scanning Trojaned Models Using Out-of-Distribution Samples
Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection
Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound
UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation
Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models
Shuffling Gradient-Based Methods for Nonconvex-Concave Minimax Optimization
Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift
Model Fusion through Bayesian Optimization in Language Model Fine-Tuning
D2R2: Diffusion-based Representation with Random Distance Matching for Tabular Few-shot Learning
The Selective $G$-Bispectrum and its Inversion: Applications to $G$-Invariant Networks
DisenGCD: A Meta Multigraph-assisted Disentangled Graph Learning Framework for Cognitive Diagnosis
John Ellipsoids via Lazy Updates
QUEST: Quadruple Multimodal Contrastive Learning with Constraints and Self-Penalization
Optimal Flow Matching: Learning Straight Trajectories in Just One Step
Group-wise oracle-efficient algorithms for online multi-group learning
Robust Conformal Prediction Using Privileged Information
Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration
Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner
GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning
Multi-Winner Reconfiguration
General Detection-based Text Line Recognition
Multi-Scale Representation Learning for Protein Fitness Prediction
Pedestrian-Centric 3D Pre-collision Pose and Shape Estimation from Dashcam Perspective
Identifying Latent State-Transition Processes for Individualized Reinforcement Learning
Synthetic Programming Elicitation for Text-to-Code in Very Low-Resource Programming and Formal Languages
This Too Shall Pass: Removing Stale Observations in Dynamic Bayesian Optimization
DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging
Nesterov acceleration despite very noisy gradients
Physically Compatible 3D Object Modeling from a Single Image
Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
Sequential Harmful Shift Detection Without Labels
A Canonicalization Perspective on Invariant and Equivariant Learning
Advection Augmented Convolutional Neural Networks
Unified Graph Augmentations for Generalized Contrastive Learning on Graphs
DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos
High-Resolution Image Harmonization with Adaptive-Interval Color Transformation
Identifying General Mechanism Shifts in Linear Causal Representations
DARNet: Dual Attention Refinement Network with Spatiotemporal Construction for Auditory Attention Detection
The Implicit Bias of Gradient Descent toward Collaboration between Layers: A Dynamic Analysis of Multilayer Perceptions
Physics-informed Neural Networks for Functional Differential Equations: Cylindrical Approximation and Its Convergence Guarantees
An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations
Nonstationary Sparse Spectral Permanental Process
Towards Neuron Attributions in Multi-Modal Large Language Models
Autoregressive Image Diffusion: Generation of Image Sequence and Application in MRI
Con4m: Context-aware Consistency Learning Framework for Segmented Time Series Classification
Query-Based Adversarial Prompt Generation
Instructor-inspired Machine Learning for Robust Molecular Property Prediction
Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities
Public-data Assisted Private Stochastic Optimization: Power and Limitations
Customizing Language Models with Instance-wise LoRA for Sequential Recommendation
DRIP: Unleashing Diffusion Priors for Joint Foreground and Alpha Prediction in Image Matting
Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimization
Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts
Lumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiT
DeepDRK: Deep Dependency Regularized Knockoff for Feature Selection
CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics
Induced Model Matching: Restricted Models Help Train Full-Featured Models
SubgDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning
MaskFactory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation
ProEdit: Simple Progression is All You Need for High-Quality 3D Scene Editing
Scaling Retrieval-Based Language Models with a Trillion-Token Datastore
SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions
PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
Flexible mapping of abstract domains by grid cells via self-supervised extraction and projection of generalized velocity signals
DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection
A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings
Happy: A Debiased Learning Framework for Continual Generalized Category Discovery
Piecewise-Stationary Bandits with Knapsacks
Optimizing Automatic Differentiation with Deep Reinforcement Learning
Autoregressive Policy Optimization for Constrained Allocation Tasks
On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity
DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment
Fixed Confidence Best Arm Identification in the Bayesian Setting
DLAD: Improving Logits-based Detector without Logits from Black-box LLMs
Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling
Detecting Bugs with Substantial Monetary Consequences by LLM and Rule-based Reasoning
Certified Machine Unlearning via Noisy Stochastic Gradient Descent
Action Imitation in Common Action Space for Customized Action Image Synthesis
A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs
The Price of Implicit Bias in Adversarially Robust Generalization
Weak-eval-Strong: Evaluating and Eliciting Lateral Thinking of LLMs with Situation Puzzles
Least Squares Regression Can Exhibit Under-Parameterized Double Descent
Q-VLM: Post-training Quantization for Large Vision-Language Models
KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension
Diversify, Contextualize, and Adapt: Efficient Entropy Modeling for Neural Image Codec
Metric Space Magnitude for Evaluating the Diversity of Latent Representations
Conditional Synthesis of 3D Molecules with Time Correction Sampler
TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight
Towards Unsupervised Model Selection for Domain Adaptive Object Detection
Rough Transformers: Lightweight Continuous-Time Sequence Modelling with Path Signatures
GOMAA-Geo: GOal Modality Agnostic Active Geo-localization
Adaptive Domain Learning for Cross-domain Image Denoising
Fine-Grained Dynamic Framework for Bias-Variance Joint Optimization on Data Missing Not at Random
HyperLogic: Enhancing Diversity and Accuracy in Rule Learning with HyperNets
Approximating the Top Eigenvector in Random Order Streams
Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection
Selective Explanations
Online Learning of Delayed Choices
Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning
GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules
Unlocking the Potential of Global Human Expertise
Bigger, Regularized, Optimistic: scaling for compute and sample efficient continuous control
SpikedAttention: Training-Free and Fully Spike-Driven Transformer-to-SNN Conversion with Winner-Oriented Spike Shift for Softmax Operation
Deep Learning for Computing Convergence Rates of Markov Chains
Theoretical Characterisation of the Gauss Newton Conditioning in Neural Networks
Private Online Learning via Lazy Algorithms
Reconstruct and Match: Out-of-Distribution Robustness via Topological Homogeneity
Long-range Brain Graph Transformer
Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
Graph Neural Networks Need Cluster-Normalize-Activate Modules
DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs
Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
Compositional Generalization Across Distributional Shifts with Sparse Tree Operations
Expected Probabilistic Hierarchies
R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction
AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective
Adaptive Important Region Selection with Reinforced Hierarchical Search for Dense Object Detection
Boundary Decomposition for Nadir Objective Vector Estimation
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
Are We on the Right Way for Evaluating Large Vision-Language Models?
Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models
RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks
KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis
EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views
Active Learning of General Halfspaces: Label Queries vs Membership Queries
Generating Origin-Destination Matrices in Neural Spatial Interaction Models
Frustratingly Easy Test-Time Adaptation of Vision-Language Models
Online Consistency of the Nearest Neighbor Rule
Temporal Sentence Grounding with Relevance Feedback in Videos
StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses
Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis
Transcendence: Generative Models Can Outperform The Experts That Train Them
ColJailBreak: Collaborative Generation and Editing for Jailbreaking Text-to-Image Deep Generation
Unlock the Intermittent Control Ability of Model Free Reinforcement Learning
What Rotary Position Embedding Can Tell Us: Identifying Query and Key Weights Corresponding to Basic Syntactic or High-level Semantic Information
PLIP: Language-Image Pre-training for Person Representation Learning
Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium
Multi-Head Mixture-of-Experts
SkipPredict: When to Invest in Predictions for Scheduling
Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement
What matters when building vision-language models?
Generalization Analysis for Label-Specific Representation Learning
Nature-Inspired Local Propagation
Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning
Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
Molecule Design by Latent Prompt Transformer
Reproducibility Study of "Robust Fair Clustering: A Novel Fairness Attack and Defense Framework"
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
Domain Adaptation for Large-Vocabulary Object Detectors
FUSE: Fast Unified Simulation and Estimation for PDEs
Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes
Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models
Thinking Forward: Memory-Efficient Federated Finetuning of Language Models
UDC: A Unified Neural Divide-and-Conquer Framework for Large-Scale Combinatorial Optimization Problems
ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence
SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead
Knowledge Graph Completion by Intermediate Variables Regularization
An exactly solvable model for emergence and scaling laws in the multitask sparse parity problem
Wasserstein Gradient Boosting: A Framework for Distribution-Valued Supervised Learning
Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
Light Unbalanced Optimal Transport
CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns
Fractal Patterns May Illuminate the Success of Next-Token Prediction
EGSST: Event-based Graph Spatiotemporal Sensitive Transformer for Object Detection
Transformer Doctor: Diagnosing and Treating Vision Transformers
Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning
Are Multiple Instance Learning Algorithms Learnable for Instances?
Distributional regression: CRPS-error bounds for model fitting, model selection and convex aggregation
Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy
One-to-Multiple: A Progressive Style Transfer Unsupervised Domain-Adaptive Framework for Kidney Tumor Segmentation
Boosting Transferability and Discriminability for Time Series Domain Adaptation
ParallelEdits: Efficient Multi-Aspect Text-Driven Image Editing with Attention Grouping
A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch
Efficient $\Phi$-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games
FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Discrepancy-Aware Aggregation
Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data
Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing
Revisiting motion information for RGB-Event tracking with MOT philosophy
Long-Range Feedback Spiking Network Captures Dynamic and Static Representations of the Visual Cortex under Movie Stimuli
Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception
Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Models
Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
OnlineTAS: An Online Baseline for Temporal Action Segmentation
Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps
Optimistic Verifiable Training by Controlling Hardware Nondeterminism
Partially Observable Cost-Aware Active-Learning with Large Language Models
Challenges of Generating Structurally Diverse Graphs
Fast yet Safe: Early-Exiting with Risk Control
SuperVLAD: Compact and Robust Image Descriptors for Visual Place Recognition
The Fairness-Quality Tradeoff in Clustering
InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos
Hybrid Reinforcement Learning Breaks Sample Size Barriers In Linear MDPs
Vivid-ZOO: Multi-View Video Generation with Diffusion Model
Identifying Equivalent Training Dynamics
Towards training digitally-tied analog blocks via hybrid gradient computation
Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
CulturePark: Boosting Cross-cultural Understanding in Large Language Models
Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness
ShowMaker: Creating High-Fidelity 2D Human Video via Fine-Grained Diffusion Modeling
MatrixNet: Learning over symmetry groups using learned group representations
Learning Frequency-Adapted Vision Foundation Model for Domain Generalized Semantic Segmentation
Learning Cut Generating Functions for Integer Programming
VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction
Strategic Linear Contextual Bandits
Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows
Debiasing Synthetic Data Generated by Deep Generative Models
SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection
Mind the Gap: A Causal Perspective on Bias Amplification in Prediction & Decision-Making
CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing
4+3 Phases of Compute-Optimal Neural Scaling Laws
On Feature Learning in Structured State Space Models
In-and-Out: Algorithmic Diffusion for Sampling Convex Bodies
IWBVT: Instance Weighting-based Bias-Variance Trade-off for Crowdsourcing
A Generative Model of Symmetry Transformations
Bandits with Ranking Feedback
Hierarchical Federated Learning with Multi-Timescale Gradient Correction
Geometry-aware training of factorized layers in tensor Tucker format
Learning diverse causally emergent representations from time series data
Amortized Fourier Neural Operators
Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization
Block Sparse Bayesian Learning: A Diversified Scheme
OPUS: Occupancy Prediction Using a Sparse Set
Learn more, but bother less: parameter efficient continual learning
Video Diffusion Models are Training-free Motion Interpreter and Controller
SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection
TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation
Truthful High Dimensional Sparse Linear Regression
Generalizable Implicit Motion Modeling for Video Frame Interpolation
Implicit Regularization Paths of Weighted Neural Representations
$\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$
Recurrent neural network dynamical systems for biological vision
Towards Next-Generation Logic Synthesis: A Scalable Neural Circuit Generation Framework
Zero-shot Generalizable Incremental Learning for Vision-Language Object Detection
Compositional PAC-Bayes: Generalization of GNNs with persistence and beyond
SDformer: Similarity-driven Discrete Transformer For Time Series Generation
Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees
A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative Missingness
Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery
Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
Fine-grained Control of Generative Data Augmentation in IoT Sensing
Unity by Diversity: Improved Representation Learning for Multimodal VAEs
Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling
Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP
Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression
Structural Inference of Dynamical Systems with Conjoined State Space Models
Collaboration! Towards Robust Neural Methods for Routing Problems
Mitigating Partial Observability in Decision Processes via the Lambda Discrepancy
Warm-starting Push-Relabel
SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors
Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing
UNIT: Unifying Image and Text Recognition in One Vision Encoder
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
Interactive Deep Clustering via Value Mining
Reprogramming Pretrained Target-Specific Diffusion Models for Dual-Target Drug Design
Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization
xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology
Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network
Goal Reduction with Loop-Removal Accelerates RL and Models Human Brain Activity in Goal-Directed Learning
TAIA: Large Language Models are Out-of-Distribution Data Learners
Hierarchical Hybrid Sliced Wasserstein: A Scalable Metric for Heterogeneous Joint Distributions
BitDelta: Your Fine-Tune May Only Be Worth One Bit
MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models
Designs for Enabling Collaboration in Human-Machine Teaming via Interactive and Explainable Systems
Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors
E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation
Protein-Nucleic Acid Complex Modeling with Frame Averaging Transformer
Data-Driven Discovery of Dynamical Systems in Pharmacology using Large Language Models
Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
The Collusion of Memory and Nonlinearity in Stochastic Approximation With Constant Stepsize
Fine-Tuning is Fine, if Calibrated
Visual Data Diagnosis and Debiasing with Concept Graphs
Sample Complexity of Interventional Causal Representation Learning
TinyTTA: Efficient Test-time Adaptation via Early-exit Ensembles on Edge Devices
Absorb & Escape: Overcoming Single Model Limitations in Generating Heterogeneous Genomic Sequences
fMRI predictors based on language models of increasing complexity recover brain left lateralization
Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning
FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention
FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference Images
Generalized Protein Pocket Generation with Prior-Informed Flow Matching
Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse Experts
Gliding over the Pareto Front with Uniform Designs
Boosting Graph Pooling with Persistent Homology
Spiking Transformer with Experts Mixture
General Articulated Objects Manipulation in Real Images via Part-Aware Diffusion Process
Query-Efficient Correlation Clustering with Noisy Oracle
A Functional Extension of Semi-Structured Networks
Provable and Efficient Dataset Distillation for Kernel Ridge Regression
Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients
Universal Neural Functionals
Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
Satformer: Accurate and Robust Traffic Data Estimation for Satellite Networks
LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed Problems
A Topology-aware Graph Coarsening Framework for Continual Graph Learning
Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach
Robust Fine-tuning of Zero-shot Models via Variance Reduction
$\textit{Bifr\"ost}$: 3D-Aware Image Compositing with Language Instructions
A Motion-aware Spatio-temporal Graph for Video Salient Object Ranking
NoiseGPT: Label Noise Detection and Rectification through Probability Curvature
MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems
The Bayesian sampling in a canonical recurrent circuit with a diversity of inhibitory interneurons
CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations
Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
Energy-based Hopfield Boosting for Out-of-Distribution Detection
Slight Corruption in Pre-training Data Makes Better Diffusion Models
Hamiltonian Score Matching and Generative Flows
DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach
Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers
Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse
Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels
Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data Coverage
Cost-efficient Knowledge-based Question Answering with Large Language Models
Spectral Adapter: Fine-Tuning in Spectral Space
StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
Cross-modal Representation Flattening for Multi-modal Domain Generalization
A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health
Faster Repeated Evasion Attacks in Tree Ensembles
DreamSteerer: Enhancing Source Image Conditioned Editability using Personalized Diffusion Models
Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model
Cryptographic Hardness of Score Estimation
Rapid Plug-in Defenders
Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics
Distribution-Aware Data Expansion with Diffusion Models
3D Gaussian Splatting as Markov Chain Monte Carlo
An eye for an ear: zero-shot audio description leveraging an image captioner with audio-visual token distribution matching
Neural Cover Selection for Image Steganography
Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning
Mixture of neural fields for heterogeneous reconstruction in cryo-EM
DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers
Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings
MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations
How Do Large Language Models Acquire Factual Knowledge During Pretraining?
What type of inference is planning?
Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning
On the Identifiability of Poisson Branching Structural Causal Model Using Probability Generating Function
SGD vs GD: Rank Deficiency in Linear Networks
One-Step Effective Diffusion Network for Real-World Image Super-Resolution
Markov Equivalence and Consistency in Differentiable Structure Learning
Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection
Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance
Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators
Frequency Adaptive Normalization For Non-stationary Time Series Forecasting
Are Graph Neural Networks Optimal Approximation Algorithms?
Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections
Diffusion-Inspired Truncated Sampler for Text-Video Retrieval
MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their Usability
Unveiling Encoder-Free Vision-Language Models
Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly
Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure
CoBo: Collaborative Learning via Bilevel Optimization
Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling
Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
Bayesian Strategic Classification
LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization
GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation
State-free Reinforcement Learning
TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control
Ensemble sampling for linear bandits: small ensembles suffice
Stabilized Proximal-Point Methods for Federated Optimization
Mixtures of Experts for Audio-Visual Learning
Temporally Consistent Atmospheric Turbulence Mitigation with Neural Representations
Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization
Typicalness-Aware Learning for Failure Detection
Cloud Object Detector Adaptation by Integrating Different Source Knowledge
A versatile informative diffusion model for single-cell ATAC-seq data generation and analysis
Computing the Bias of Constant-step Stochastic Approximation with Markovian Noise
Statistical and Geometrical properties of the Kernel Kullback-Leibler divergence
Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks using the Marginal Likelihood
SymILO: A Symmetry-Aware Learning Framework for Integer Linear Optimization
Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation
QVAE-Mole: The Quantum VAE with Spherical Latent Variable Learning for 3-D Molecule Generation
SCaR: Refining Skill Chaining for Long-Horizon Robotic Manipulation via Dual Regularization
Scaling the Codebook Size of VQ-GAN to 100,000 with a Utilization Rate of 99%
Iteratively Refined Behavior Regularization for Offline Reinforcement Learning
Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification
DDN: Dual-domain Dynamic Normalization for Non-stationary Time Series Forecasting
Collaborative Refining for Learning from Inaccurate Labels
Non-Asymptotic Uncertainty Quantification in High-Dimensional Learning
On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion
Improving Generalization of Dynamic Graph Learning via Environment Prompt
Sample-efficient Bayesian Optimisation Using Known Invariances
Exploitation of a Latent Mechanism in Graph Contrastive Learning: Representation Scattering
Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts
EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection
The motion planning neural circuit in goal-directed navigation as Lie group operator search
Faster Differentially Private Top-$k$ Selection: A Joint Exponential Mechanism with Pruning
Cascade of phase transitions in the training of energy-based models
GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts
Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration Bonus
Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
Toward Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal Consistency
Hybrid Mamba for Few-Shot Segmentation
Grounded Answers for Multi-agent Decision-making Problem through Generative World Model
Rule Based Rewards for Language Model Safety
Graph-based Uncertainty Metrics for Long-form Language Model Generations
Tetrahedron Splatting for 3D Generation
DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Rendering
SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening
WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment
The surprising efficiency of temporal difference learning for rare event prediction
Learning rigid-body simulators over implicit shapes for large-scale scenes and vision
Cross-video Identity Correlating for Person Re-identification Pre-training
Bridge-IF: Learning Inverse Protein Folding with Markov Bridges
Statistical-Computational Trade-offs for Density Estimation
Sharpness-Aware Minimization Activates the Interactive Teaching's Understanding and Optimization
realSEUDO for real-time calcium imaging analysis
Set-based Neural Network Encoding Without Weight Tying
$\text{ID}^3$: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition
PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation
Provable Posterior Sampling with Denoising Oracles via Tilted Transport
On Sampling Strategies for Spectral Model Sharding
What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights
KnowGPT: Knowledge Graph based Prompting for Large Language Models
Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models
SF-V: Single Forward Video Generation Model
Gradient Methods for Online DR-Submodular Maximization with Stochastic Long-Term Constraints
Mutual Information Estimation via $f$-Divergence and Data Derangements
Active preference learning for ordering items in- and out-of-sample
Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss
Towards Efficient and Optimal Covariance-Adaptive Algorithms for Combinatorial Semi-Bandits
Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox
The Reliability of OKRidge Method in Solving Sparse Ridge Regression Problems
Efficient Graph Matching for Correlated Stochastic Block Models
Accelerating Relative Entropy Coding with Space Partitioning
Diffusion Priors for Variational Likelihood Estimation and Image Denoising
A Theoretical Understanding of Self-Correction through In-context Alignment
Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning
On the Computational Complexity of Private High-dimensional Model Selection
Observational Scaling Laws and the Predictability of Langauge Model Performance
Decomposable Transformer Point Processes
ST$_k$: A Scalable Module for Solving Top-k Problems
CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers
Parallel Backpropagation for Shared-Feature Visualization
Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
Identifying Causal Effects Under Functional Dependencies
Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration
Honor Among Bandits: No-Regret Learning for Online Fair Division
Abrupt Learning in Transformers: A Case Study on Matrix Completion
GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning
Reinforcement Learning with Euclidean Data Augmentation for State-Based Continuous Control
Breaking Semantic Artifacts for Generalized AI-generated Image Detection
ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models
What do Graph Neural Networks learn? Insights from Tropical Geometry
Test-Time Dynamic Image Fusion
Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
A Local Method for Satisfying Interventional Fairness with Partially Known Causal Graphs
AID: Attention Interpolation of Text-to-Image Diffusion
Diffusion for World Modeling: Visual Details Matter in Atari
Deep Submodular Peripteral Networks
Harmonizing Stochasticity and Determinism: Scene-responsive Diverse Human Motion Prediction
Smoothed Online Classification can be Harder than Batch Classification
ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation
Time-Constrained Robust MDPs
Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model
Enhancing LLM Reasoning via Vision-Augmented Prompting
UniAudio 1.5: Large Language Model-Driven Audio Codec is A Few-Shot Audio Task Learner
DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection
TFG: Unified Training-Free Guidance for Diffusion Models
Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data
DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut
A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models
OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations
Boosting Weakly Supervised Referring Image Segmentation via Progressive Comprehension
Equivariant spatio-hemispherical networks for diffusion MRI deconvolution
Generating compositional scenes via Text-to-image RGBA Instance Generation
Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
You Only Look Around: Learning Illumination-Invariant Feature for Low-light Object Detection
Implicit Regularization of Decentralized Gradient Descent for Sparse Regression
LG-CAV: Train Any Concept Activation Vector with Language Guidance
On Sparse Canonical Correlation Analysis
SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining
SAND: Smooth imputation of sparse and noisy functional data with Transformer networks
Analysis of Corrected Graph Convolutions
Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual Information Minimization
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization
From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement Learning
A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
Online Classification with Predictions
Scaling Sign Language Translation
Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling
Estimating the Hallucination Rate of Generative AI
A Framework for Bilevel Optimization on Riemannian Manifolds
Demystify Mamba in Vision: A Linear Attention Perspective
Multivariate Probabilistic Time Series Forecasting with Correlated Errors
Enhancing Protein Mutation Effect Prediction through a Retrieval-Augmented Framework
A Kernel Perspective on Distillation-based Collaborative Learning
Continuous Spatiotemporal Events Decoupling through Spike-based Bayesian Computation
Zero-shot Image Editing with Reference Imitation
STL: Still Tricky Logic (for System Validation, Even When Showing Your Work)
Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models
Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
Where does In-context Learning \\ Happen in Large Language Models?
NeuralFluid: Nueral Fluidic System Design and Control with Differentiable Simulation
NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation
Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models
Where's Waldo: Diffusion Features For Personalized Segmentation and Retrieval
Non-geodesically-convex optimization in the Wasserstein space
Partial observation can induce mechanistic mismatches in data-constrained models of neural dynamics
LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning
Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression
Truthfulness of Calibration Measures
Learning to Handle Complex Constraints for Vehicle Routing Problems
Learning to Price Homogeneous Data
PointMamba: A Simple State Space Model for Point Cloud Analysis
Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?
RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health Interventions
Do LLMs Build World Representations? Probing Through the Lens of State Abstraction
BrainBits: How Much of the Brain are Generative Reconstruction Methods Using?
Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learning
Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment
Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise
Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation
FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?
Mind the Gap Between Prototypes and Images in Cross-domain Finetuning
Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models
Binding in hippocampal-entorhinal circuits enables compositionality in cognitive maps
Symmetry-Informed Governing Equation Discovery
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors
Transcoders find interpretable LLM feature circuits
Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators
ChatCam: Empowering Camera Control through Conversational AI
Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization
Real-time Stereo-based 3D Object Detection for Streaming Perception
Contrastive dimension reduction: when and how?
Dynamic Rescaling for Training GNNs
Soft ascent-descent as a stable and flexible alternative to flooding
Probablistic Emulation of a Global Climate Model with Spherical DYffusion
Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks
Predictive Attractor Models
TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression
OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images
Fair Online Bilateral Trade
Rethinking Score Distillation as a Bridge Between Image Distributions
Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective
Towards Understanding Evolving Patterns in Sequential Data
Communication Bounds for the Distributed Experts Problem
Variance estimation in compound decision theory under boundedness
Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection
Efficient Multi-task LLM Quantization and Serving for Multiple LoRA Adapters
Asymptotics of Alpha-Divergence Variational Inference Algorithms with Exponential Families
SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning
Decomposed Prompt Decision Transformer for Efficient Unseen Task Generalization
Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularization
Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting
Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations
Style Adaptation and Uncertainty Estimation for Multi-Source Blended-Target Domain Adaptation
SCOREQ: Speech Quality Assessment with Contrastive Regression
Adaptive Exploration for Data-Efficient General Value Function Evaluations
The Importance of Online Data: Understanding Preference Fine-tuning via Coverage
Animate3D: Animating Any 3D Model with Multi-view Video Diffusion
DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus
Embedding Dimension of Contrastive Learning and $k$-Nearest Neighbors
Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training
Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning
Bayesian Domain Adaptation with Gaussian Mixture Domain-Indexing
SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning
Towards Calibrated Robust Fine-Tuning of Vision-Language Models
What Is Missing For Graph Homophily? Disentangling Graph Homophily For Graph Neural Networks
Omnigrasp: Simulated Humanoid Grasping on Diverse Objects
CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning
A distributional simplicity bias in the learning dynamics of transformers
Instruction Tuning With Loss Over Instructions
Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network
Bridging Gaps: Federated Multi-View Clustering in Heterogeneous Hybrid Views
CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training
Discrete Flow Matching
Pre-training Differentially Private Models with Limited Public Data
Differentially Private Set Representations
Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization
Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization
Consistency of Neural Causal Partial Identification
Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
Where Do Large Learning Rates Lead Us?
Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
Hybrid Generative AI for De Novo Design of Co-Crystals with Enhanced Tabletability
Achievable distributional robustness when the robust risk is only partially identified
Diffusion of Thought: Chain-of-Thought Reasoning in Diffusion Language Models
Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes
The Power of Extrapolation in Federated Learning
Constrained Synthesis with Projected Diffusion Models
Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models.
Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?
Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
Euclidean distance compression via deep random features
A Critical Evaluation of AI Feedback for Aligning Large Language Models
CLIP in Mirror: Disentangling text from visual images through reflection
StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences
AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM
Using Surrogates in Covariate-adjusted Response-adaptive Randomization Experiments with Delayed Outcomes
DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion
Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling
A Walsh Hadamard Derived Linear Vector Symbolic Architecture
Efficient multi-prompt evaluation of LLMs
Learning Group Actions on Latent Representations
AutoSurvey: Large Language Models Can Automatically Write Surveys
DoFIT: Domain-aware Federated Instruction Tuning with Alleviated Catastrophic Forgetting
Dimension-free deterministic equivalents and scaling laws for random feature regression
Newton Informed Neural Operator for Computing Multiple Solutions of Nonlinear Partials Differential Equations
MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning
Towards Exact Gradient-based Training on Analog In-memory Computing
Deep linear networks for regression are implicitly regularized towards flat minima
ZeroMark: Towards Dataset Ownership Verification without Disclosing Watermark
MoEUT: Mixture-of-Experts Universal Transformers
Towards a Scalable Reference-Free Evaluation of Generative Models
Neural decoding from stereotactic EEG: accounting for electrode variability across subjects
Understanding and Improving Training-free Loss-based Diffusion Guidance
Constrained Diffusion Models via Dual Training
Graph Diffusion Transformers for Multi-Conditional Molecular Generation
Diffusion Models With Learned Adaptive Noise
Revisiting K-mer Profile for Effective and Scalable Genome Representation Learning
SE(3)-bi-equivariant Transformers for Point Cloud Assembly
Conformalized Time Series with Semantic Features
Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models
Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective
Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
Predicting Label Distribution from Ternary Labels
On the Parameter Identifiability of Partially Observed Linear Causal Models
Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization
Spectral Graph Pruning Against Over-Squashing and Over-Smoothing
Addressing Spatial-Temporal Heterogeneity: General Mixed Time Series Analysis via Latent Continuity Recovery and Alignment
MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making
MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes
Emergence of heavy tails in homogenized stochastic gradient descent
Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning
The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing
Learning 3D Garment Animation from Trajectories of A Piece of Cloth
An Information Theoretic Perspective on Conformal Prediction
On the Expressive Power of Tree-Structured Probabilistic Circuits
Distributionally Robust Performative Prediction
On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
Rethinking 3D Convolution in $\ell_p$-norm Space
Online Non-convex Learning in Dynamic Environments
Animal-Bench: Benchmarking Multimodal Video Models for Animal-centric Video Understanding
Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers
A Siamese Transformer with Hierarchical Refinement for Lane Detection
Recursive Introspection: Teaching Language Model Agents How to Self-Improve
HORSE: Hierarchical Representation for Large-Scale Neural Subset Selection
Pre-Trained Multi-Goal Transformers with Prompt Optimization for Efficient Online Adaptation
Intervention and Conditioning in Causal Bayesian Networks
Interpreting the Weight Space of Customized Diffusion Models
Segment Any Change
ACFun: Abstract-Concrete Fusion Facial Stylization
Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences
Spike-based Neuromorphic Model for Sound Source Localization
Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition
Fourier-enhanced Implicit Neural Fusion Network for Multispectral and Hyperspectral Image Fusion
Weight for Robustness: A Comprehensive Approach towards Optimal Fault-Tolerant Asynchronous ML
Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learning
LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes
Spiking Neural Network as Adaptive Event Stream Slicer
Ex Uno Pluria: Insights on Ensembling in Low Precision Number Systems
Spatio-Spectral Graph Neural Networks
UV-free Texture Generation with Denoising and Geodesic Heat Diffusion
Infusing Self-Consistency into Density Functional Theory Hamiltonian Prediction via Deep Equilibrium Models
Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks
Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent Coding
Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
HYDRA: Model Factorization Framework for Black-Box LLM Personalization
Mitigating Object Hallucination via Concentric Causal Attention
Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models
Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processes
Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery
Diffusion Spectral Representation for Reinforcement Learning
Convergence of No-Swap-Regret Dynamics in Self-Play
Carrot and Stick: Eliciting Comparison Data and Beyond
Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference
Fully Unconstrained Online Learning
Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding
Contracting with a Learning Agent
CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense
Bias Amplification in Language Model Evolution: An Iterated Learning Perspective
Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning
Online Budgeted Matching with General Bids
SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures
High-dimensional (Group) Adversarial Training in Linear Regression
Scaling Laws in Linear Regression: Compute, Parameters, and Data
Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation
Divide-and-Conquer Posterior Sampling for Denoising Diffusion priors
Sample Complexity of Posted Pricing for a Single Item
Self-Calibrating Conformal Prediction
Self-Guiding Exploration for Combinatorial Problems
Model Sensitivity Aware Continual Learning
Differentiable Structure Learning with Partial Orders
Matryoshka Query Transformer for Large Vision-Language Models
Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate
$\textit{NeuroPath}$: A Neural Pathway Transformer for Joining the Dots of Human Connectomes
MVGamba: Unify 3D Content Generation as State Space Sequence Modeling
Unsupervised Anomaly Detection in The Presence of Missing Values
XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX
$E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset
Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
Expanding Sparse Tuning for Low Memory Usage
Transferable Boltzmann Generators
Causal Context Adjustment Loss for Learned Image Compression
Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
QKFormer: Hierarchical Spiking Transformer using Q-K Attention
GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell Genomics
GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching
Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA
A New Neural Kernel Regime: The Inductive Bias of Multi-Task Learning
CALE: Continuous Arcade Learning Environment
MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset
DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data
QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
Learning Action and Reasoning-Centric Image Editing from Videos and Simulation
Learning to Embed Distributions via Maximum Kernel Entropy
FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection
Online Learning with Sublinear Best-Action Queries
Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion
Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning
Knowledge-Empowered Dynamic Graph Network for Irregularly Sampled Medical Time Series
A Bayesian Approach to Data Point Selection
A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
Coded Computing for Resilient Distributed Computing: A Learning-Theoretic Framework
Vision Mamba Mender
Optimization Algorithm Design via Electric Circuits
FairJob: A Real-World Dataset for Fairness in Online Systems
RandNet-Parareal: a time-parallel PDE solver using Random Neural Networks
Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs
Boosting Alignment for Post-Unlearning Text-to-Image Generative Models
Global Distortions from Local Rewards: Neural Coding Strategies in Path-Integrating Neural Systems
Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers
Evidence of Learned Look-Ahead in a Chess-Playing Neural Network
A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data
Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry
BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping
INQUIRE: A Natural World Text-to-Image Retrieval Benchmark
Provable Benefit of Cutout and CutMix for Feature Learning
FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic Understanding
Learnability of high-dimensional targets by two-parameter models and gradient flow
Empowering and Assessing the Utility of Large Language Models in Crop Science
MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
WeiPer: OOD Detection using Weight Perturbations of Class Projections
Scale Equivariant Graph Metanetworks
SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion
Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials
Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Prediction
FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning
Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention
A Taxonomy of Challenges to Curating Fair Datasets
QUEEN: QUantized Efficient ENcoding for Streaming Free-viewpoint Videos
Achievable Fairness on Your Data With Utility Guarantees
HENASY: Learning to Assemble Scene-Entities for Interpretable Egocentric Video-Language Model
Flipping-based Policy for Chance-Constrained Markov Decision Processes
The Power of Resets in Online Reinforcement Learning
LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single Image
AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos
Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
Retrieval-Retro: Retrieval-based Inorganic Retrosynthesis with Expert Knowledge
DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features
Dissecting the Failure of Invariant Learning on Graphs
Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation
Do's and Don'ts: Learning Desirable Skills with Instruction Videos
Derivatives of Stochastic Gradient Descent in parametric optimization
Codec Avatar Studio: Paired Human Captures for Complete, Driveable, and Generalizable Avatars
You Don’t Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning
RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models
Uncovering the Redundancy in Graph Self-supervised Learning Models
A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers
Error Analysis of Spherically Constrained Least Squares Reformulation in Solving the Stackelberg Prediction Game
4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on RDBs
Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks
Learning with Fitzpatrick Losses
Discrete Modeling via Boundary Conditional Diffusion Processes
MedCalc-Bench: Evaluating Large Language Models for Medical Calculations
Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach
Diffusion Policies Creating a Trust Region for Offline Reinforcement Learning
Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models
Offline Multitask Representation Learning for Reinforcement Learning
DiffGS: Functional Gaussian Splatting Diffusion
Energy-based Epistemic Uncertainty for Graph Neural Networks
Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars
Memorize What Matters: Emergent Scene Decomposition from Multitraverse
Fisher Flow Matching for Generative Modeling over Discrete Data
MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models
Complete Graphical Criterion for Sequential Covariate Adjustment in Causal Inference
DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
Classifier Clustering and Feature Alignment for Federated Learning under Distributed Concept Drift
Confusion-Resistant Federated Learning via Diffusion-Based Data Harmonization on Non-IID Data
Graph neural networks and non-commuting operators
DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation
Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models
The Sample-Communication Complexity Trade-off in Federated Q-Learning
Scale-invariant Optimal Sampling for Rare-events Data and Sparse Models
On the Optimality of Dilated Entropy and Lower Bounds for Online Learning in Extensive-Form Games
Towards Comprehensive Detection of Chinese Harmful Memes: Dataset and Detector
IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation
Open-Book Neural Algorithmic Reasoning
Active Perception for Grasp Detection via Neural Graspness Field
MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting
Policy Optimization for Robust Average Reward MDPs
Learning Discrete Latent Variable Structures with Tensor Rank Conditions
Addressing Hidden Confounding with Heterogeneous Observational Datasets for Recommendation
Noisy Dual Mirror Descent: A Near Optimal Algorithm for Jointly-DP Convex Resource Allocation
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
$\texttt{Model-GLUE}$: Democratized LLM Scaling for A Large Model Zoo in the Wild
ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks
EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding
MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models
Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers
Verifiably Robust Conformal Prediction
Unconditional stability of a recurrent neural circuit implementing divisive normalization
On the Efficiency of ERM in Feature Learning
Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text Prompts
On the Adversarial Robustness of Benjamini Hochberg
Scalable Early Childhood Reading Performance Prediction
Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis
PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
Hypothesis Testing the Circuit Hypothesis in LLMs
Hierarchical and Density-based Causal Clustering
Transfer Q-star : Principled Decoding for LLM Alignment
Private Attribute Inference from Images with Vision-Language Models
e-COP : Episodic Constrained Optimization of Policies
MG-Net: Learn to Customize QAOA with Circuit Depth Awareness
Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning
Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation
Relating Hopfield Networks to Episodic Control
Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution
T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback
Bootstrapping Top-down Information for Self-modulating Slot Attention
Exploring Low-Dimensional Subspace in Diffusion Models for Controllable Image Editing
NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention
LCGen: Mining in Low-Certainty Generation for View-consistent Text-to-3D
Gradient-based Discrete Sampling with Automatic Cyclical Scheduling
Do Finetti: On Causal Effects for Exchangeable Data
ABCFair: an Adaptable Benchmark approach for Comparing Fairness Methods
Alleviate Anchor-Shift: Explore Blind Spots with Cross-View Reconstruction for Incomplete Multi-View Clustering
Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function
Motion Forecasting in Continuous Driving
Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective
HEMM: Holistic Evaluation of Multimodal Foundation Models
ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Driving
DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning
BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning
Resolving Discrepancies in Compute-Optimal Scaling of Language Models
Image2Struct: A Benchmark for Evaluating Vision-Language Models in Extracting Structured Information from Images
Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers
CoLLaM: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models
AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation
A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise
Chain-of-Thought Reasoning Without Prompting
CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making
Dynamic Subgroup Identification in Covariate-adjusted Response-adaptive Randomization Experiments
Disentangled Style Domain for Implicit $z$-Watermark Towards Copyright Protection
The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms
Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codes
OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking
Differentially Private Optimization with Sparse Gradients
AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
WATT: Weight Average Test Time Adaptation of CLIP
IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS
Towards Dynamic Message Passing on Graphs
FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling
Slack-Free Spiking Neural Network Formulation for Hypergraph Minimum Vertex Cover
NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation
COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing
DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain
Boundary Matters: A Bi-Level Active Finetuning Method
MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions
The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space
OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning
Nearly Optimal Approximation of Matrix Functions by the Lanczos Method
Conformal Classification with Equalized Coverage for Adaptively Selected Groups
Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
Multi-Agent Coordination via Multi-Level Communication
$\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning
Distributed Sparse Regression via Penalization
A Unified Recipe for Deriving (Time-Uniform) PAC-Bayes Bounds
Improving the Learning Capability of Small-size Image Restoration Network by Deep Fourier Shifting
Global Rewards in Restless Multi-Armed Bandits
GS-Hider: Hiding Messages into 3D Gaussian Splatting
Numerically Stable Sparse Gaussian Processes via Minimum Separation using Cover Trees
Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding
Theoretical Foundations of Deep Selective State-Space Models
Fourier Neural Operator with Learned Deformations for PDEs on General Geometries
Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
B-ary Tree Push-Pull Method is Provably Efficient for Distributed Learning on Heterogeneous Data
FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation
Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
Optimal Clustering with Bandit Feedback
LLM Circuit Analyses Are Consistent Across Training and Scale
Transfer Learning with Informative Priors: Simple Baselines Better than Previously Reported
Expressive Gaussian Human Avatars from Monocular RGB Video
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
Understanding Emergent Abilities of Language Models from the Loss Perspective
Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual Structures
LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings
How Does Variance Shape the Regret in Contextual Bandits?
Generative Retrieval Meets Multi-Graded Relevance
Bridging semantics and pragmatics in information-theoretic emergent communication
Exploring Fixed Point in Image Editing: Theoretical Support and Convergence Optimization
SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction
Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning
Quantitative Convergences of Lie Group Momentum Optimizers
OneActor: Consistent Subject Generation via Cluster-Conditioned Guidance
Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
Weight Diffusion for Future: Learn to Generalize in Non-Stationary Environments
Aligning Individual and Collective Objectives in Multi-Agent Cooperation
Globally Q-linear Gauss-Newton Method for Overparameterized Non-convex Matrix Sensing
Distributional Preference Alignment of LLMs via Optimal Transport
Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection
Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information
Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective
Can Models Learn Skill Composition from Examples?
Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation
Does Egalitarian Fairness Lead to Instability? The Fairness Bounds in Stable Federated Learning Under Altruistic Behaviors
FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner
Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation
Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes
Wide Two-Layer Networks can Learn from Adversarial Perturbations
Multilingual Diversity Improves Vision-Language Representations
A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embedding
Truth is Universal: Robust Detection of Lies in LLMs
Multiview Scene Graph
FINALLY: fast and universal speech enhancement with studio-like quality
Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation
A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
Unleashing Region Understanding in Intermediate Layers for MLLM-based Referring Expression Generation
Diversity Is Not All You Need: Training A Robust Cooperative Agent Needs Specialist Partners
Enhancing Domain Adaptation through Prompt Gradient Alignment
Data Distribution Valuation
Mixture of Tokens: Continuous MoE through Cross-Example Aggregation
BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models
Confidence Regulation Neurons in Language Models
ProtGO: Function-Guided Protein Modeling for Unified Representation Learning
Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling
Mobility-LLM: Learning Visiting Intentions and Travel Preference from Human Mobility Data with Large Language Models
Learning Complete Protein Representation by Dynamically Coupling of Sequence and Structure
Sourcerer: Sample-based Maximum Entropy Source Distribution Estimation
Fourier Amplitude and Correlation Loss: Beyond Using L2 Loss for Skillful Precipitation Nowcasting
Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
Reliable Learning of Halfspaces under Gaussian Marginals
Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference
Grounding Multimodal Large Language Models in Actions
Improved Analysis for Bandit Learning in Matching Markets
SyncTweedies: A General Generative Framework Based on Synchronized Diffusions
Achieving Constant Regret in Linear Markov Decision Processes
PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection
Seek Commonality but Preserve Differences: Dissected Dynamics Modeling for Multi-modal Visual RL
Causal discovery with endogenous context variables
Exploring Context Window of Large Language Models via Decomposed Positional Vectors
Enhancing Semi-Supervised Learning via Representative and Diverse Sample Selection
Assembly Fuzzy Representation on Hypergraph for Open-Set 3D Object Retrieval
MeshFormer : High-Quality Mesh Generation with 3D-Guided Reconstruction Model
Pard: Permutation-Invariant Autoregressive Diffusion for Graph Generation
Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders
Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient
Unveiling the Bias Impact on Symmetric Moral Consistency of Large Language Models
Going Beyond Heuristics by Imposing Policy Improvement as a Constraint
Mixture of Demonstrations for In-Context Learning
Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate
DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States
Monomial Matrix Group Equivariant Neural Functional Networks
No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
Integrating GNN and Neural ODEs for Estimating Non-Reciprocal Two-Body Interactions in Mixed-Species Collective Motion
IODA: Instance-Guided One-shot Domain Adaptation for Super-Resolution
Uncertainty-aware Fine-tuning of Segmentation Foundation Models
Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers
SnapKV: LLM Knows What You are Looking for Before Generation
E-Motion: Future Motion Simulation via Event Sequence Diffusion
Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs
Masked Pre-training Enables Universal Zero-shot Denoiser
Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data
CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions
Cascade Speculative Drafting for Even Faster LLM Inference
EMR-Merging: Tuning-Free High-Performance Model Merging
BMRS: Bayesian Model Reduction for Structured Pruning
Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
Data-faithful Feature Attribution: Mitigating Unobservable Confounders via Instrumental Variables
Reinforcement Learning with LTL and $\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards
Fast and Memory-Efficient Video Diffusion Using Streamlined Inference
Precipitation Downscaling with Spatiotemporal Video Diffusion
TPC: Test-time Procrustes Calibration for Diffusion-based Human Image Animation
DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction
Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking
Dual Lagrangian Learning for Conic Optimization
Pandora's Box: Towards Building Universal Attackers against Real-World Large Vision-Language Models
Learning predictable and robust neural representations by straightening image sequences
MKGL: Mastery of a Three-Word Language
Adversarial Environment Design via Regret-Guided Diffusion Models
Transition Constrained Bayesian Optimization via Markov Decision Processes
Scalable DBSCAN with Random Projections
How do Large Language Models Handle Multilingualism?
DeiSAM: Segment Anything with Deictic Prompting
Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift
Opponent Modeling with In-context Search
Reconstruction of Manipulated Garment with Guided Deformation Prior
How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach
CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos
A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective
User-item fairness tradeoffs in recommendations
Optimal Top-Two Method for Best Arm Identification and Fluid Analysis
Transductive Learning is Compact
Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method
Large Scale Transfer Learning for Tabular Data via Language Modeling
Understanding Transformers via N-Gram Statistics
MambaTree: Tree Topology is All You Need in State Space Model
Relational Verification Leaps Forward with RABBit
Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion models
Continual Counting with Gradual Privacy Expiration
Dynamic Service Fee Pricing under Strategic Behavior: Actions as Instruments and Phase Transition
On the Scalability of Certified Adversarial Robustness with Generated Data
Robust group and simultaneous inferences for high-dimensional single index model
Universal Rates for Active Learning
U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models
Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction
EEG2Video: Towards Decoding Dynamic Visual Perception from EEG Signals
Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques
Learning and Transferring Sparse Contextual Bigrams with Linear Transformers
DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices
Resource-Aware Federated Self-Supervised Learning with Global Class Representations
Local to Global: Learning Dynamics and Effect of Initialization for Transformers
M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation
VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
Text to Blind Motion
Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance
Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach
The Secretary Problem with Predicted Additive Gap
Risk-sensitive control as inference with Rényi divergence
GUIDE: Real-Time Human-Shaped Agents
Rejection via Learning Density Ratios
Provable Editing of Deep Neural Networks using Parametric Linear Relaxation
Tackling Uncertain Correspondences for Multi-Modal Entity Alignment
An effective framework for estimating individualized treatment rules
Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models
Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers
Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain
On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift
Tensor-Based Synchronization and the Low-Rankness of the Block Trifocal Tensor
Effective Exploration Based on the Structural Information Principles
Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling
2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
Learning Transferable Features for Implicit Neural Representations
Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
Off-policy estimation with adaptively collected data: the power of online learning
Fast Channel Simulation via Error-Correcting Codes
Performative Control for Linear Dynamical Systems
Factorized Diffusion Architectures for Unsupervised Image Generation and Segmentation
CLIPAway: Harmonizing focused embeddings for removing objects via diffusion models
Supervised Kernel Thinning
AED: Adaptable Error Detection for Few-shot Imitation Policy
TARSS-Net: Temporal-Aware Radar Semantic Segmentation Network
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
Active, anytime-valid risk controlling prediction sets
ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
SA3DIP: Segment Any 3D Instance with Potential 3D Priors
Compact Proofs of Model Performance via Mechanistic Interpretability
When Is Inductive Inference Possible?
Sample-Efficient Constrained Reinforcement Learning with General Parameterization
Private and Personalized Frequency Estimation in a Federated Setting
Probing the Decision Boundaries of In-context Learning in Large Language Models
Scaling transformer neural networks for skillful and reliable medium-range weather forecasting
Multi-scale Consistency for Robust 3D Registration via Hierarchical Sinkhorn Tree
When is an Embedding Model More Promising than Another?
Training for Stable Explanation for Free
RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models
Stochastic Concept Bottleneck Models
Idiographic Personality Gaussian Process for Psychological Assessment
PERIA: Perceive, Reason, Imagine, Act via Holistic Language and Vision Planning for Manipulation
G2D: From Global to Dense Radiography Representation Learning via Vision-Language Pre-training
Enhancing Robustness of Graph Neural Networks on Social Media with Explainable Inverse Reinforcement Learning
GenRL: Multimodal-foundation world models for generalization in embodied agents
InstructG2I: Synthesizing Images from Multimodal Attributed Graphs
Neural Gaffer: Relighting Any Object via Diffusion
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders
Marginal Causal Flows for Validation and Inference
Slicing Vision Transformer for Flexibile Inference
REBEL: Reinforcement Learning via Regressing Relative Rewards
Towards Flexible 3D Perception: Object-Centric Occupancy Completion Augments 3D Object Detection
Optimal Algorithms for Learning Partitions with Faulty Oracles
Large Spatial Model: End-to-end Unposed Images to Semantic 3D
Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking
Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations
Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes
Safe Time-Varying Optimization based on Gaussian Processes with Spatio-Temporal Kernel
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping
Towards Human-AI Complementarity with Prediction Sets
Evaluate then Cooperate: Shapley-based View Cooperation Enhancement for Multi-view Clustering
DDK: Distilling Domain Knowledge for Efficient Large Language Models
Causal vs. Anticausal merging of predictors
On $f$-Divergence Principled Domain Adaptation: An Improved Framework
Infinite-Dimensional Feature Interaction
Multi-Reward Best Policy Identification
DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation
Efficient LLM Scheduling by Learning to Rank
TSDS: Data Selection for Task-Specific Model Finetuning
Reflective Multi-Agent Collaboration based on Large Language Models
Unified Generative and Discriminative Training for Multi-modal Large Language Models
Improving Subgroup Robustness via Data Selection
LOVA3: Learning to Visual Question Answering, Asking and Assessment
Skinned Motion Retargeting with Dense Geometric Interaction Perception
FilterNet: Harnessing Frequency Filters for Time Series Forecasting
Calibrating Reasoning in Language Models with Internal Consistency
MoVA: Adapting Mixture of Vision Experts to Multimodal Context
DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation
Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs
Enriching Disentanglement: From Logical Definitions to Quantitative Metrics
Leveraging Tumor Heterogeneity: Heterogeneous Graph Representation Learning for Cancer Survival Prediction in Whole Slide Images
TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration
When to Act and When to Ask: Policy Learning With Deferral Under Hidden Confounding
Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks
One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection
Physics-Informed Variational State-Space Gaussian Processes
Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers
UniFL: Improve Latent Diffusion Model via Unified Feedback Learning
DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization
Semi-supervised Knowledge Transfer Across Multi-omic Single-cell Data
Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies
Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games
Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models
Aligning to Thousands of Preferences via System Message Generalization
F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning
Neural Persistence Dynamics
RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation
AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
Prune and Repaint: Content-Aware Image Retargeting for any Ratio
Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting
Hallo3D: Multi-Modal Hallucination Detection and Mitigation for Consistent 3D Content Generation
Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning
Unleashing Multispectral Video's Potential in Semantic Segmentation: A Semi-supervised Viewpoint and New UAV-View Benchmark
$\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation
From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos
Generalization Bounds via Conditional $f$-Information
BiDM: Pushing the Limit of Quantization for Diffusion Models
Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks
Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs
Toward Real Ultra Image Segmentation: Leveraging Surrounding Context to Cultivate General Segmentation Model
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs
Yo'LLaVA: Your Personalized Language and Vision Assistant
RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space
Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension
S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity
Quadratic Quantum Variational Monte Carlo
TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation
Parameter Competition Balancing for Model Merging
Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy
Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation
Data Attribution for Text-to-Image Models by Unlearning Synthesized Images
Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe
ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models
Neural Isometries: Taming Transformations for Equivariant ML
EGODE: An Event-attended Graph ODE Framework for Modeling Rigid Dynamics
LocCa: Visual Pretraining with Location-aware Captioners
COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation
Soft-Label Integration for Robust Toxicity Classification
Sm: enhanced localization in Multiple Instance Learning for medical imaging classification
Constant Acceleration Flow
GraphVis: Boosting LLMs with Visual Knowledge Graph Integration
Vision-Language Models are Strong Noisy Label Detectors
NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction
Propensity Score Alignment of Unpaired Multimodal Data
LESS: Label-Efficient and Single-Stage Referring 3D Segmentation
Faster Algorithms for User-Level Private Stochastic Convex Optimization
Dissect Black Box: Interpreting for Rule-Based Explanations in Unsupervised Anomaly Detection
Image Copy Detection for Diffusion Models
Do Counterfactually Fair Image Classifiers Satisfy Group Fairness? -- A Theoretical and Empirical Study
Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
In-Context Learning State Vector with Inner and Momentum Optimization
PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation
Gene-Gene Relationship Modeling Based on Genetic Evidence for Single-Cell RNA-Seq Data Imputation
HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning
Harmonizing Visual Text Comprehension and Generation
MatFormer: Nested Transformer for Elastic Inference
Referring Human Pose and Mask Estimation In the Wild
Rethinking the Diffusion Models for Missing Data Imputation: A Gradient Flow Perspective
MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model
Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis
LinNet: Linear Network for Efficient Point Cloud Representation Learning
CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy
GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation
Is the MMI Criterion Necessary for Interpretability? Degenerating Non-causal Features to Plain Noise for Self-Rationalization
Exploring DCN-like architecture for fast image generation with arbitrary resolution
Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
LLMs Can Evolve Continually on Modality for $\mathbb{X}$-Modal Reasoning
Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL
Generalizing CNNs to graphs with learnable neighborhood quantization
UniDSeg: Unified Cross-Domain 3D Semantic Segmentation via Visual Foundation Models Prior
A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation
Customized Subgraph Selection and Encoding for Drug-drug Interaction Prediction
Oja's Algorithm for Streaming Sparse PCA
Improving Generalization and Convergence by Enhancing Implicit Regularization
Learning Truncated Causal History Model for Video Restoration
Depth Anything V2
AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario
UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation
How Does Message Passing Improve Collaborative Filtering?
Can Graph Learning Improve Planning in LLM-based Agents?
LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing
Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation
A Recipe for Charge Density Prediction
Historical Test-time Prompt Tuning for Vision Foundation Models
Elucidating the Design Space of Dataset Condensation
Is Multiple Object Tracking a Matter of Specialization?
Few-Shot Task Learning through Inverse Generative Modeling
Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
On the Sparsity of the Strong Lottery Ticket Hypothesis
Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models
VMamba: Visual State Space Model
ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models
Sample-Efficient Geometry Reconstruction from Euclidean Distances using Non-Convex Optimization
Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing
CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks
VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation
Fairness without Harm: An Influence-Guided Active Sampling Approach
On the Limitations of Fractal Dimension as a Measure of Generalization
A Cat Is A Cat (Not A Dog!): Unraveling Information Mix-ups in Text-to-Image Encoders through Causal Analysis and Embedding Optimization
DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
Regularized Conditional Diffusion Model for Multi-Task Preference Alignment
Harnessing small projectors and multiple views for efficient vision pretraining
Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
SpeedLoader: An I/O efficient scheme for heterogeneous and distributed LLM operation
MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Step
A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds
Amortized Planning with Large-Scale Transformers: A Case Study on Chess
Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention
Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics
MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing
LLaMo: Large Language Model-based Molecular Graph Assistant
Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing
Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptative Residual Module
SGLang: Efficient Execution of Structured Language Model Programs
FUG: Feature-Universal Graph Contrastive Pre-training for Graphs with Diverse Node Features
Stability and Generalizability in SDE Diffusion Models with Measure-Preserving Dynamics
Connectivity-Driven Pseudo-Labeling Makes Stronger Cross-Domain Segmenters
WizardArena: Post-training Large Language Models via Simulated Offline Chatbot Arena
Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment
Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification
HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion
MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging
Interfacing Foundation Models' Embeddings
Online Iterative Reinforcement Learning from Human Feedback with General Preference Model
Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability
A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model
Open-Vocabulary Object Detection via Language Hierarchy
GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning
SpeechAlign: Aligning Speech Generation to Human Preferences
Scalable Optimization in the Modular Norm
Déjà Vu Memorization in Vision–Language Models
Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise
Conditional Controllable Image Fusion
Online Adaptation of Language Models with a Memory of Amortized Contexts
Large Language Models Must Be Taught to Know What They Don’t Know
Physics-Constrained Comprehensive Optical Neural Networks
Grasp as You Say: Language-guided Dexterous Grasp Generation
ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restoration
Upping the Game: How 2D U-Net Skip Connections Flip 3D Segmentation
Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
Generative Hierarchical Materials Search
Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection?
Group Robust Preference Optimization in Reward-free RLHF
Relationship Prompt Learning is Enough for Open-Vocabulary Semantic Segmentation
Functionally Constrained Algorithm Solves Convex Simple Bilevel Problem
Leveraging Separated World Model for Exploration in Visually Distracted Environments
Scalable Bayesian Optimization via Focalized Sparse Gaussian Processes
Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation
Understanding Visual Feature Reliance through the Lens of Complexity
SlimGPT: Layer-wise Structured Pruning for Large Language Models
Scalable Kernel Inverse Optimization
A Modular Conditional Diffusion Framework for Image Reconstruction
DiffPhyCon: A Generative Approach to Control Complex Physical Systems
Swift Sampler: Efficient Learning of Sampler by 10 Parameters
FedAvP: Augment Local Data via Shared Policy in Federated Learning
Learning 1D Causal Visual Representation with De-focus Attention Networks
Posture-Informed Muscular Force Learning for Robust Hand Pressure Estimation
Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts
Visual Pinwheel Center Act as Geometric Saliency Detector
Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Search
Towards Principled Graph Transformers
RL-GPT: Integrating Reinforcement Learning and Code-as-policy
EfficientCAPER: An End-to-End Framework for Fast and Robust Category-Level Articulated Object Pose Estimation
A Structure-Aware Framework for Learning Device Placements on Computation Graphs
EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization
Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling
RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation
Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
PowerPM: Foundation Model for Power Systems
Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization
DiffuBox: Refining 3D Object Detection with Point Diffusion
GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance
Combining Observational Data and Language for Species Range Estimation
Unveiling User Satisfaction and Creator Productivity Trade-Offs in Recommendation Platforms
Reinforcing LLM Agents via Policy Optimization with Action Decomposition
HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting
Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priors
Classification Done Right for Vision-Language Pre-Training
Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation
No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests
Online Feature Updates Improve Online (Generalized) Label Shift Adaptation
Universal In-Context Approximation By Prompting Fully Recurrent Models
Physical Consistency Bridges Heterogeneous Data in Molecular Multi-Task Learning
MeshXL: Neural Coordinate Field for Generative 3D Foundation Models
MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs
Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
Improving Gloss-free Sign Language Translation by Reducing Representation Density
Seeing Beyond the Crop: Using Language Priors for Out-of-Bounding Box Keypoint Prediction
On Affine Homotopy between Language Encoders
Generalized Linear Bandits with Limited Adaptivity
Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving
Segmenting Watermarked Texts From Language Models
HonestLLM: Toward an Honest and Helpful Large Language Model
Leveraging an ECG Beat Diffusion Model for Morphological Reconstruction from Indirect Signals
Base of RoPE Bounds Context Length
Novel Object Synthesis via Adaptive Text-Image Harmony
Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning
FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion
TAPTRv2: Attention-based Position Update Improves Tracking Any Point
DAGER: Exact Gradient Inversion for Large Language Models
ANT: Adaptive Noise Schedule for Time Series Diffusion Models
Multistep Distillation of Diffusion Models via Moment Matching
VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions
DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection
Slot State Space Models
On improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
NeuMA: Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics
End-to-end Learnable Clustering for Intent Learning in Recommendation
On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice
Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generation
Auditing Privacy Mechanisms via Label Inference Attacks
Understanding Transformer Reasoning Capabilities via Graph Algorithms
Proportional Fairness in Non-Centroid Clustering
4-bit Shampoo for Memory-Efficient Network Training
Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
ConStat: Performance-Based Contamination Detection in Large Language Models
Efficient Lifelong Model Evaluation in an Era of Rapid Progress
RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
Context and Geometry Aware Voxel Transformer for Semantic Scene Completion
Transformers need glasses! Information over-squashing in language tasks
CV-VAE: A Compatible Video VAE for Latent Generative Video Models
NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction
Improved Generation of Adversarial Examples Against Safety-aligned LLMs
EAI: Emotional Decision-Making of LLMs in Strategic Games and Ethical Dilemmas
How does PDE order affect the convergence of PINNs?
Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD
Offline Behavior Distillation
Learning from Pattern Completion: Self-supervised Controllable Generation
Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation
DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models
Invisible Image Watermarks Are Provably Removable Using Generative AI
Optimal Scalarizations for Sublinear Hypervolume Regret
Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models
SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction
Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
ContextCite: Attributing Model Generation to Context
PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding
Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers
Sparse High Rank Adapters
Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis
Robust Contrastive Multi-view Clustering against Dual Noisy Correspondence
Locating What You Need: Towards Adapting Diffusion Models to OOD Concepts In-the-Wild
VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time
Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication
Imitating Language via Scalable Inverse Reinforcement Learning
Robust Gaussian Processes via Relevance Pursuit
FNP: Fourier Neural Processes for Arbitrary-Resolution Data Assimilation
ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction
ActSort: An active-learning accelerated cell sorting algorithm for large-scale calcium imaging datasets
Convolutional Differentiable Logic Gate Networks
On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection
ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention
Learnability Matters: Active Learning for Video Captioning
E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection
AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion Models
Learning symmetries via weight-sharing with doubly stochastic tensors
ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses
HyperPrism: An Adaptive Non-linear Aggregation Framework for Distributed Machine Learning over Non-IID Data and Time-varying Communication Links
A Swiss Army Knife for Heterogeneous Federated Learning: Flexible Coupling via Trace Norm
Training Data Attribution via Approximate Unrolling
OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding
Towards Multi-dimensional Explanation Alignment for Medical Classification
Contextual Multinomial Logit Bandits with General Value Functions
Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos
EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models
TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering
Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation
I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing
Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching
Learning to Shape In-distribution Feature Space for Out-of-distribution Detection
Risk-Averse Fine-tuning of Large Language Models
AdaNovo: Towards Robust \emph{De Novo} Peptide Sequencing in Proteomics against Data Biases
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
Neural collapse vs. low-rank bias: Is deep neural collapse really optimal?
FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributions
Learning Versatile Skills with Curriculum Masking
Voxel Proposal Network via Multi-Frame Knowledge Distillation for Semantic Scene Completion
Bridge the Modality and Capability Gaps in Vision-Language Model Selection
On the Noise Robustness of In-Context Learning for Text Generation
Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models
Optimal Multiclass U-Calibration Error and Beyond
Multiclass Transductive Online Learning
Contrastive-Equivariant Self-Supervised Learning Improves Alignment with Primate Visual Area IT
On the cohesion and separability of average-link for hierarchical agglomerative clustering
BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
A Unifying Normative Framework of Decision Confidence
DeepITE: Designing Variational Graph Autoencoders for Intervention Target Estimation
Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages
A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning
GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration
Continuous Heatmap Regression for Pose Estimation via Implicit Neural Representation
Learning the Infinitesimal Generator of Stochastic Diffusion Processes
Theoretical Analysis of Weak-to-Strong Generalization
Learning via Surrogate PAC-Bayes
SAMPa: Sharpness-aware Minimization Parallelized
Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization
NeuralSolver: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks
A Foundation Model for Zero-shot Logical Query Reasoning
Even Sparser Graph Transformers
RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
Generalized Fast Exact Conformalization
QBB: Quantization with Binary Bases for LLMs
RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning
ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models
SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off
Building a stable classifier with the inflated argmax
Robust Offline Active Learning on Graphs
Adversarially Robust Dense-Sparse Tradeoffs via Heavy-Hitters
Hierarchical Programmatic Option Framework
Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
Non-asymptotic Convergence of Training Transformers for Next-token Prediction
Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality
Towards Stable Representations for Protein Interface Prediction
Geometric Trajectory Diffusion Models
Clustering in Causal Attention Masking
Language Model as Visual Explainer
Almost Surely Asymptotically Constant Graph Neural Networks
Pretraining with Random Noise for Fast and Robust Learning without Weight Transport
Linear Causal Bandits: Unknown Graph and Soft Interventions
Variational Delayed Policy Optimization
Simplifying Latent Dynamics with Softly State-Invariant World Models
Efficient Policy Evaluation Across Multiple Different Experimental Datasets
GREATS: Online Selection of High-Quality Data for LLM Training in Every Iteration
Quantum Deep Equilibrium Models
Optimal Private and Communication Constraint Distributed Goodness-of-Fit Testing for Discrete Distributions in the Large Sample Regime
Neuro-Symbolic Data Generation for Math Reasoning
DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks
Tangent Space Causal Inference: Leveraging Vector Fields for Causal Discovery in Dynamical Systems
Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs
Genetic-guided GFlowNets for Sample Efficient Molecular Optimization
What does guidance do? A fine-grained analysis in a simple setting
Persistent Homology for High-dimensional Data Based on Spectral Methods
Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales
Generative Modelling of Structurally Constrained Graphs
Disentangling the Roles of Distinct Cell Classes with Cell-Type Dynamical Systems
MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution
Sample Complexity Reduction via Policy Difference Estimation in Tabular Reinforcement Learning
SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams
Computational Aspects of Bayesian Persuasion under Approximate Best Response
Enhancing Chess Reinforcement Learning with Graph Representation
UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes
RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs
Finding Transformer Circuits With Edge Pruning
Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency
AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data
General bounds on the quality of Bayesian coresets
Pricing and Competition for Generative AI
The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
Self-Guided Masked Autoencoder
Optimal Hypothesis Selection in (Almost) Linear Time
Amortized Active Causal Induction with Deep Reinforcement Learning
Improved Particle Approximation Error for Mean Field Neural Networks
HHD-GP: Incorporating Helmholtz-Hodge Decomposition into Gaussian Processes for Learning Dynamical Systems
Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models
Transformers on Markov data: Constant depth suffices
Testably Learning Polynomial Threshold Functions
Do causal predictors generalize better to new domains?
On the Surprising Effectiveness of Attention Transfer for Vision Transformers
Adaptable Logical Control for Large Language Models
Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment
Exocentric-to-Egocentric Video Generation
Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models
TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scene
Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional Optimization
Improving Adaptivity via Over-Parameterization in Sequence Models
GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing
AHA: Human-Assisted Out-of-Distribution Generalization and Detection
AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
Recurrent neural networks: vanishing and exploding gradients are not the end of the story
Stochastic Newton Proximal Extragradient Method
Revisiting Differentially Private ReLU Regression
Learning Where to Edit Vision Transformers
Topological obstruction to the training of shallow ReLU neural networks
Latent Neural Operator for Solving Forward and Inverse PDE Problems
PrivCirNet: Efficient Private Inference via Block Circulant Transformation
Post-Hoc Reversal: Are We Selecting Models Prematurely?
IR-CM: The Fast and Universal Image Restoration Method Based on Consistency Model
Learning Generalized Linear Programming Value Functions
Partial Transportability for Domain Generalization
Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies
Accelerating Augmentation Invariance Pretraining
Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting
PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications
DarkSAM: Fooling Segment Anything Model to Segment Nothing
Stochastic Optimal Control for Diffusion Bridges in Function Spaces
Generalization of Hamiltonian algorithms
Learning-Augmented Algorithms with Explicit Predictors
High-probability complexity bounds for stochastic non-convex minimax optimization
Online Bayesian Persuasion Without a Clue
Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning
Random Cycle Coding: Lossless Compression of Cluster Assignments via Bits-Back Coding
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
Learning Mixtures of Unknown Causal Interventions
Why Do We Need Weight Decay in Modern Deep Learning?
Online Control in Population Dynamics
SlimSAM: 0.1% Data Makes Segment Anything Slim
Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training
Mutli-Armed Bandits with Network Interference
Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling
Navigating Chemical Space with Latent Flows
On Differentially Private Subspace Estimation in a Distribution-Free Setting
An Accelerated Gradient Method for Convex Smooth Simple Bilevel Optimization
Rethinking Parity Check Enhanced Symmetry-Preserving Ansatz
Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks
An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding
Unified Covariate Adjustment for Causal Inference
Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms
Learning Elastic Costs to Shape Monge Displacements
Disentangling and mitigating the impact of task similarity for continual learning
Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model
Instruction-Guided Visual Masking
Stopping Bayesian Optimization with Probabilistic Regret Bounds
Robust Reinforcement Learning from Corrupted Human Feedback
Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference
Lookback Prophet Inequalities
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
Return of Unconditional Generation: A Self-supervised Representation Generation Method
Preference Learning Algorithms Do Not Learn Preference Rankings
Can LLMs Implicitly Learn Numeric Parameter Constraints in Data Science APIs?
Multi-model Ensemble Conformal Prediction in Dynamic Environments
Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity
Scaling laws for learning with real and surrogate data
From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization
Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models
UniIF: Unified Molecule Inverse Folding
Easy Regional Contrastive Learning of Expressive Fashion Representations
Retrieval-Augmented Diffusion Models for Time Series Forecasting
On Weak Regret Analysis for Dueling Bandits
Bayesian Identification of the Hamiltonian Inductive Bias in Dynamical Systems
Not so griddy: Internal representations of RNNs path integrating more than one agent
Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithm
Statistical Efficiency of Distributional Temporal Difference Learning
Image-aware Evaluation of Generated Medical Reports
Nuclear Norm Regularization for Deep Learning
How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression
To Learn or Not to Learn, That is the Question — A Feature-Task Dual Learning Model of Perceptual Learning
Fully Explicit Dynamic Gaussian Splatting
Biologically-Inspired Learning Model for Instructed Vision
Neural Collapse To Multiple Centers For Imbalanced Data
Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures
FlexCap: Describe Anything in Images in Controllable Detail
Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses
A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems
Contrastive losses as generalized models of global epistasis
LLM Dataset Inference: Did you train on my dataset?
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
Causal Effect Identification in a Sub-Population with Latent Variables
Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints
3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection
TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment
Generalizable Person Re-identification via Balancing Alignment and Uniformity
DiffuserLite: Towards Real-time Diffusion Planning
CoFie: Learning Compact Neural Surface Representations with Coordinate Fields
Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inference
Gated Slot Attention for Efficient Linear-Time Sequence Modeling
Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer
RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation
Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Loss
Chain of Thoughtlessness? An Analysis of CoT in Planning
Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity
MindMerger: Efficiently Boosting LLM Reasoning in non-English Languages
Functional Gradient Flows for Constrained Sampling
Tell What You Hear From What You See - Video to Audio Generation Through Text
Acceleration Exists! Optimization Problems When Oracle Can Only Compare Objective Function Values
Improved Sample Complexity for Multiclass PAC Learning
Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning
Nonlinear dynamics of localization in neural receptive fields
Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records
The Star Geometry of Critic-Based Regularizer Learning
Practical Shuffle Coding
How many classifiers do we need?
Neglected Hessian component explains mysteries in sharpness regularization
ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration
Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signals
AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
Towards Robust Multimodal Sentiment Analysis with Incomplete Data
Online Relational Inference for Evolving Multi-agent Interacting Systems
S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning
One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection
Understanding and Minimising Outlier Features in Transformer Training
Code Repair with LLMs gives an Exploration-Exploitation Tradeoff
Self-playing Adversarial Language Game Enhances LLM Reasoning
A Label is Worth A Thousand Images in Dataset Distillation
A theoretical design of concept sets: improving the predictability of concept bottleneck models
Measuring Per-Unit Interpretability at Scale Without Humans
Policy Mirror Descent with Lookahead
Particle Semi-Implicit Variational Inference
Data Free Backdoor Attacks
SuperDeepFool: a new fast and accurate minimal adversarial attack
Continual learning with the neural tangent ensemble
Most Influential Subset Selection: Challenges, Promises, and Beyond
Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models
Parametric model reduction of mean-field and stochastic systems via higher-order action matching
Super Consistency of Neural Network Landscapes and Learning Rate Transfer
A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation
The Impact of Initialization on LoRA Finetuning Dynamics
Approximation-Aware Bayesian Optimization
Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate
Learning to Reason via Program Generation, Emulation, and Search
Dynamic Conditional Optimal Transport through Simulation-Free Flows
Explaining Datasets in Words: Statistical Models with Natural Language Parameters
AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies
Adam with model exponential moving average is effective for nonconvex optimization
Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising
Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering Playlists
Batched Energy-Entropy acquisition for Bayesian Optimization
Taming the Long Tail in Human Mobility Prediction
Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective
Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis
An Analysis of Tokenization: Transformers under Markov Data
Alignment at Pre-training! Towards Native Alignment for Arabic LLMs
Human Expertise in Algorithmic Prediction
Solving Inverse Problems via Diffusion Optimal Control
Quantum Algorithms for Non-smooth Non-convex Optimization
pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning
Co-occurrence is not Factual Association in Language Models
Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient
MAmmoTH2: Scaling Instructions from the Web
AV-Cloud: Spatial Audio Rendering Through Audio-Visual Cloud Splatting
Bridging Geometric States via Geometric Diffusion Bridge
Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models
Pretrained Optimization Model for Zero-Shot Black Box Optimization
CogVLM: Visual Expert for Pretrained Language Models
Navigating Extremes: Dynamic Sparsity in Large Output Spaces
Private Geometric Median
Implicit Optimization Bias of Next-token Prediction in Linear Models
Robust Sparse Regression with Non-Isotropic Designs
Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity
Auditing Local Explanations is Hard
Gradient-Variation Online Learning under Generalized Smoothness
Generative Modeling of Molecular Dynamics Trajectories
A Theoretical Perspective for Speculative Decoding Algorithm
Bandits with Preference Feedback: A Stackelberg Game Perspective
The Fine-Grained Complexity of Gradient Computation for Training Large Language Models
A Tractable Inference Perspective of Offline RL
Learning Formal Mathematics From Intrinsic Motivation
Linear Transformers are Versatile In-Context Learners
Implicit Curriculum in Procgen Made Explicit
Polynomial-Time Computation of Exact $\Phi$-Equilibria in Polyhedral Games
Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
Policy-shaped prediction: avoiding distractions in model-based reinforcement learning
An Equivalence Between Static and Dynamic Regret Minimization
Classification Diffusion Models: Revitalizing Density Ratio Estimation
Improving self-training under distribution shifts via anchored confidence with theoretical guarantees
Efficiency for Free: Ideal Data Are Transportable Representations
Aligning Audio-Visual Joint Representations with an Agentic Workflow
Automatically Learning Hybrid Digital Twins of Dynamical Systems
On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and Games
Distribution Learning with Valid Outputs Beyond the Worst-Case
Edit Distance Robust Watermarks via Indexing Pseudorandom Codes
CosAE: Learnable Fourier Series for Image Restoration
Any2Policy: Learning Visuomotor Policy with Any-Modality
S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training
Optimal Classification under Performative Distribution Shift
The Sample Complexity of Gradient Descent in Stochastic Convex Optimization
Segment Anything without Supervision
Alignment for Honesty
Length Optimization in Conformal Prediction
Autonomous Driving with Spiking Neural Networks
Localizing Memorization in SSL Vision Encoders
Dynamics of Supervised and Reinforcement Learning in the Non-Linear Perceptron
Identifying Selections for Unsupervised Subtask Discovery
Generalized Eigenvalue Problems with Generative Priors
Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning
3D Gaussian Rendering Can Be Sparser: Efficient Rendering via Learned Fragment Pruning
All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation
Mixture of Nested Experts: Adaptive Processing of Visual Tokens
The Intelligible and Effective Graph Neural Additive Network
ClashEval: Quantifying the tug-of-war between an LLM’s internal prior and external evidence
We use cookies to store which papers have been visited.
I agree
Successful Page Load
NeurIPS uses cookies for essential functions only. We do not sell your personal information.
Our Privacy Policy »
Accept Cookies
We use cookies to store which papers have been visited.
I agree
