NeurIPS 2025 Papers

San Diego Mexico City Layout: mini compact topic detail × No topics available No sessions available 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. More effort is needed to protect pedestrian privacy in the era of AI Test-Time Adaptive Object Detection with Foundation Model PolypSense3D: A Multi-Source Benchmark Dataset for Depth-Aware Polyp Size Measurement in Endoscopy StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assembly NegoCollab: A Common Representation Negotiation Approach for Heterogeneous Collaborative Perception Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding Flow-Based Policy for Online Reinforcement Learning Reconstructing Heterogeneous Biomolecules via Hierarchical Gaussian Mixtures and Part Discovery Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation Connectome-Based Modelling Reveals Orientation Maps in the Drosophila Optic Lobe Hawaii: Hierarchical Visual Knowledge Transfer for Efficient Vision-Language Models Online Multi-Class Selection with Group Fairness Guarantee Majority of the Bests: Improving Best-of-N via Bootstrapping Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs Orthogonal Contrastive Learning for Multi-Representation fMRI Analysis Near-Optimal Experiment Design in Linear non-Gaussian Cyclic Models Localized Data Shapley: Accelerating Valuation for Nearest Neighbor Algorithms UniDomain: Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning COALA: Numerically Stable and Efficient Framework for Context-Aware Low-Rank Approximation Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders No Object Is an Island: Enhancing 3D Semantic Segmentation Generalization with Diffusion Models When Kernels Multiply, Clusters Unify: Fusing Embeddings with the Kronecker Product 3DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimization AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs Don’t Give Up on Democratizing AI for the Wrong Reasons PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts Linguini: A benchmark for language-agnostic linguistic reasoning SSRB: Direct Natural Language Querying to Massive Heterogeneous Semi-Structured Data OpenGU: A Comprehensive Benchmark for Graph Unlearning ChemX: A Collection of Chemistry Datasets for Benchmarking Automated Information Extraction MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual Correspondence OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning PhysDrive: A Multimodal Remote Physiological Measurement Dataset for In-vehicle Driver Monitoring Care-PD: A Multi-Site Anonymized Clinical Dataset for Parkinson’s Disease Gait Assessment A Learning-Augmented Approach to Online Allocation Problems DERD-Net: Learning Depth from Event-based Ray Densities Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning More Than Just Functional: LLM-as-a-Critique for Efficient Code Generation Memory-Augmented Potential Field Theory: A Framework for Adaptive Control in Non-Convex Domains Limitations of Normalization in Attention Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs Learning to Plan Like the Human Brain via Visuospatial Perception and Semantic-Episodic Synergistic Decision-Making Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment Dr. RAW: Towards General High-Level Vision from RAW with Efficient Task Conditioning Predictable Scale (Part II) --- Farseer: A Refined Scaling Law in LLMs Cognitive Predictive Processing: A Human-inspired Framework for Adaptive Exploration in Open-World Reinforcement Learning A unified framework for establishing the universal approximation of transformer-type architectures A machine learning approach that beats Rubik's cubes PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priors Information Theoretic Learning for Diffusion Models with Warm Start Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm A Dynamic Learning Strategy for Dempster-Shafer Theory with Applications in Classification and Enhancement RankSEG-RMA: An Efficient Segmentation Algorithm via Reciprocal Moment Approximation PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion TreeSplat: Mergeable Tree for Deformable Gaussian Splatting Adaptive Sigmoid Clipping for Balancing the Direction–Magnitude Mismatch Trade-off in Differentially Private Learning Resource-Constrained Federated Continual Learning: What Does Matter? The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection THD-BAR: Topology Hierarchical Derived Brain Autoregressive Modeling for EEG Generic Representations F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training Unsupervised Federated Graph Learning FrameShield: Adversarially Robust Video Anomaly Detection A Closer Look at Graph Transformers: Cross-Aggregation and Beyond Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization HypoBootstrap: A Bootstrapping Framework for Inductive Reasoning Can Class-Priors Help Single-Positive Multi-Label Learning? GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization Storyboard-guided Alignment for Fine-grained Video Action Recognition Multi-Objective Hyperparameter Selection via Hypothesis Testing on Reliability Graphs Strassen Attention, Split VC Dimension and Compositionality in Transformers Pessimistic Data Integration for Policy Evaluation Fair Matroid Selection LLM at Network Edge: A Layer-wise Efficient Federated Fine-tuning Approach Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks Local Curvature Descent: Squeezing More Curvature out of Standard and Polyak Gradient Descent Mesh Interpolation Graph Network for Dynamic and Spatially Irregular Global Weather Forecasting V2V: Scaling Event-Based Vision through Efficient Video-to-Voxel Simulation FedIGL: Federated Invariant Graph Learning for Non-IID Graphs DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection Doubly Robust Alignment for Large Language Models Aligning What Matters: Masked Latent Adaptation for Text-to-Audio-Video Generation More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models BNMusic: Blending Environmental Noises into Personalized Music MSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression Integral Imprecise Probability Metrics CHPO: Constrained Hybrid-action Policy Optimization for Reinforcement Learning Nearly-Linear Time Private Hypothesis Selection with the Optimal Approximation Factor Shapley-Based Data Valuation for Weighted $k$-Nearest Neighbors VPO: Reasoning Preferences Optimization Based on $\mathcal{V}$-Usable Information GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition Prompt Tuning Transformers for Data Memorization One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models Diffusion-Guided Graph Data Augmentation Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes An Evidence-Based Post-Hoc Adjustment Framework for Anomaly Detection Under Data Contamination Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples Towards foundational LiDAR world models with efficient latent flow matching RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Rank Correlation between Labels NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding Toward a Unified Geometry Understanding : Riemannian Diffusion Framework for Graph Generation and Prediction Constant Bit-size Transformers Are Turing Complete Navigating the MIL Trade-Off: Flexible Pooling for Whole Slide Image Classification AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretraining Transcending Cost-Quality Tradeoff in Agent Serving via Session-Awareness Physics-informed Reduced Order Modeling of Time-dependent PDEs via Differentiable Solvers IMPACT: Irregular Multi-Patch Adversarial Composition Based on Two‑Phase Optimization Compressed and Smooth Latent Space for Text Diffusion Modeling Spatial Understanding from Videos: Structured Prompts Meet Simulation Data Visual Structures Help Visual Reasoning: Addressing the Binding Problem in LVLMs Capturing Individual Human Preferences with Reward Features How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning Manipulating Feature Visualizations with Gradient Slingshots Rope to Nope and Back Again: A New Hybrid Attention Strategy Enhancing Privacy in Multimodal Federated Learning with Information Theory Tight Bounds on the Distortion of Randomized and Deterministic Distributed Voting Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses $\texttt{STRCMP}$: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization InstructHOI: Context-Aware Instruction for Multi-Modal Reasoning in Human-Object Interaction Detection The Quotient Bayesian Learning Rule S-Crescendo: A Nested Transformer Weaving Framework for Scalable Nonlinear System in S-Domain Representation On the VC dimension of deep group convolutional neural networks The Promise of RL for Autoregressive Image Editing Light-Weight Diffusion Multiplier and Uncertainty Quantification for Fourier Neural Operators SEMPO: Lightweight Foundation Models for Time Series Forecasting Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning Efficient Knowledge Transfer in Federated Recommendation for Joint Venture Ecosystem AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant Adversarial Patches YEAST: Yet Another Sequential Test PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning Understanding Prompt Tuning and In-Context Learning via Meta-Learning Breakthrough Sensor-Limited Single View: Towards Implicit Temporal Dynamics for Time Series Domain Adaptation Turning the Tables: Enabling Backward Transfer via Causal-Aware LoRA in Continual Learning Unifying and Enhancing Graph Transformers via a Hierarchical Mask Framework HoloLLM: Multisensory Foundation Model for Language-Grounded Human Sensing and Reasoning The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness Improving the Straight-Through Estimator with Zeroth-Order Information Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models Enhancing GUI Agent with Uncertainty-Aware Self-Trained Evaluator Robust Federated Finetuning of LLMs via Alternating Optimization of LoRA Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning Diversity Is All You Need for Contrastive Learning: Spectral Bounds on Gradient Magnitudes GLNCD: Graph-Level Novel Category Discovery When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners Soft-consensual Federated Learning for Data Heterogeneity via Multiple Paths Neural Attention Search One Sample is Enough to Make Conformal Prediction Robust CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation Semi-supervised Graph Anomaly Detection via Robust Homophily Learning Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems BADiff: Bandwidth Adaptive Diffusion Model Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction Towards Unified Multimodal Interleaved Generation via Group Relative Policy Optimization Addressing Mark Imbalance in Integration-free Marked Temporal Point Processes The Quest for Universal Master Key Filters in DS-CNNs Pin the Tail on the Model: Blindfolded Repair of User-Flagged Failures in Text-to-Image Services AutoPartGen: Autoregressive 3D Part Generation and Discovery Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning Uncertainty-Aware Multi-Objective Reinforcement Learning-Guided Diffusion Models for 3D De Novo Molecular Design Dynamic Diffusion Schrödinger Bridge in Astrophysical Observational Inversions Learning Simple Interpolants for Linear Integer Arithmetic EAReranker: Efficient Embedding Adequacy Assessment for Retrieval Augmented Generation Identifying Macro Causal Effects in C-DMGs over DMGs Bridging Time and Linguistics: LLMs as Time Series Analyzer through Symbolization and Segmentation Statistical inference for Linear Stochastic Approximation with Markovian Noise Revealing Multimodal Causality with Large Language Models Gradient Variance Reveals Failure Modes in Flow-Based Generative Models Leveraging robust optimization for llm alignment under distribution shifts Relaxing partition admissibility in Cluster-DAGs: a causal calculus with arbitrary variable clustering SPICED: A Synaptic Homeostasis-Inspired Framework for Unsupervised Continual EEG Decoding $\epsilon$-Seg: Sparsely Supervised Semantic Segmentation of Microscopy Data Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection Statistical Parity with Exponential Weights Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning GRAVER: Generative Graph Vocabularies for Robus