Scaling Language-Centric Omnimodal Representation Learning
机构 * DAMO Academy, Alibaba Group（达摩院，阿里巴巴集团）
Comments NeurIPS 2025
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
FACE: Faithful Automatic Concept Extraction
机构 * Rochester Institute of Technology（罗切斯特理工大学） ； Toyota InfoTech Labs（丰田信息科技实验室） ； University of Florida（佛罗里达大学）
Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025)
SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction
机构 * PKU（北京大学） ； HKUST（香港科技大学） ； SEU（上海师范大学） ； HKU（香港大学）
Comments NeurIPS 2025 https://xishuxishu.github.io/SyncHuman.github.io/
Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm
机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； University of Auckland（奥克兰大学） ； Chongqing University（重庆大学）
Comments Accepted to NeurIPS 2025. Title used at submission and review: PIRO: Toward Stable Reward Learning for Inverse RL via Monotonic Policy Divergence Reduction
InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition
机构 * Aerospace Information Research Institute, Chinese Academy of Sciences（航天信息研究所，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） ； Harbin Institute of Technology（哈尔滨工业大学） ； Shanghai Jiao Tong University（上海交通大学） ； University of Wollongong（沃林戈大学） ； SAIS, Shanghai Jiao Tong University（上海交通大学国际关系学院）
Comments Accepted to NeurIPS 2025
Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression
机构 * Fudan University（复旦大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； Shanghai Innovation Institute（上海创新研究院） ； The Chinese University of Hong Kong（香港中文大学）
Comments Accepted at NeurIPS 2025
Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model
机构 * Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院） ； Hunan University（湖南大学） ； ETH Zurich（苏黎世联邦理工学院）
Comments Accepted to NeurIPS 2025 Datasets and Benchmarks Track. Dataset and Code: https://github.com/RuipingL/Situat3DChange
Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
机构 * School of Computing & Data Science, The University of Hong Kong（计算与数据科学学院，香港大学）
Comments 71 pages, 12 figures, NeurIPS 2025
Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis
Comments NeurIPS 2025 poster
Test-Time Adaptation by Causal Trimming
机构 * School of Computing, National University of Singapore（新加坡国立大学计算机学院） ； Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所） ； Singapore-MIT Alliance for Research and Technology（新加坡-麻省理工联合研究技术联盟）
Comments Accepted to the Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025); Code is available at https://github.com/NancyQuris/TACT
Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment
机构 * School of Nursing, The Hong Kong Polytechnic University（香港理工大学护理学院） ； Department of Computer Science, Hong Kong Baptist University（香港 Baptist 大学计算机科学系）
Comments NeurIPS 2025 Spotlight
Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution
机构 * School of Data Science, Fudan University（复旦大学数据科学学院） ； Shanghai Innovation Institute（上海创新研究院） ； University of Surrey（Surrey大学） ； Imperial College London（伦敦帝国理工学院）
Comments NeurIPS 2025
Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling
机构 * Institute for AI Industry Research (AIR), Tsinghua University（人工智能产业研究所（AIR），清华大学） ； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； The Chinese University of Hong Kong（香港中文大学）
Comments 26 pages, 6 figures. Accepted at NeurIPS 2025
A Joint Learning Approach to Hardware Caching and Prefetching
Comments Accepted at ML for Systems Workshop at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)
How Patterns Dictate Learnability in Sequential Data
Comments NeurIPS 2025, 36 pages, 4 figures
A Stochastic Differential Equation Framework for Multi-Objective LLM Interactions: Dynamical Systems Analysis with Code Generation Applications
机构 * University of San Francisco（旧金山大学） ； Vector Institute for Artificial Intelligence（人工智能向量研究所）
Comments Peer-reviewed and accepted to the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) DynaFront 2025 Workshop (https://sites.google.com/view/dynafrontneurips25)
Learning-Augmented Streaming Algorithms for Correlation Clustering
Comments NeurIPS 2025
Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits
机构 * KAUST Center of Excellence for Generative AI（知识增强人工智能卓越中心） ； ETH Zurich（苏黎世联邦理工学院） ； ETH AI Center（苏黎世联邦理工学院人工智能中心） ； Georgia Institute of Technology（佐治亚理工学院）
Comments Accepted for publication at NeurIPS 2025
Information-Computation Tradeoffs for Noiseless Linear Regression with Oblivious Contamination
Comments To appear in NeurIPS 2025
Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization
机构 * Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系） ； Huawei（华为）
Comments Accepted by NeurIPS 2025
Failure Prediction at Runtime for Generative Robot Policies
Comments Project page: https://tum-lsy.github.io/fiper_website. 33 pages, 12 figures. Accepted to NeurIPS 2025
Graph Your Own Prompt
机构 * Griffith University（格里菲斯大学） ； Data61/CSIRO ； Australian National University（澳大利亚国立大学） ； University of New South Wales（新南威尔士大学）
Comments Accepted at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)
Long-Range Graph Wavelet Networks
机构 * School of Computation, Information and Technology（计算、信息与技术学院） ； Munich Data Science Institute（慕尼黑数据科学研究所） ； Technical University of Munich（慕尼黑技术大学）
Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: New Perspectives in Advancing Graph Machine Learning
VendiRL: A Framework for Self-Supervised Reinforcement Learning of Diversely Diverse Skills
Comments 17 pages including appendices, full paper at the Scaling Environments for Agents workshop at NeurIPS 2025
Learning Diffusion Models with Flexible Representation Guidance
Comments NeurIPS 2025; Also Oral at ICML 2025 FM4LS workshop
The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models
机构 * University of Science and Technology of China（中国科学技术大学） ； NLPR & MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Comments NeurIPS 2025 Datasets and Benchmarks Track. Github link: https://github.com/TomSheng21/tta-vlm
Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints
机构 * Shanghai Jiao Tong University（上海交通大学） ； Xiaohongshu Inc.（小红书公司）
Comments Accepted by NeurIPS 2025 Spotlight
State-Covering Trajectory Stitching for Diffusion Planners
机构 * KAIST（韩国科学技术院）
Comments Accepted to NeurIPS 2025
Learning Shared Representations from Unpaired Data
机构 * Department of Computer Science Bar-Ilan University（巴伊兰大学计算机科学系） ； Electrical and Computer Engineering Technion（技术学院电子与计算机工程系）
Comments Accepted to NeurIPS 2025
ARM: Adaptive Reasoning Model
机构 * Shanghai Key Laboratory of Data Science, College of Computer Science and Artificial Intelligence, Fudan University（上海数据科学关键实验室，计算机科学与人工智能学院，复旦大学） ； The Ohio State University（俄亥俄州立大学） ； Shanghai Academy of AI for Science（上海人工智能科学研究院）
Comments NeurIPS 2025 (Spotlight)
