arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

NeurIPS

Conference on Neural Information Processing Systems · 会议 · Machine Learning

共收录 17324
2506.01713 2025-10-07 cs.CL

SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning

Zhongwei Wan, Zhihao Dou, Che Liu, Yu Zhang, Dongfei Cui, Qinjian Zhao, Hui Shen, Jing Xiong, Yi Xin, Yifan Jiang, Chaofan Tao, Yangfan He, Mi Zhang, Shen Yan

机构 * The Ohio State University(俄亥俄州立大学)

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01583 2025-10-07 cs.RO cs.AI cs.CV

FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens

Yiming Zhong, Yumeng Liu, Chuyang Xiao, Zemin Yang, Youzhuo Wang, Yufei Zhu, Ye Shi, Yujing Sun, Xinge Zhu, Yuexin Ma

机构 * ShanghaiTech University(上海科技大学) The University of Hong Kong(香港大学) Digital Trust Centre, Nanyang Technological University(南洋理工大学数字信任中心) The Chinese University of Hong Kong(香港中文大学)

Comments Comments: Published at Neural Information Processing Systems (NeurIPS) 2025. Project page and code: https://freq-policy.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.19281 2025-10-07 cs.LG

A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

Yuzheng Hu, Fan Wu, Haotian Ye, David Forsyth, James Zou, Nan Jiang, Jiaqi W. Ma, Han Zhao

机构 * UIUC Urbana(伊利诺伊大学 Urbana分校) Stanford University(斯坦福大学)

Comments Accepted at NeurIPS 2025 as an oral

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.18825 2025-10-07 cs.LG cs.CV

How to build a consistency model: Learning flow maps via self-distillation

Nicholas M. Boffi, Michael S. Albergo, Eric Vanden-Eijnden

机构 * Carnegie Mellon University(卡内基梅隆大学) Harvard University(哈佛大学) Courant Institute of Mathematical Sciences(数学科学学院)

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.16322 2025-10-07 cs.LG cs.AI cs.CL

AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners

Woosung Koh, Wonbeen Oh, Jaein Jang, MinHyung Lee, Hyeongjin Kim, Ah Yeon Kim, Joonkee Kim, Junghyun Lee, Taehyeon Kim, Se-Young Yun

机构 * KAIST AI(韩国科学技术院人工智能研究所) LG AI Research(LG人工智能研究)

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13050 2025-10-07 cs.CV

RGB-to-Polarization Estimation: A New Task and Benchmark Study

Beibei Lin, Zifeng Yuan, Tingting Chen

机构 * National University of Singapore(新加坡国立大学)

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.20752 2025-10-07 cs.CV cs.AI

Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models

Huajie Tan, Yuheng Ji, Xiaoshuai Hao, Xiansheng Chen, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang

机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(多媒体信息处理国家重点实验室,计算机科学学院,北京大学) Beijing Academy of Artificial Intelligence(北京人工智能研究院) 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(中国科学院自动化研究所人工智能学院)

Comments 51 pages, 23 figures, NeurIPS'25

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.20117 2025-10-07 cs.LG cs.DC

Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable

Bicheng Ying, Zhe Li, Haibo Yang

机构 * Google(谷歌) Rochester Institute of Technology(罗切斯特理工大学)

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.05323 2025-10-07 stat.ML cs.LG math.PR math.SP math.ST stat.TH

Graph Alignment via Birkhoff Relaxation

Sushil Mahavir Varma, Irène Waldspurger, Laurent Massoulié

机构 * Industrial and Systems Engineering University of Michigan(工业与系统工程大学密歇根大学) CNRS, INRIA Université Paris Dauphine(国家科学研究中心、法国国家信息与自动化研究所巴黎第九大学) INRIA, DI/ENS PSL Research University(法国国家信息与自动化研究所、巴黎高等师范学校研究大学)

Comments To appear in NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.16706 2025-10-07 cs.LG cs.AI cs.CL cs.SE

DISC: Dynamic Decomposition Improves LLM Inference Scaling

Jonathan Light, Wei Cheng, Benjamin Riviere, Wu Yue, Masafumi Oyamada, Mengdi Wang, Yisong Yue, Santiago Paternain, Haifeng Chen

机构 * Rensselaer Polytechnic Institute(拉特克利夫理工学院) NEC Laboratories America(NEC美洲实验室) Princeton University(普林斯顿大学) California Institute of Technology(加州理工学院) NEC Corporation(NEC公司)

Comments 10 pages, Accepted to NeurIPS 2025 (Conference on Neural Information Processing Systems)

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.04686 2025-10-07 cs.CL cs.AI cs.LG

Unlocking Multimodal Mathematical Reasoning via Process Reward Model

Ruilin Luo, Zhuofan Zheng, Yifan Wang, Xinzhe Ni, Zicheng Lin, Songtao Jiang, Yiyao Yu, Chufan Shi, Lei Wang, Ruihang Chu, Jin Zeng, Yujiu Yang

机构 * Tsinghua University(清华大学) ByteDance(字节跳动) Zhejiang University(浙江大学) Ping An Technology (Shenzhen) Co., Ltd(平安科技(深圳)有限公司)

Comments NeurIPS 2025 Main Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.23169 2025-10-07 cs.LG

The Persistence of Neural Collapse Despite Low-Rank Bias

Connall Garrod, Jonathan P. Keating

机构 * Mathematical Institute University of Oxford(牛津大学数学研究所)

Comments 48 pages, 19 figures. To appear in NeurIPS 2025. Slightly reformatted for readability

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.09678 2025-10-07 cs.LG stat.ML

Learning Orthogonal Multi-Index Models: A Fine-Grained Information Exponent Analysis

Yunwei Ren, Jason D. Lee

机构 * Princeton University(普林斯顿大学)

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03521 2025-10-07 cs.CL cs.AI

Identifying Financial Risk Information Using RAG with a Contrastive Insight

Ali Elahi

机构 * Department of Computer Science University of Illinois Chicago(伊利诺伊大学芝加哥分校计算机科学系) Surlamer Investments(Surlamer投资公司)

Comments 7 pages, 1 figure, Workshop on Generative AI in Finance, NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03371 2025-10-07 cs.LG cs.AI cs.DC

Distributed Low-Communication Training with Decoupled Momentum Optimization

Sasho Nedelkoski, Alexander Acker, Odej Kao, Soeren Becker, Dominik Scheinert

Comments NeurIPS 2025 - DynaFront 2025: Dynamics at the Frontiers of Optimization, Sampling, and Games Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03315 2025-10-07 cs.CL cs.AI cs.LG

Decomposing Attention To Find Context-Sensitive Neurons

Alex Gibson

机构 * University of Cambridge(剑桥大学)

Comments 10 pages, 7 figures. Submitted to the Mechanistic Interpretability Workshop at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03282 2025-10-07 cs.LG cs.CL

Discovering Transformer Circuits via a Hybrid Attribution and Pruning Framework

Hao Gu, Vibhas Nair, Amrithaa Ashok Kumar, Jayvart Sharma, Ryan Lagasse

机构 * Algoverse AI Research(Algoverse AI研究)

Comments Accepted to the NeurIPS 2025 Workshop on Mechanistic Interpretability (Mechinterp) and the NeurIPS 2025 Workshop on New Perspectives in Graph Machine Learning

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03276 2025-10-07 cs.LG cs.AI

QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks

Qian Chen, Linxin Yang, Akang Wang, Xiaodong Luo, Yin Zhang

机构 * School of Science and Engineering(科学与工程学院) The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)) Shenzhen International Center for Industrial and Applied Mathematics(深圳国际工业与应用数学中心) Shenzhen Research Institute of Big Data(深圳大数据研究院) School of Data Science(数据科学学院)

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.18917 2025-10-07 cs.LG cs.AI

Behavior Injection: Preparing Language Models for Reinforcement Learning

Zhepeng Cen, Yihang Yao, William Han, Zuxin Liu, Ding Zhao

机构 * Carnegie Mellon University(卡内基梅隆大学) Salesforce AI Research(Salesforce人工智能研究)

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03207 2025-10-06 cs.LG

To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning

Yuda Song, Dhruv Rohatgi, Aarti Singh, J. Andrew Bagnell

Comments 45 pages, 9 figures, published at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03110 2025-10-06 cs.CV

GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion

Beibei Lin, Tingting Chen, Robby T. Tan

机构 * National University of Singapore(新加坡国立大学)

Comments Accepted by NeurIPS 2025. Project page: https://bb12346.github.io/GeoComplete/

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.02936 2025-10-06 cs.LG

RAxSS: Retrieval-Augmented Sparse Sampling for Explainable Variable-Length Medical Time Series Classification

Aydin Javadov, Samir Garibov, Tobias Hoesli, Qiyang Sun, Florian von Wangenheim, Joseph Ollier, Björn W. Schuller

机构 * ETH Zurich(苏黎世联邦理工学院) University of Freiburg(弗赖堡大学) Imperial College London(伦敦帝国学院) Technical University of Munich(慕尼黑技术大学)

Comments Accepted at the NeurIPS 2025 Workshop on Learning from Time Series for Health

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.02892 2025-10-06 cs.LG

RoiRL: Efficient, Self-Supervised Reasoning with Offline Iterative Reinforcement Learning

Aleksei Arzhantsev, Otmane Sakhi, Flavian Vasile

机构 * Criteo AI Lab(Criteo人工智能实验室) Ecole Polytechnique Paris(巴黎高等理工学院)

Comments Accepted to the Efficient Reasoning Workshop at NeuRIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.02768 2025-10-06 cs.LG cs.CL

A Granular Study of Safety Pretraining under Model Abliteration

Shashank Agnihotri, Jonas Jakubassa, Priyam Dey, Sachin Goyal, Bernt Schiele, Venkatesh Babu Radhakrishnan, Margret Keuper

机构 * Data and Web Science Group, University of Mannheim(曼海姆大学数据与网络科学组) Vision and AI Lab, Indian Institute of Science(印度科学院视觉与人工智能实验室) Carnegie Mellon University(卡内基梅隆大学) Max-Planck-Institute for Informatics, Saarland Informatics Campus(马克斯·普朗克信息研究所,萨尔兰信息校园)

Comments Accepted at NeurIPS 2025 bWorkshop Lock-LLM. *Equal Contribution

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01407 2025-10-06 cs.LG cs.CV

Ultra-Efficient Decoding for End-to-End Neural Compression and Reconstruction

Ethan G. Rogers, Cheng Wang

机构 * Department of Electrical and Computer Engineering(电气与计算机工程系)

Comments 5 pages, 4 figures, NeurIPS 2025 Workshop MLForSys

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.22807 2025-10-06 cs.IR cs.AI

MTRec: Learning to Align with User Preferences via Mental Reward Models

Mengchen Zhao, Yifan Gao, Yaqing Hou, Xiangyang Li, Pengjie Gu, Zhenhua Dong, Ruiming Tang, Yi Cai

机构 * School of Software Engineering, South China University of Technology(华南理工大学软件学院) School of Computer Science and Technology, Dalian University of Technology(大连理工大学计算机科学与技术学院) Huawei Noah’s Ark Lab(华为诺亚实验室) Nanyang Technological University(南洋理工大学)

Journal ref Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.18389 2025-10-06 cs.LG

Towards Provable Emergence of In-Context Reinforcement Learning

Jiuqi Wang, Rohan Chandra, Shangtong Zhang

Comments NeurIPS 2025, 29 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.09650 2025-10-06 cs.CV cs.LG cs.MM cs.RO eess.IV

HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios

Kunyu Peng, Junchao Huang, Xiangsheng Huang, Di Wen, Junwei Zheng, Yufan Chen, Kailun Yang, Jiamin Wu, Chongqing Hao, Rainer Stiefelhagen

机构 * Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院) Beijing Institute of Technology(北京理工大学) Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) Hunan University(湖南大学) Shanghai AI Lab(上海人工智能实验室) HEBUST

Comments Accepted to NeurIPS 2025. The dataset and code are available at https://github.com/KPeng9510/HopaDIFF

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00771 2025-10-06 cs.LG cs.AI

Manipulating 3D Molecules in a Fixed-Dimensional E(3)-Equivariant Latent Space

Zitao Chen, Yinjun Jia, Zitong Tian, Wei-Ying Ma, Yanyan Lan

机构 * Institute for AI Industry Research (AIR), Tsinghua University(人工智能产业研究院(AIR),清华大学) Department of Computer Science and Technology, Tsinghua University(计算机科学与技术系,清华大学) Qiuzhen College, Tsinghua University(启真学院,清华大学)

Comments This version (v2) includes minor edits. The paper has been accepted to NeurIPS 2025. Code is available at: https://github.com/MuZhao2333/MolFLAE

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.11840 2025-10-06 cs.LG math.OC

On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm

Huan Li, Yiming Dong, Zhouchen Lin

机构 * Institute of Robotics and Automatic Information Systems, College of Artificial Intelligence, Nankai University, Tianjin, China(机器人与自动信息系统研究所,人工智能学院,南开大学,天津,中国) National Key Lab of General AI, School of Intelligence Science and Technology, Peking University, Beijing, China(通用人工智能国家重点实验室,智能科学与技术学院,北京大学,北京,中国)

Comments V2: NeurIPS Camera-Ready. V3: expand upon the conference version by incorporating the analysis of NAdamW

详情

展开后加载摘要…

URL PDF HTML 收藏