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 17322
2507.10425 2025-10-27 cs.LG stat.ML

Non-exchangeable Conformal Prediction with Optimal Transport: Tackling Distribution Shifts with Unlabeled Data

Alvaro H. C. Correia, Christos Louizos

机构 * Qualcomm AI Research(高通人工智能研究)

Journal ref Advances in Neural Information Processing Systems 38 (NeurIPS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.23726 2025-10-27 cs.LG cs.AI

System-Embedded Diffusion Bridge Models

Bartlomiej Sobieski, Matthew Tivnan, Yuang Wang, Siyeop Yoon, Pengfei Jin, Dufan Wu, Quanzheng Li, Przemyslaw Biecek

机构 * University of Warsaw(华沙大学) Harvard University(哈佛大学) Massachusetts General Hospital(麻省总医院) Warsaw University of Technology(华沙技术大学)

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.21584 2025-10-27 cs.CL cs.AI cs.CY

Empirical Evidence for Alignment Faking in a Small LLM and Prompt-Based Mitigation Techniques

Jeanice Koorndijk

机构 * Seraphion Technology(塞拉菲昂技术)

Comments NeurIPS RegML Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.15745 2025-10-27 eess.IV cs.LG

InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding

Minsoo Kim, Kyuhong Shim, Jungwook Choi, Simyung Chang

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.14674 2025-10-27 cs.CV

Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models

Ling Li, Yao Zhou, Yuxuan Liang, Fugee Tsung, Jiaheng Wei

机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州)) The Hong Kong University of Science and Technology(香港科学与技术大学)

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.12945 2025-10-27 cs.CV

Metropolis-Hastings Sampling for 3D Gaussian Reconstruction

Hyunjin Kim, Haebeom Jung, Jaesik Park

机构 * UC San Diego(加州大学圣地亚哥分校) Seoul National University(首尔国立大学)

Comments NeurIPS 2025. Project Page: https://hjhyunjinkim.github.io/MH-3DGS

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.09498 2025-10-27 cs.AI

Fast Monte Carlo Tree Diffusion: 100x Speedup via Parallel Sparse Planning

Jaesik Yoon, Hyeonseo Cho, Yoshua Bengio, Sungjin Ahn

Comments 20 pages, 6 figures, NeurIPS 25 Spotlight

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.09033 2025-10-27 cs.CL cs.AI cs.LG

Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning

Haozhen Zhang, Tao Feng, Jiaxuan You

机构 * University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Comments Accepted by NeurIPS 2025. Code is available at https://github.com/ulab-uiuc/Router-R1. Models and Datasets are available at https://huggingface.co/collections/ulab-ai/router-r1-6851bbe099c7a56914b5db03

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.08428 2025-10-27 math.OC cs.LG

Sharper Convergence Rates for Nonconvex Optimisation via Reduction Mappings

Evan Markou, Thalaiyasingam Ajanthan, Stephen Gould

Comments Accepted to NeurIPS 2025 (Spotlight). 43 pages, 12 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.07851 2025-10-27 cs.CL

Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning

Yiju Guo, Wenkai Yang, Zexu Sun, Ning Ding, Zhiyuan Liu, Yankai Lin

Comments Accepted at NeurIPS 2025, camera-ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.07736 2025-10-27 cs.AI

RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards

Jingnan Zheng, Xiangtian Ji, Yijun Lu, Chenhang Cui, Weixiang Zhao, Gelei Deng, Zhenkai Liang, An Zhang, Tat-Seng Chua

Journal ref 39th Conference on Neural Information Processing Systems (NeurIPS 2025). 39th Conference on Neural Information Processing Systems (NeurIPS 2025). 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06958 2025-10-27 cs.CY cs.AI cs.MA

Simulating Society Requires Simulating Thought

Chance Jiajie Li, Jiayi Wu, Zhenze Mo, Ao Qu, Yuhan Tang, Kaiya Ivy Zhao, Yulu Gan, Jie Fan, Jiangbo Yu, Jinhua Zhao, Paul Liang, Luis Alonso, Kent Larson

机构 * MIT Media Lab(麻省理工学院媒体实验室) MIT EECS(麻省理工学院电子工程与计算机科学系) MIT BCS(麻省理工学院生物工程与计算机科学系) MIT IDSS(麻省理工学院国际设计与研究系统) MIT CEE(麻省理工学院土木与环境工程系) MIT DUSP(麻省理工学院设计与科学计划) MIT Architecture(麻省理工学院建筑系) Northeastern University(东北大学) Brown University(布朗大学) McGill University(麦吉尔大学)

Comments NeurIPS 2025 (Position Paper Track)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06072 2025-10-27 cs.RO cs.LG

BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning

Hongyi Zhou, Weiran Liao, Xi Huang, Yucheng Tang, Fabian Otto, Xiaogang Jia, Xinkai Jiang, Simon Hilber, Ge Li, Qian Wang, Ömer Erdinç Yağmurlu, Nils Blank, Moritz Reuss, Rudolf Lioutikov

机构 * Karlsruhe Institute of Technology(卡尔斯鲁厄理工大学) Robotics Institute Germany(德国机器人研究所) Microsoft Research(微软研究院)

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.05282 2025-10-27 cs.CV cs.AI cs.RO

Rectified Point Flow: Generic Point Cloud Pose Estimation

Tao Sun, Liyuan Zhu, Shengyu Huang, Shuran Song, Iro Armeni

机构 * Stanford University(斯坦福大学) NVIDIA Research(NVIDIA研究)

Comments NeurIPS 2025 Camera-ready. Project page: https://rectified-pointflow.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.04723 2025-10-27 cs.AI

Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning

Jiayu Wang, Yifei Ming, Zixuan Ke, Caiming Xiong, Shafiq Joty, Aws Albarghouthi, Frederic Sala

机构 * University of Wisconsin-Madison(威斯康星大学麦迪逊分校) Salesforce AI Research(Salesforce AI研究)

Comments Accepted to NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02489 2025-10-27 cs.RO cs.CV cs.LG

Grasp2Grasp: Vision-Based Dexterous Grasp Translation via Schrödinger Bridges

Tao Zhong, Jonah Buchanan, Christine Allen-Blanchette

机构 * Princeton University(普林斯顿大学) San Jose State University(圣何塞州立大学) Lockheed Martin Corporation(洛克希德·马丁公司)

Comments Accepted at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01728 2025-10-27 cs.LG cs.AI

Principled Data Augmentation for Learning to Solve Quadratic Programming Problems

Chendi Qian, Christopher Morris

机构 * Department of Computer Science(计算机科学系) RWTH Aachen University(亚琛工业大学)

Comments Accepted at NeurIPS 2025 as spotlight

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01084 2025-10-27 cs.CL cs.LG

zip2zip: Inference-Time Adaptive Tokenization via Online Compression

Saibo Geng, Nathan Ranchin, Yunzhen yao, Maxime Peyrard, Chris Wendler, Michael Gastpar, Robert West

机构 * EPFL(瑞士联邦理工学院) Northeastern University(东北大学) Université Grenoble Alpes(格勒诺布尔阿尔卑斯大学) CNRS(法国国家科学研究中心) Grenoble INP(格勒诺布尔INP) LIG(图灵研究所)

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00362 2025-10-27 cs.LG math.OC

FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees

Hoang T. Nguyen, Priya L. Donti

机构 * Massachusetts Institute of Technology(麻省理工学院)

Comments In NeurIPS 2025. Code available at https://github.com/MOSSLab-MIT/FSNet

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.24022 2025-10-27 cs.LG math.OC stat.ML

The Rich and the Simple: On the Implicit Bias of Adam and SGD

Bhavya Vasudeva, Jung Whan Lee, Vatsal Sharan, Mahdi Soltanolkotabi

机构 * Department of Computer Science University of Southern California(计算机科学系 美国南加州大学)

Comments Accepted at NeurIPS 2025; 30 pages, 12 figures, 17 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23811 2025-10-27 cs.CL cs.AI cs.LG

LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions

Hadi Askari, Shivanshu Gupta, Fei Wang, Anshuman Chhabra, Muhao Chen

机构 * University of California, Davis(加州大学戴维斯分校) University of California, Irvine(加州大学伊市分校) University of Southern California(南加州大学) University of South Florida(佛罗里达州立大学)

Comments Neurips 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.22854 2025-10-27 cs.CV

CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting

Kornel Howil, Joanna Waczyńska, Piotr Borycki, Tadeusz Dziarmaga, Marcin Mazur, Przemysław Spurek

Comments Accepted to NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.22535 2025-10-27 cs.CV cs.LG

RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting

Mohamad Hakam Shams Eddin, Yikui Zhang, Stefan Kollet, Juergen Gall

机构 * Institute of Computer Science, University of Bonn(波恩大学计算机科学研究所) Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔人工智能与机器学习研究所) Institute of Bio- and Geosciences Agrosphere (IBG-3), Research Centre Jülich(茹里奇研究中心生物与地质科学农业球面研究所) Centre for High-Performance Scientific Computing in Terrestrial Systems, Geoverbund ABC/J, Jülich(地球系统高性能科学计算中心,Geoverbund ABC/J,茹里奇)

Comments Accepted at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025). Main paper 10 pages, Appendix 54 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.21955 2025-10-27 cs.CV cs.AI

Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs

Insu Lee, Wooje Park, Jaeyun Jang, Minyoung Noh, Kyuhong Shim, Byonghyo Shim

Comments Accepted to NeurIPS 2025 (Spotlight)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.21749 2025-10-27 cs.LG cs.CL

Revisiting Bi-Linear State Transitions in Recurrent Neural Networks

M. Reza Ebrahimi, Roland Memisevic

机构 * Qualcomm AI Research(高通人工智能研究)

Comments Accepted to NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.20922 2025-10-27 cs.MA cs.AI cs.LG

Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective

Yang Zhang, Xinran Li, Jianing Ye, Shuang Qiu, Delin Qu, Xiu Li, Chongjie Zhang, Chenjia Bai

机构 * Tsinghua University(清华大学) The Hong Kong University of Science and Technology(香港科技大学) Washington University in St. Louis(圣路易斯华盛顿大学) City University of Hong Kong(香港城市大学) Fudan University(复旦大学) Institute of Artificial Intelligence (TeleAI)(人工智能研究所) China Telecom(中国电信) Shenzhen Research Institute of Northwestern Polytechnical University(西北工业大学深圳研究院)

Comments Accepted at NIPS'25

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.20749 2025-10-27 cs.AI cs.SE

Can Agents Fix Agent Issues?

Alfin Wijaya Rahardja, Junwei Liu, Weitong Chen, Zhenpeng Chen, Yiling Lou

Comments Accepted by the 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.20280 2025-10-27 stat.ML cs.LG hep-ph

Lorentz Local Canonicalization: How to Make Any Network Lorentz-Equivariant

Jonas Spinner, Luigi Favaro, Peter Lippmann, Sebastian Pitz, Gerrit Gerhartz, Tilman Plehn, Fred A. Hamprecht

机构 * ITP, Heidelberg University, Germany(海德堡大学ITP, 德国) CP3, UCLouvain, Belgium(列日大学CP3, 比利时) IWR, Heidelberg University, Germany(海德堡大学IWR, 德国)

Comments 22 pages, 6 figures, 6 tables. v2: NeurIPS camera-ready version, 23 pages, 6 figures, 7 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.20215 2025-10-27 cs.CL

Dependency Parsing is More Parameter-Efficient with Normalization

Paolo Gajo, Domenic Rosati, Hassan Sajjad, Alberto Barrón-Cedeño

机构 * University of Bologna(博洛尼亚大学) Dalhousie University(达尔豪斯大学)

Comments Accepted at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.18812 2025-10-27 cs.CV

SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models

Ye Sun, Hao Zhang, Henghui Ding, Tiehua Zhang, Xingjun Ma, Yu-Gang Jiang

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏