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
2505.18522 2025-10-27 cs.CL

How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation

Xin Lu, Yanyan Zhao, Si Wei, Shijin Wang, Bing Qin, Ting Liu

机构 * Research Center for Social Computing and Interactive Robotics(社会计算与交互机器人研究中心) Harbin Institute of Technology(哈尔滨工业大学) iFLYTEK Co., Ltd(iFLYTEK公司)

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.18512 2025-10-27 cs.IR cs.AI cs.CL cs.LG

AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking

Soyoung Yoon, Gyuwan Kim, Gyu-Hwung Cho, Seung-won Hwang

Comments Accepted at NeurIPS 2025. The first two authors contributed equally. Author order is randomly determined via coin toss

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17859 2025-10-27 cs.LG cs.AI stat.ML

Scalable Valuation of Human Feedback through Provably Robust Model Alignment

Masahiro Fujisawa, Masaki Adachi, Michael A. Osborne

机构 * The University of Osaka(大阪大学) Lattice Lab, Toyota Motor Corporation(丰田公司Lattice实验室) Machine Learning Research Group, University of Oxford(牛津大学机器学习研究组) RIKEN AIP(理化学研究所AIP)

Comments Accepted by the 39th Conference on Neural Information Processing Systems (NeurIPS2025), 49 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17761 2025-10-27 cs.LG

Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models

Benjamin Walker, Lingyi Yang, Nicola Muca Cirone, Cristopher Salvi, Terry Lyons

机构 * Mathematical Institute, University of Oxford(牛津大学数学院) Department of Mathematics, Imperial College London(伦敦帝国理工学院数学系)

Comments 32 pages, 5 figures

Journal ref Proceedings of the Thirty-Ninth Annual Conference on Neural Information Processing Systems, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17749 2025-10-27 cs.LG cs.AI

Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement Learning

Ghada Sokar, Pablo Samuel Castro

机构 * Google DeepMind(谷歌DeepMind)

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.16548 2025-10-27 cs.LG stat.ML

Incremental Sequence Classification with Temporal Consistency

Lucas Maystre, Gabriel Barello, Tudor Berariu, Aleix Cambray, Rares Dolga, Alvaro Ortega Gonzalez, Andrei Nica, David Barber

机构 * UiPath(UiPath公司) UCL(大学学院)

Comments To be presented as a spotlight paper at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.15657 2025-10-27 cs.LG cs.AI

LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought

Cheng Yan, Felix Mohr, Tom Viering

机构 * Delft University of Technology(代尔夫特理工大学) Universidad de La Sabana(拉萨芭纳大学)

Comments Accepted at NeurIPS 2025 Datasets & Benchmarks Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13181 2025-10-27 cs.CL cs.SD eess.AS

Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space

Zhengrui Ma, Yang Feng, Chenze Shao, Fandong Meng, Jie Zhou, Min Zhang

机构 * Key Laboratory of Intelligent Information Processing Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所智能信息处理重点实验室) University of Chinese Academy of Sciences(中国科学院大学) Pattern Recognition Center, WeChat AI, Tencent Inc(腾讯人工智能研究院模式识别中心) School of Future Science and Engineering, Soochow University(苏州大学未来科学与工程学院)

Comments NeurIPS 2025; Demos and code are available at https://github.com/ictnlp/SLED-TTS

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.12448 2025-10-27 cs.CV

SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning

Yang Liu, Ming Ma, Xiaomin Yu, Pengxiang Ding, Han Zhao, Mingyang Sun, Siteng Huang, Donglin Wang

机构 * Westlake University(西湖大学) Zhejiang University(浙江大学) Harbin Institute of Technology(哈尔滨工业大学) The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) Shanghai Innovation Institute(上海创新研究院)

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.11475 2025-10-27 cs.CL cs.AI cs.LG

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages

Zhilin Wang, Jiaqi Zeng, Olivier Delalleau, Hoo-Chang Shin, Felipe Soares, Alexander Bukharin, Ellie Evans, Yi Dong, Oleksii Kuchaiev

机构 * NVIDIA

Comments NeurIPS 2025 Datasets and Benchmarks Track Camera Ready, 46 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.11217 2025-10-27 cs.SD cs.AI cs.CV cs.MM eess.AS

Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization

Yanhao Jia, Ji Xie, S Jivaganesh, Hao Li, Xu Wu, Mengmi Zhang

机构 * Nanyang Technological University, Singapore(南洋理工大学) Peking University, China(北京大学) Shenzhen University, China(深圳大学)

Comments NeurIPS 2025, Spotlight

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.10704 2025-10-27 cs.LG

ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data

Patryk Marszałek, Tomasz Kuśmierczyk, Witold Wydmański, Jacek Tabor, Marek Śmieja

机构 * Faculty of Mathematics and Computer Science, Jagiellonian University(数学与计算机科学学院,杰团大学) Doctoral School of Exact and Natural Sciences, Jagiellonian University(精确与自然科学博士学院,杰团大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.05892 2025-10-27 cs.CV cs.LG

Register and [CLS] tokens yield a decoupling of local and global features in large ViTs

Alexander Lappe, Martin A. Giese

机构 * Hertie Institute, University Clinics Tübingen(海德堡大学诊所赫尔蒂研究所) IMPRS-IS(马克斯·普朗克研究所)

Journal ref NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.14882 2025-10-27 cs.LG cs.CV stat.ML

Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness

Mojtaba Kolahdouzi, Hatice Gunes, Ali Etemad

机构 * Department of Electrical and Computer Engineering, Queen’s University(皇后大学电气与计算机工程系) Department of Computer Science and Technology, University of Cambridge(剑桥大学计算机科学与技术系)

Comments Accepted in NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.09702 2025-10-27 cs.AI

MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?

Yunxiang Zhang, Muhammad Khalifa, Shitanshu Bhushan, Grant D Murphy, Lajanugen Logeswaran, Jaekyeom Kim, Moontae Lee, Honglak Lee, Lu Wang

机构 * University of Michigan(密歇根大学) LG AI Research(LG人工智能研究) University of Illinois at Chicago(伊利诺伊大学香槟分校)

Comments NeurIPS 2025 Datasets and Benchmarks Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.22330 2025-10-27 cs.CR cs.CV

WMCopier: Forging Invisible Image Watermarks on Arbitrary Images

Ziping Dong, Chao Shuai, Zhongjie Ba, Peng Cheng, Zhan Qin, Qinglong Wang, Kui Ren

机构 * The State Key Laboratory of Blockchain and Data Security, Zhejiang University(区块链与数据安全国家重点实验室,浙江大学) Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新技术区(滨江)区块链与数据安全研究院)

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.20083 2025-10-27 cs.CL

Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching

Benjamin Minixhofer, Ivan Vulić, Edoardo Maria Ponti

机构 * University of Cambridge(剑桥大学) University of Edinburgh(爱丁堡大学)

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.15114 2025-10-27 cs.LG

DeCaFlow: A deconfounding causal generative model

Alejandro Almodóvar, Adrián Javaloy, Juan Parras, Santiago Zazo, Isabel Valera

Comments 55 pages, 29 figures. Spotlight at NeurIPS 2025. Camera-ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.12919 2025-10-27 cs.LG

Continuous Simplicial Neural Networks

Aref Einizade, Dorina Thanou, Fragkiskos D. Malliaros, Jhony H. Giraldo

机构 * LTCI, Télécom Paris Institut Polytechnique de Paris(巴黎理工信息计算学院) EPFL, Lausanne, Switzerland(瑞士洛桑联邦理工学院) CentraleSupélec, Inria Université Paris-Saclay(中央超导学院、法国国家信息与自动化技术研究所、巴黎萨克雷大学)

Comments 20 pages, 7 figures, Accepted at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.11544 2025-10-27 cs.CV

AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition

Parsa Rahimi, Damien Teney, Sebastien Marcel

机构 * EPFL(苏黎世联邦理工学院) Idiap(日内瓦人工智能研究所) UNIL(日内瓦大学)

Comments Accepted to NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.10799 2025-10-27 cs.LG

Fixed-Point RNNs: Interpolating from Diagonal to Dense

Sajad Movahedi, Felix Sarnthein, Nicola Muca Cirone, Antonio Orvieto

机构 * ELLIS Institute Tuebingen(图宾根ELLIS研究所) Max Planck Institute for Intelligent Systems(智能系统马克斯·普朗克研究所) Department of Mathematics, Imperial College London(伦敦帝国学院数学系)

Comments NeurIPS 2025 (Spotlight)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.12171 2025-10-27 cs.LG cs.AI cs.CL

GoRA: Gradient-driven Adaptive Low Rank Adaptation

Haonan He, Peng Ye, Yuchen Ren, Yuan Yuan, Luyang Zhou, Shucun Ju, Lei Chen

机构 * University of Science and Technology of China(中国科学技术大学) Institute of Intelligent Machines, HFIPS, Chinese Academy of Sciences(中国科学院智能机械研究所) Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Fudan University(复旦大学) The Chinese University of Hong Kong(香港中文大学) University of Sydney(悉尼大学) Anhui Disaster Warning & Agrometeorological Information Center(安徽省灾害预警与农业气象信息中心)

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.11546 2025-10-27 cs.CL

DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection

Yingli Shen, Wen Lai, Shuo Wang, Xueren Zhang, Kangyang Luo, Alexander Fraser, Maosong Sun

机构 * Dept. of Comp. Sci. & Tech., Tsinghua University(清华大学计算机科学与技术系) Technical University of Munich(慕尼黑技术大学) Munich Center for Machine Learning(慕尼黑机器学习中心) ModelBest Inc.(ModelBest公司) BNRist Center, Institute for AI, Tsinghua University(清华大学人工智能研究院脑神经与认知科学中心) Jiangsu Collaborative Innovation Center for Language Ability, Jiangsu Normal University(江苏省语言能力协同创新中心,江苏师范大学)

Comments NeurIPS 2025 Datasets and Benchmarks Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.00739 2025-10-27 stat.ML cs.LG

An Efficient Orlicz-Sobolev Approach for Transporting Unbalanced Measures on a Graph

Tam Le, Truyen Nguyen, Hideitsu Hino, Kenji Fukumizu

机构 * Institute of Statistical Mathematics(统计数学研究所) University of Akron(阿克隆大学)

Comments to appear in Neural Information Processing Systems (NeurIPS), 2025. [spotlight]

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.01015 2025-10-27 cs.CV cs.CR

Boosting Adversarial Transferability with Spatial Adversarial Alignment

Zhaoyu Chen, Haijing Guo, Kaixun Jiang, Jiyuan Fu, Xinyu Zhou, Dingkang Yang, Hao Tang, Bo Li, Wenqiang Zhang

机构 * College of Intelligent Robotics and Advanced Manufacturing, Fudan University(智能机器人与先进制造学院,复旦大学) College of Computer Science and Artificial Intelligence, Fudan University(计算机科学与人工智能学院,复旦大学) China Southern Power Grid Artificial Intelligence Technology Co., Ltd.(中国南方电网人工智能技术有限公司) School of Computer Science, Peking University(北京大学计算机学院) vivo Mobile Communication Co., Ltd.(vivo移动通信有限公司)

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.09805 2025-10-27 cs.LG cs.AI cs.SI

Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness-Generalization Perspective

Ming Gu, Zhuonan Zheng, Sheng Zhou, Meihan Liu, Jiawei Chen, Tanyu Qiao, Liangcheng Li, Jiajun Bu

机构 * Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, Zhejiang University(浙江可及感知与智能系统重点实验室,浙江大学) College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院) School of Software Technology, Zhejiang University(浙江大学软件学院) China University of Mining and Technology(中国矿业大学) Department of Computer Science, New York University Shanghai(纽约大学上海分校计算机科学系)

Comments 36 pages. Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.00661 2025-10-27 cs.LG cs.AI cs.MA cs.SY eess.SY math.OC

Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning

Emile Anand, Ishani Karmarkar, Guannan Qu

机构 * Georgia Institute of Technology(佐治亚理工学院) Stanford University(斯坦福大学) Carnegie Mellon University(卡内基梅隆大学)

Comments 53 pages. AAAI 2025 MARW Best Paper Award. Accepted at NeurIPS 2025 (spotlight)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.19315 2025-10-27 cs.AI cs.LG q-bio.NC

Brain-like Variational Inference

Hadi Vafaii, Dekel Galor, Jacob L. Yates

机构 * Redwood Center for Theoretical Neuroscience, UC Berkeley(伯克利大学红木理论神经科学中心)

Comments To appear at NeurIPS 2025: https://openreview.net/forum?id=573IcLusXq

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.10587 2025-10-27 cs.CV cs.LG

TopoFR: A Closer Look at Topology Alignment on Face Recognition

Jun Dan, Yang Liu, Jiankang Deng, Haoyu Xie, Siyuan Li, Baigui Sun, Shan Luo

机构 * Zhejiang University(浙江大学) FaceChain Community(FaceChain社区) King’s College London(伦敦国王学院) Imperial College London(伦敦帝国学院) Alibaba Group(阿里巴巴集团)

Comments Accepted by NeurIPS 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.03119 2025-10-27 cs.LG

Spatial-Aware Decision-Making with Ring Attractors in Reinforcement Learning Systems

Marcos Negre Saura, Richard Allmendinger, Wei Pan, Theodore Papamarkou

机构 * The University of Manchester(曼彻斯特大学) PolyShape

Comments Accepted at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏