NeurIPS

Beyond Parallelism: Synergistic Computational Graph Effects in Multi-Head Attention

Haitz Sáez de Ocáriz Borde

机构 * Supermodel 纠错

Comments 16 pages, 4 figures, 6 tables. Accepted at NeurIPS 2025 Workshop on Symmetry and Geometry in Neural Representations

DynaGuide: Steering Diffusion Polices with Active Dynamic Guidance

Maximilian Du, Shuran Song

机构 * Stanford University（斯坦福大学） 纠错

Comments 9 pages main, 21 pages with appendix and citations. 9 figures. Presented at Neurips 2025

FlashMoE: Fast Distributed MoE in a Single Kernel

Osayamen Jonathan Aimuyo, Byungsoo Oh, Rachee Singh

机构 * Cornell University（康奈尔大学） 纠错

Comments To appear at NeurIPS '25

From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications

Yang Cai, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng

机构 * Yale University（耶鲁大学） ； University of Southern California（南加州大学） ； University of Virginia（弗吉尼亚大学） 纠错

Comments NeurIPS 2025. 24 pages. Updated version with more discussions and robustness in the bandit feedback setting

Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations

Chaofan Gan, Yuanpeng Tu, Xi Chen, Tieyuan Chen, Yuxi Li, Mehrtash Harandi, Weiyao Lin

机构 * Shanghai Jiao Tong University（上海交通大学） ； Monash University（墨尔本大学） ； The University of Hong Kong（香港大学） 纠错

Comments NeurIPS 2025, code: https://github.com/ganchaofan0000/DiTF

Private Statistical Estimation via Truncation

Manolis Zampetakis, Felix Zhou

机构 * Yale University（耶鲁大学） 纠错

Comments to appear at NeurIPS'25

Quantum Doubly Stochastic Transformers

Jannis Born, Filip Skogh, Kahn Rhrissorrakrai, Filippo Utro, Nico Wagner, Aleksandros Sobczyk

机构 * IBM Research（IBM研究院） 纠错

Comments NeurIPS 2025 (Spotlight)

Journal ref Advances of Neural Information Processing Systems 2025

MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering

Qiwen Gu, Xufei Wang, Junqiao Zhao, Siyue Tao, Tiantian Feng, Ziqiao Wang, Guang Chen

机构 * School of Computer Science and Technology, Tongji University, Shanghai, China（计算机科学与技术学院，同济大学，上海，中国） ； MOE Key Lab of Embedded System and Service Computing, Tongji University, Shanghai, China（教育部嵌入式系统与服务计算重点实验室，同济大学，上海，中国） ； Shanghai Research Institute for Intelligent Autonomous System, Tongji University, Shanghai, China（上海智能自主系统研究院，同济大学，上海，中国） ； School of Surveying and Geo-Informatics, Tongji University, Shanghai, China（测绘地理信息学院，同济大学，上海，中国） 纠错

Comments 15 pages, 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

Hybrid Training for Enhanced Multi-task Generalization in Multi-agent Reinforcement Learning

Mingliang Zhang, Sichang Su, Chengyang He, Guillaume Sartoretti

机构 * National University of Singapore（新加坡国立大学） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Comments NeurIPS 2025 ARLET Workshop

Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models

Julien Siems, Konstantin Ditschuneit, Winfried Ripken, Alma Lindborg, Maximilian Schambach, Johannes S. Otterbach, Martin Genzel

Journal ref Advances in Neural Information Processing Systems 36 (NeurIPS 2023), 19029-19057

How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?

Tuan Anh Tran, Duy M. H. Nguyen, Hoai-Chau Tran, Michael Barz, Khoa D. Doan, Roger Wattenhofer, Ngo Anh Vien, Mathias Niepert, Daniel Sonntag, Paul Swoboda

Comments Accepted at NeurIPS 2025

Unsupervised Discovery of High-Redshift Galaxy Populations with Variational Autoencoders

Aayush Saxena

Comments 5 Pages, 2 Figures, Accepted at the Machine Learning and the Physical Sciences Workshop at Neural Information Processing Systems 2025 (NeurIPS 2025)

Diffusion-Based Electromagnetic Inverse Design of Scattering Structured Media

Mikhail Tsukerman, Konstantin Grotov, Pavel Ginzburg

Comments Accepted to Machine Learning and the Physical Sciences Workshop, NeurIPS 2025

Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agents

Gauri Kholkar, Ratinder Ahuja

机构 * Pure Storage 纠错

Comments Accepted at 3rd Regulatable ML Workshop at NEURIPS 2025

Inference-Time Hyper-Scaling with KV Cache Compression

Adrian Łańcucki, Konrad Staniszewski, Piotr Nawrot, Edoardo M. Ponti

Comments Accepted to NeurIPS 2025

FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning

Li Zhang, Zhongxuan Han, Xiaohua Feng, Jiaming Zhang, Yuyuan Li, Chaochao Chen

机构 * Zhejiang University（浙江大学） ； Hangzhou Dianzi University（杭州电子科技大学） 纠错

Comments Accepted by NeurIPS 2025

LiveStar: Live Streaming Assistant for Real-World Online Video Understanding

Zhenyu Yang, Kairui Zhang, Yuhang Hu, Bing Wang, Shengsheng Qian, Bin Wen, Fan Yang, Tingting Gao, Weiming Dong, Changsheng Xu

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； University of Chinese Academy of Sciences（中国科学院大学） ； ShanghaiTech University（上海科技大学） ； Kuaishou Technology（快手科技） ； Peng Cheng Laboratory（鹏城实验室） 纠错

Comments NeurIPS 2025 Accepted

ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining

Xincheng Yao, Yan Luo, Zefeng Qian, Chongyang Zhang

机构 * School of Information Science and Electronic Engineering, Shanghai Jiao Tong University（上海交通大学信息科学与电子工程学院） ； MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（上海交通大学人工智能MOE重点实验室） ； College of Artificial Intelligence, Nanjing Agricultural University（南京农业大学人工智能学院） ； Key Laboratory of Livestock Farming Equipment, Ministry of Agriculture and Rural Affairs, Nanjing Agricultural University（南京农业大学农业机械化关键实验室） 纠错

Comments Accepted by NeurIPS 2025

A differentiable model of supply-chain shocks

Saad Hamid, José Moran, Luca Mungo, Arnau Quera-Bofarull, Sebastian Towers

机构 * Aioi R&D Lab（Aioi 研发实验室） ； Macrocosm ； Institute for New Economic Thinking at the Oxford Martin School, University of Oxford（牛津大学奥克斯马丁学院新经济思想研究所） ； FLAIR, Foerster Lab for AI Research, University of Oxford（牛津大学FLAIR人工智能研究实验室） ； Department of Engineering, University of Oxford（牛津大学工程学院） 纠错

Comments Accepted to 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Differentiable Systems and Scientific Machine Learning (EurIPS)

4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos

Mengqi Guo, Bo Xu, Yanyan Li, Gim Hee Lee

机构 * National University of Singapore（新加坡国立大学） ； Wuhan University（武汉大学） 纠错

Comments 17 pages, 5 figures

Journal ref NeurIPS 2025

FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction

Jiang Lin, Xinyu Chen, Song Wu, Zhiqiu Zhang, Jizhi Zhang, Ye Wang, Qiang Tang, Qian Wang, Jian Yang, Zili Yi

机构 * Nanjing University（南京大学） ； JIUTIAN Research（JIUTIAN研究） ； University of British Columbia（不列颠哥伦比亚大学） ； Jilin University（吉林大学） 纠错

Comments Accepted by NIPS 2025

Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start

Fuyang Liu, Jiaqi Xu, Xiaowei Hu

机构 * South China University of Technology（华南理工大学） ； Nanjing University of Science and Technology（南京理工大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

Comments Accepted by NeurIPS 2025

Order-Level Attention Similarity Across Language Models: A Latent Commonality

Jinglin Liang, Jin Zhong, Shuangping Huang, Yunqing Hu, Huiyuan Zhang, Huifang Li, Lixin Fan, Hanlin Gu

机构 * South China University of Technology（华南理工大学） ； Pazhou Laboratory（Pazhou实验室） ； Zhuzhou CRRC Times Electric Co.（株洲 CRRC 时代电子公司） ； China Telecom Research Institute（中国电信研究院） ； WeBank（我们银行） ； The Hong Kong University of Science and Technology（香港科技大学） 纠错

Comments Accepted by NeurIPS 2025

8bit-GPT: Exploring Human-AI Interaction on Obsolete Macintosh Operating Systems

Hala Sheta

机构 * Department of Computer Science University of Waterloo（计算机科学系大学水力学院） 纠错

Comments NeurIPS Creative AI Track 2025: Humanity

Pluralistic Behavior Suite: Stress-Testing Multi-Turn Adherence to Custom Behavioral Policies

Prasoon Varshney, Makesh Narsimhan Sreedhar, Liwei Jiang, Traian Rebedea, Christopher Parisien

机构 * NVIDIA 纠错

Comments Accepted at the Multi-Turn Interactions workshop at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

You Need Reasoning to Learn Reasoning: The Limitations of Label-Free RL in Weak Base Models

Shuvendu Roy, Hossein Hajimirsadeghi, Mengyao Zhai, Golnoosh Samei

机构 * Sea AI Lab（海思人工智能实验室） ； National University of Singapore（新加坡国立大学） ； Singapore Management University（新加坡管理学院） 纠错

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: MATH-AI

A Standardized Benchmark for Multilabel Antimicrobial Peptide Classification

Sebastian Ojeda, Rafael Velasquez, Nicolás Aparicio, Juanita Puentes, Paula Cárdenas, Nicolás Andrade, Gabriel González, Sergio Rincón, Carolina Muñoz-Camargo, Pablo Arbeláez

机构 * Universidad de los Andes（圣何塞安德斯大学） 纠错

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025). Camera-ready version. Code: https://github.com/BCV-Uniandes/ESCAPE. Dataset DOI: https://doi.org/10.7910/DVN/C69MCD

Blind Strong Gravitational Lensing Inversion: Joint Inference of Source and Lens Mass with Score-Based Models

Gabriel Missael Barco, Ronan Legin, Connor Stone, Yashar Hezaveh, Laurence Perreault-Levasseur

机构 * Université de Montréal（蒙特利尔大学） ； Mila ； Ciela Institute（Ciela研究所） ； CCA, Flatiron Institute（CCA与Flatiron研究所） ； Perimeter Institute for Theoretical Physics（理论物理研究所） ； Trottier Space Institute（Trottier空间研究所） 纠错

Comments 18 pages, 9 figures, 1 table. Accepted to the NeurIPS 2025 Workshop on Machine Learning and the Physical Sciences

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

Andrew M. Bean, Ryan Othniel Kearns, Angelika Romanou, Franziska Sofia Hafner, Harry Mayne, Jan Batzner, Negar Foroutan, Chris Schmitz, Karolina Korgul, Hunar Batra, Oishi Deb, Emma Beharry, Cornelius Emde, Thomas Foster, Anna Gausen, María Grandury, Simeng Han, Valentin Hofmann, Lujain Ibrahim, Hazel Kim, Hannah Rose Kirk, Fangru Lin, Gabrielle Kaili-May Liu, Lennart Luettgau, Jabez Magomere, Jonathan Rystrøm, Anna Sotnikova, Yushi Yang, Yilun Zhao, Adel Bibi, Antoine Bosselut, Ronald Clark, Arman Cohan, Jakob Foerster, Yarin Gal, Scott A. Hale, Inioluwa Deborah Raji, Christopher Summerfield, Philip H. S. Torr, Cozmin Ududec, Luc Rocher, Adam Mahdi

机构 * University of Oxford（牛津大学） ； EPFL（苏黎世联邦理工学院） ； Weizenbaum Institute Berlin（柏林Weizenbaum研究所） ； Technical University Munich（慕尼黑技术大学） ； Centre for Digital Governance, Hertie School（赫尔姆霍兹学院数字治理中心） ； Stanford University（斯坦福大学） ； UK AI Security Institute（英国人工智能安全研究所） ； SomosNLP ； Universdad Politécnica de Madrid（马德里理工大学） ； Yale University（耶鲁大学） ； Allen Institute for AI（人工智能研究所） ； University of Washington（华盛顿大学） ； Meedan ； UC Berkeley（加州大学伯克利分校） 纠错

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Track on Datasets and Benchmarks

STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology

Barathi Subramanian, Rathinaraja Jeyaraj, Mitchell Nevin Peterson, Terry Guo, Nigam Shah, Curtis Langlotz, Andrew Y. Ng, Jeanne Shen

Comments 37 pages, 18 figures, Accepted in NeurIPS 2025