NeurIPS

A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation

Yiwen Tu, Pingbang Hu, Jiaqi Ma

机构 * University of Michigan, Ann Arbor（密歇根大学安阿伯分校） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

When One Modality Sabotages the Others: A Diagnostic Lens on Multimodal Reasoning

Chenyu Zhang, Minsol Kim, Shohreh Ghorbani, Jingyao Wu, Rosalind Picard, Patricia Maes, Paul Pu Liang

机构 * Harvard University（哈佛大学） ； MIT Media Lab（麻省理工学院媒体实验室） 纠错

Comments Accepted at the Multimodal Algorithmic Reasoning (MAR) Workshop, NeurIPS 2025

Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold

Xinghan Li, Haodong Wen, Kaifeng Lyu

机构 * Tsinghua University（清华大学） ； Institute for Interdisciplinary Information Sciences（交叉信息研究院） 纠错

Journal ref The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)

VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models

Zhicheng Zhang, Weicheng Wang, Yongjie Zhu, Wenyu Qin, Pengfei Wan, Di Zhang, Jufeng Yang

机构 * Nankai University（南开大学） ； Pengcheng Laboratory（鹏城实验室） ； Kuaishou Technology（快手科技） ； Nankai International Advanced Research Institute (SHENZHEN·FUTIAN)（南开国际先进研究院（深圳·福田）） 纠错

Comments 41 pages, 26 figures

Journal ref NeurIPS 2025

Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs

Georgios Tzannetos, Parameswaran Kamalaruban, Adish Singla

机构 * MPI-SWS（马克斯·普朗克所际研究所） 纠错

Comments NeurIPS'25 paper

Differentiable Hierarchical Visual Tokenization

Marius Aasan, Martine Hjelkrem-Tan, Nico Catalano, Changkyu Choi, Adín Ramírez Rivera

Comments NeurIPS 2025 Spotlight

Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning

Yixiu Mao, Yun Qu, Qi Wang, Xiangyang Ji

机构 * Department of Automation, Tsinghua University（自动化系，清华大学） 纠错

Comments Accepted to NeurIPS 2025 (Spotlight)

DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding

Zixuan Liu, Siavash H. Khajavi, Guangkai Jiang

机构 * Department of Computer Science（计算机科学系） ； Tulane University（Tulane 大学） ； Department of Industrial Engineering and Management（工业工程与管理系） ； Aalto University（Aalto 大学） 纠错

Comments Advances in Neural Information Processing Systems 2025 (NeurIPS 2025), Poster, https://neurips.cc/virtual/2025/loc/san-diego/poster/121400

Human-Machine Ritual: Synergic Performance through Real-Time Motion Recognition

Zhuodi Cai, Ziyu Xu, Juan Pampin

机构 * Department of Digital Arts and Experimental Media (DXARTS), University of Washington（数字艺术与实验媒体系（DXARTS）、华盛顿大学） 纠错

Comments 8 pages, 5 figures. Camera-ready manuscript for the Creative AI Track of NeurIPS 2025

LTD-Bench: Evaluating Large Language Models by Letting Them Draw

Liuhao Lin, Ke Li, Zihan Xu, Yuchen Shi, Yulei Qin, Yan Zhang, Xing Sun, Rongrong Ji

机构 * Youtu-Agent Team（优图智能团队） 纠错

Comments Accepted by NeurIPS 2025

Cycle-Sync: Robust Global Camera Pose Estimation through Enhanced Cycle-Consistent Synchronization

Shaohan Li, Yunpeng Shi, Gilad Lerman

机构 * School of Mathematics, University of Minnesota（明尼苏达大学数学系） ； Department of Mathematics, University of California, Davis（加州大学戴维斯分校数学系） 纠错

Comments NeurIPS 2025 spotlight paper

Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness

Yuheng Zhao, Yu-Hu Yan, Kfir Yehuda Levy, Peng Zhao

Comments NeurIPS 2025

QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code

Hainan Fang, Yuanbo Wen, Jun Bi, Yihan Wang, Tonghui He, Yanlin Tang, Di Huang, Jiaming Guo, Rui Zhang, Qi Guo, Yunji Chen

机构 * State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China（中国科学院计算技术研究所处理器重点实验室，北京，中国） ； University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国） 纠错

Comments Accepted at NeurIPS 2025

GRAM-DTI: adaptive multimodal representation learning for drug target interaction prediction

Feng Jiang, Amina Mollaysa, Hehuan Ma, Tommaso Mansi, Junzhou Huang, Mangal Prakash, Rui Liao

机构 * University of Texas at Arlington（德克萨斯理工大学） ； Johnson & Johnson Innovative Medicine（强生创新医学） 纠错

Journal ref NeurIPS 2025 2nd Workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences

Generative World Models of Tasks: LLM-Driven Hierarchical Scaffolding for Embodied Agents

Brennen Hill

机构 * Department of Computer Science University of Wisconsin-Madison（计算机科学系威斯康星大学麦迪逊分校） 纠错

Comments In the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Embodied World Models for Decision Making (EWM)

The Physical Basis of Prediction: World Model Formation in Neural Organoids via an LLM-Generated Curriculum

Brennen Hill

机构 * Department of Computer Science University of Wisconsin-Madison（计算机科学系 威斯康星大学麦迪逊分校） 纠错

Comments Published in the proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Scaling Environments for Agents (SEA). Additionally accepted for presentation in NeurIPS 2025 Workshop: Embodied World Models for Decision Making

Co-Evolving Complexity: An Adversarial Framework for Automatic MARL Curricula

Brennen Hill

机构 * Department of Computer Science University of Wisconsin-Madison（计算机科学系 明尼苏达大学） 纠错

Comments Published in the proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Scaling Environments for Agents (SEA)

Prior-Guided Flow Matching for Target-Aware Molecule Design with Learnable Atom Number

Jingyuan Zhou, Hao Qian, Shikui Tu, Lei Xu

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院） 纠错

Comments Accepted by NeurIPS 2025

DIsoN: Decentralized Isolation Networks for Out-of-Distribution Detection in Medical Imaging

Felix Wagner, Pramit Saha, Harry Anthony, J. Alison Noble, Konstantinos Kamnitsas

机构 * Department of Engineering Science, University of Oxford（工程科学系，牛津大学） 纠错

Comments Accepted at NeurIPS 2025

Reliably Detecting Model Failures in Deployment Without Labels

Viet Nguyen, Changjian Shui, Vijay Giri, Siddharth Arya, Amol Verma, Fahad Razak, Rahul G. Krishnan

Comments 44 pages, 9 figures, 12 tables. Accepted at NeurIPS 2025. Code available at https://github.com/teivng/d3m

From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit

Valérie Costa, Thomas Fel, Ekdeep Singh Lubana, Bahareh Tolooshams, Demba Ba

机构 * EPFL（瑞士联邦理工学院） ； Kempner Institute, Harvard University（哈佛大学凯普纳研究所） ； CBS-NTT Program in Physics of Intelligence, Harvard University（哈佛大学物理智能CBSTNTT项目） ； Physics of Artificial Intelligence Group, NTT Research, Inc., Sunnyvale, CA, USA（NTT研究公司人工智能物理研究组） ； University of Alberta（阿尔伯塔大学） ； Alberta Machine Intelligence Institute (Amii)（阿尔伯塔人工智能研究所） ； SEAS, Harvard University（哈佛大学工程与应用科学学院） 纠错

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

MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing Solver

Yuepeng Zheng, Fu Luo, Zhenkun Wang, Yaoxin Wu, Yu Zhou

机构 * College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院） ； School of Automation and Intelligent Manufacturing, Southern University of Science and Technology（南方科技大学自动化与智能制造学院） ； Guangdong Provincial Key Laboratory of Fully Actuated System Control Theory and Technology, Southern University of Science and Technology（广东省全驱动系统控制理论与技术重点实验室，南方科技大学） ； Department of Industrial Engineering and Innovation Sciences, Eindhoven University of Technology（埃因霍温理工大学工业工程与创新科学系） 纠错

Comments Accepted at NeurIPS 2025

SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents

Ibragim Badertdinov, Alexander Golubev, Maksim Nekrashevich, Anton Shevtsov, Simon Karasik, Andrei Andriushchenko, Maria Trofimova, Daria Litvintseva, Boris Yangel

机构 * Nebius 纠错

Comments Dataset: https://huggingface.co/datasets/nebius/SWE-rebench, SWE-rebench leaderboard https://swe-rebench.com NeurIPS 2025

A Unified Framework for Variable Selection in Model-Based Clustering with Missing Not at Random

Binh H. Ho, Long Nguyen Chi, TrungTin Nguyen, Binh T. Nguyen, Van Ha Hoang, Christopher Drovandi

机构 * Faculty of Mathematics and Computer Science, University of Science, Ho Chi Minh City, Vietnam（越南科技大学数学与计算机科学学院） ； Vietnam National University Ho Chi Minh City, Vietnam（越南胡志明市国家大学） ； School of Information and Communications Technology, Hanoi University of Science and Technology, Ha Noi, Vietnam（河内科学技术大学信息与通信技术学院） ； ARC Centre of Excellence for the Mathematical Analysis of Cellular Systems（细胞系统数学分析卓越中心） ； School of Mathematical Sciences, Queensland University of Technology, Brisbane City, Australia（昆士兰科技大学数学科学学院） 纠错

Comments Binh H. Ho, Long Nguyen Chi, and TrungTin Nguyen are co-first authors. Correct final typos for the NeurIPS 2025 camera-ready version

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

Dense Backpropagation Improves Training for Sparse Mixture-of-Experts

Ashwinee Panda, Vatsal Baherwani, Zain Sarwar, Benjamin Therien, Sambit Sahu, Tom Goldstein, Supriyo Chakraborty

机构 * University of Maryland（马里兰大学） ； Capital One ； University of Chicago（芝加哥大学） ； Mila – Quebec AI Institute（魁北克人工智能研究所） 纠错

Comments NeurIPS 2025

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing

Fengxiang Wang, Yulin Wang, Mingshuo Chen, Haiyan Zhao, Yangang Sun, Shuo Wang, Hongzhen Wang, Di Wang, Long Lan, Wenjing Yang, Jing Zhang

机构 * College of Computer Science and Technology, National University of Defense Technology, China（国防科技大学计算机科学与技术学院） ； Tsinghua University, China（清华大学） ； Beijing University of Posts and Telecommunications, China（北京邮电大学） ； School of Computer Science, Wuhan University, China（武汉大学计算机学院） ； Zhongguancun Academy, China（中关村学院） 纠错

Comments NeurIPS 2025

Position: Bridge the Gaps between Machine Unlearning and AI Regulation

Bill Marino, Meghdad Kurmanji, Nicholas D. Lane

机构 * University of Cambridge（剑桥大学） 纠错

Comments NeurIPS 2025 Position Paper Track Oral, https://openreview.net/forum?id=0ngi2StMwC

Image Super-Resolution with Guarantees via Conformalized Generative Models

Eduardo Adame, Daniel Csillag, Guilherme Tegoni Goedert

机构 * School of Applied Mathematics（应用数学学院） ； Getulio Vargas Foundation（格尔维斯基金会） 纠错

Comments To appear at NeurIPS 2025. 17 pages, 7 figures

Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning

Chaofan Lin, Jiaming Tang, Shuo Yang, Hanshuo Wang, Tian Tang, Boyu Tian, Ion Stoica, Song Han, Mingyu Gao

机构 * Tsinghua University（清华大学） ； Massachusetts Institute of Technology（麻省理工学院） ； University of California, Berkeley（加州大学伯克利分校） 纠错

Comments To appear on NeurIPS 2025 (spotlight)

On Extending Direct Preference Optimization to Accommodate Ties

Jinghong Chen, Guangyu Yang, Weizhe Lin, Jingbiao Mei, Bill Byrne

机构 * Department of Engineering University of Cambridge（工程系剑桥大学） 纠错

Comments 24 pages, NeurIPS 2025