NeurIPS

Separating the what and how of compositional computation to enable reuse and continual learning

Haozhe Shan, Sun Minni, Lea Duncker

机构 * Center for Theoretical Neuroscience（理论神经科学中心） ； Department of Computer Science（计算机科学系） ； Columbia University（哥伦比亚大学） ； Department of Neuroscience（神经科学系） 纠错

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

UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset

Chen Zhao, En Ci, Yunzhe Xu, Tiehan Fan, Shanyan Guan, Yanhao Ge, Jian Yang, Ying Tai

机构 * State Key Laboratory of Novel Software Technology, Nanjing University, China（南京大学新型软件技术国家重点实验室） ； vivo Mobile Communication Co., Ltd., China（vivo移动通信有限公司） 纠错

Comments Accepted by NeurIPS 2025

Finding the Sweet Spot: Trading Quality, Cost, and Speed During Inference-Time LLM Reflection

Jack Butler, Nikita Kozodoi, Zainab Afolabi, Brian Tyacke, Gaiar Baimuratov

机构 * Amazon Web Services（亚马逊网络服务） ； Zalando 纠错

Journal ref Neural Information Processing Systems (NeurIPS 2025) Workshop: Efficient Reasoning

Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging

Ibrahim Ethem Hamamci, Sezgin Er, Suprosanna Shit, Hadrien Reynaud, Dong Yang, Pengfei Guo, Marc Edgar, Daguang Xu, Bernhard Kainz, Bjoern Menze

机构 * University of Zurich（苏黎世大学） ； NVIDIA ； Imperial College London（伦敦帝国理工学院） ； FAU Erlangen-Nürnberg（埃尔朗根-纽伦堡大学） 纠错

Comments NeurIPS 2025

MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation

Yang Han, Pengyu Wang, Kai Yu, Xin Chen, Lu Chen

机构 * X-LANCE Lab, School of Computer Science MoE Key Lab of Artificial Intelligence, SJTU AI Institute Shanghai Jiao Tong University, Shanghai, China（X-LANCE实验室，计算机科学学院，人工智能教育部重点实验室，上海交通大学人工智能研究院，上海，中国） ； Suzhou Laboratory, Suzhou, China（苏州实验室，苏州，中国） ； Shanghai Innovation Institute, Shanghai, China（上海创新研究院，上海，中国） ； Jiangsu Key Lab of Language Computing, Suzhou, China（江苏省语言计算重点实验室，苏州，中国） 纠错

Comments NeurIPS 2025, We provide the data and code at https://github.com/OpenDFM/MS-BART

OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects

Mark He Huang, Lin Geng Foo, Christian Theobalt, Ying Sun, De Wen Soh

机构 * Singapore University of Technology and Design（新加坡科技设计大学） ； Max Planck Institute for Informatics（马克斯·普朗克研究所（信息学）） 纠错

Comments NeurIPS 2025 (Spotlight)

Resounding Acoustic Fields with Reciprocity

Zitong Lan, Yiduo Hao, Mingmin Zhao

机构 * University of Pennsylvania（宾夕法尼亚大学） 纠错

Comments NeurIPS 2025

Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models

Tomáš Souček, Sylvestre-Alvise Rebuffi, Pierre Fernandez, Nikola Jovanović, Hady Elsahar, Valeriu Lacatusu, Tuan Tran, Alexandre Mourachko

机构 * Meta FAIR ； ETH Zurich（苏黎世联邦理工学院） 纠错

Comments NeurIPS 2025

Ask a Strong LLM Judge when Your Reward Model is Uncertain

Zhenghao Xu, Qin Lu, Qingru Zhang, Liang Qiu, Ilgee Hong, Changlong Yu, Wenlin Yao, Yao Liu, Haoming Jiang, Lihong Li, Hyokun Yun, Tuo Zhao

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Amazon（亚马逊） 纠错

Comments NeurIPS 2025, 18 pages

AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models

Seunghoon Lee, Jeongwoo Choi, Byunggwan Son, Jaehyeon Moon, Jeimin Jeon, Bumsub Ham

Comments Accepted to NeurIPS 2025

SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time Series

Qitai Tan, Yiyun Chen, Mo Li, Ruiwen Gu, Yilin Su, Xiao-Ping Zhang

Comments NeurIPS 2025

Scalable GPU-Accelerated Euler Characteristic Curves: Optimization and Differentiable Learning for PyTorch

Udit Saxena

Comments Extended Abstract: Accepted to the NeurReps 2025 workshop at NeurIPS 2025. 4 pages, 3 figures

Kinaema: a recurrent sequence model for memory and pose in motion

Mert Bulent Sariyildiz, Philippe Weinzaepfel, Guillaume Bono, Gianluca Monaci, Christian Wolf

Comments 10 pages + references + checklist + appendix, 29 pages total

Journal ref Neural Information Processing Systems (NeurIPS) 2025

Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding

Minseok Kang, Minhyeok Lee, Minjung Kim, Donghyeong Kim, Sangyoun Lee

机构 * Yonsei University（延世大学） ； LG Electronics（LG电子） 纠错

Comments Comments: 28 pages, including appendix. 5 figures. Full version of the NeurIPS 2025 paper

COS3D: Collaborative Open-Vocabulary 3D Segmentation

Runsong Zhu, Ka-Hei Hui, Zhengzhe Liu, Qianyi Wu, Weiliang Tang, Shi Qiu, Pheng-Ann Heng, Chi-Wing Fu

机构 * The Chinese University of Hong Kong（香港中文大学） ； Autodesk AI Lab（Autodesk人工智能实验室） ； Lingnan University（岭大大学） ； Monash University（墨尔本大学） 纠错

Comments NeurIPS 2025. The code is publicly available at \href{https://github.com/Runsong123/COS3D}{https://github.com/Runsong123/COS3D}

Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach

Woohyeon Byeon, Giseung Park, Jongseong Chae, Amir Leshem, Youngchul Sung

Comments Accepted to NeurIPS 2025

Federated Learning via Meta-Variational Dropout

Insu Jeon, Minui Hong, Junhyeog Yun, Gunhee Kim

机构 * Seoul National University（首尔国立大学） 纠错

Comments Published in the Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) 2023, Main Conference Track

Journal ref Jeon, I., Hong, M., Yun, J., Kim, G. (2023). Federated Learning via Meta-Variational Dropout. Advances in Neural Information Processing Systems 36 (NeurIPS 2023)

High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning

Qinyu Xu, Yuanyang Zhu, Xuefei Wu, Chunlin Chen

机构 * School of Management and Engineering（管理与工程学院） ； School of Information Management（信息管理学院） ； School of Robotics and Automation（机器人与自动化学院） 纠错

Comments 39th Conference on Neural Information Processing Systems

PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching

Yun Wang, Junjie Hu, Qiaole Dong, Yongjian Zhang, Yanwei Fu, Tin Lun Lam, Dapeng Wu

机构 * City University of Hong Kong（香港城市大学） ； The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； Shenzhen Campus, Sun Yat-sen University（中山大学深圳校区） 纠错

Journal ref NeurIPS 2025

Revisiting Logit Distributions for Reliable Out-of-Distribution Detection

Jiachen Liang, Ruibing Hou, Minyang Hu, Hong Chang, Shiguang Shan, Xilin Chen

机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, CAS, China（人工智能安全国家重点实验室，计算技术研究所，中国科学院，中国） ； University of Chinese Academy of Sciences (CAS), China（中国科学院大学（中国科学院）） 纠错

Comments Accepted by NeurIPS 2025

MG-NECOLA: Fast Neural Emulators for Modified Gravity Cosmologies

J. Bayron Orjuela-Quintana, Mauricio Reyes, Elena Giusarma, Francisco Villaescusa-Navarro, Neerav Kaushal, César A. Valenzuela-Toledo

Comments Contribution to Machine Learning and the Physical Sciences Workshop at the 39th conference on Neural Information Processing Systems (NeurIPS)

Teaming LLMs to Detect and Mitigate Hallucinations

Demian Till, John Smeaton, Peter Haubrick, Gouse Saheb, Florian Graef, David Berman

Comments Accepted to NeurIPS 2025 workshop on Reliable ML from Unreliable Data

The Parameterized Complexity of Computing the VC-Dimension

Florent Foucaud, Harmender Gahlawat, Fionn Mc Inerney, Prafullkumar Tale

机构 * Université Clermont Auvergne, CNRS, Mines Saint-Étienne, Clermont Auvergne INP, LIMOS（克莱蒙特-奥弗涅大学、国家科学研究中心、圣艾蒂安矿业学院、克莱蒙特-奥弗涅理工学院、LIMOS实验室） ； Telefónica Scientific Research Barcelona, Spain（西班牙巴塞罗那电信科学研究所） ； Indian Institute of Science Education and Research Pune Pune, India（印度班加罗尔印度科学教育与研究学院） 纠错

Comments To appear in the proceedings of NeurIPS 2025

Towards Robust Zero-Shot Reinforcement Learning

Kexin Zheng, Lauriane Teyssier, Yinan Zheng, Yu Luo, Xianyuan Zhan

机构 * The Chinese University of Hong Kong（香港中文大学） ； Tsinghua University（清华大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） 纠错

Comments Neurips 2025, 29 pages, 19 figures

Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning

Yang Li, Aming Wu, Zihao Zhang, Yahong Han

机构 * School of Artificial Intelligence, College of Intelligence and Computing, Tianjin University, China（人工智能学院、智能与计算学院、天津大学） ； School of Computer Science and Information Engineering, Hefei University of Technology, China（计算机科学与信息工程学院、合肥工业大学） 纠错

Comments Accepted by NeurIPS 2025

Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning

Simin Li, Zihao Mao, Hanxiao Li, Zonglei Jing, Zhuohang bian, Jun Guo, Li Wang, Zhuoran Han, Ruixiao Xu, Xin Yu, Chengdong Ma, Yuqing Ma, Bo An, Yaodong Yang, Weifeng Lv, Xianglong Liu

机构 * State Key Laboratory of Complex & Critical Software Environment（复杂与关键软件环境国家重点实验室） ； Beihang University（北京航空航天大学） ； Zhongguancun Laboratory（中关村实验室） ； Institute of Artificial Intelligence, Peking University（北京大学人工智能研究院） ； Institute of data space, Hefei Comprehensive National Science Center（合肥综合国家科学中心数据空间研究院） ； Nanyang Technological University（南洋理工大学） 纠错

Comments 44 pages, 16 figures, NeurIPS 2025

mmWalk: Towards Multi-modal Multi-view Walking Assistance

Kedi Ying, Ruiping Liu, Chongyan Chen, Mingzhe Tao, Hao Shi, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen

机构 * CV:HCI, KIT（KIT计算机视觉与人机交互中心） ； Hunan University（湖南大学） ； ETH Zurich（苏黎世联邦理工学院） ； University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Zhejiang University（浙江大学） 纠错

Comments Accepted by NeurIPS 2025 Datasets and Benchmarks Track. Data and Code: https://github.com/KediYing/mmWalk

FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts

Heming Zou, Yunliang Zang, Wutong Xu, Yao Zhu, Xiangyang Ji

机构 * Department of Automation, Tsinghua University（自动化系，清华大学） ； Academy of Medical Engineering and Translational Medicine, Tianjin University（医学工程与转化医学学院，天津大学） 纠错

Comments NeurIPS 2025 accepted paper

VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning

Wenhao Li, Qiangchang Wang, Xianjing Meng, Zhibin Wu, Yilong Yin

机构 * School of Software, Shandong University（山东大学软件学院） ； Shenzhen Loop Area Institute（深圳河套学院） ； School of Computing and Artificial Intelligence, Shandong University of Finance and Economics（山东财经大学计算机与人工智能学院） 纠错

Comments Accepted by NeurIPS 2025

FerretNet: Efficient Synthetic Image Detection via Local Pixel Dependencies

Shuqiao Liang, Jian Liu, Renzhang Chen, Quanlong Guan

机构 * Jinan University（济南大学） 纠错

Comments 9 pages, 4 figures, 8 tables, accepted at NeurIPS 2025