NeurIPS

KAN-GCN: Combining Kolmogorov-Arnold Network with Graph Convolution Network for an Accurate Ice Sheet Emulator

Zesheng Liu, YoungHyun Koo, Maryam Rahnemoonfar

Comments Accept for NeurIPS 2025 Workshop: New Perspectives in Graph Machine Learning

Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations

Olawale Salaudeen, Haoran Zhang, Kumail Alhamoud, Sara Beery, Marzyeh Ghassemi

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

Comments Accepted as a Spotlight paper at NeurIPS 2025

Augmenting Biological Fitness Prediction Benchmarks with Landscapes Features from GraphFLA

Mingyu Huang, Shasha Zhou, Ke Li

机构 * School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院） ； Department of Computer Science, University of Exeter（埃克塞特大学计算机科学系） 纠错

Comments 56 apges, 18 figures, 8 tables, accepted as a conference paper at NeurIPS 2025

From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning

Junsoo Oh, Jerry Song, Chulhee Yun

机构 * KAIST（韩国科学技术院） 纠错

Comments NeurIPS 2025 camera-ready version, 70 pages

ProofSketch: Efficient Verified Reasoning for Large Language Models

Disha Sheshanarayana, Tanishka Magar

机构 * Manipal University Jaipur（马普尔大学斋普尔） 纠错

Comments Accepted at NeurIPS 2025, ER Workshop

The Underappreciated Power of Vision Models for Graph Structural Understanding

Xinjian Zhao, Wei Pang, Zhongkai Xue, Xiangru Jian, Lei Zhang, Yaoyao Xu, Xiaozhuang Song, Shu Wu, Tianshu Yu

机构 * School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院） ； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； Cheriton School of Computer Science, University of Waterloo（滑铁卢大学切尔顿计算机科学学院） 纠错

Comments NeurIPS 2025

ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents

Zhenyu Zhang, Tianyi Chen, Weiran Xu, Alex Pentland, Jiaxin Pei

机构 * Department of Computer Science, Stanford University（斯坦福大学计算机科学系） ； Stanford Institute for Human-Centered AI（斯坦福大学人本人工智能研究所） ； MIT Media Lab（麻省理工学院媒体实验室） 纠错

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

FastJAM: a Fast Joint Alignment Model for Images

Omri Hirsch, Ron Shapira Weber, Shira Ifergane, Oren Freifeld

Comments Accepted to NeurIPS 2025. Pages 1-10 are the Main Paper. Pages 23-31 are Supplemental Material. FastJAM website - https://bgu-cs-vil.github.io/FastJAM/

Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers

Gangwei Xu, Haotong Lin, Hongcheng Luo, Xianqi Wang, Jingfeng Yao, Lianghui Zhu, Yuechuan Pu, Cheng Chi, Haiyang Sun, Bing Wang, Guang Chen, Hangjun Ye, Sida Peng, Xin Yang

机构 * Huazhong University of Science and Technology（华中科技大学） ； Xiaomi EV（小米电动车） ； Zhejiang University（浙江大学） 纠错

Comments NeurIPS 2025. Project page: https://pixel-perfect-depth.github.io/

GnnXemplar: Exemplars to Explanations -- Natural Language Rules for Global GNN Interpretability

Burouj Armgaan, Eshan Jain, Harsh Pandey, Mahesh Chandran, Sayan Ranu

机构 * Dept. of CSE, IIT Delhi（印度德里理工学院计算机科学与工程系） ； Fujitsu Research of India, Bangalore（印度班加罗尔富士通印度研究机构） ； Dept. of CSE and Yardi ScAI, IIT Delhi（印度德里理工学院计算机科学与工程系） 纠错

Comments 38 pages, 20 figures, NeurIPS 2025 (Oral)

UGM2N: An Unsupervised and Generalizable Mesh Movement Network via M-Uniform Loss

Zhichao Wang, Xinhai Chen, Qinglin Wang, Xiang Gao, Qingyang Zhang, Menghan Jia, Xiang Zhang, Jie Liu

机构 * Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology（数字化前沿装备软件实验室，国防科技大学） ； National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology（并行与分布式计算国家重点实验室，国防科技大学） 纠错

Comments Accepted as a Poster at NeurIPS 2025

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

Thomas Kuntz, Agatha Duzan, Hao Zhao, Francesco Croce, Zico Kolter, Nicolas Flammarion, Maksym Andriushchenko

机构 * EPFL（苏黎世联邦理工学院） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments NeurIPS 2025 Datasets & Benchmarks Track (Spotlight)

Learning single-index models via harmonic decomposition

Nirmit Joshi, Hugo Koubbi, Theodor Misiakiewicz, Nathan Srebro

机构 * Toyota Technological Institute at Chicago（芝加哥丰田技术研究所） ； Department of Statistics and Data Science, Yale University（耶鲁大学统计与数据科学系） ； Centre Borelli, ENS Paris-Saclay（巴黎萨克雷大学Borelli中心） 纠错

Comments 84 pages. Comments are welcome. To appear at NeurIPS 2025

RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation

Songhao Han, Boxiang Qiu, Yue Liao, Siyuan Huang, Chen Gao, Shuicheng Yan, Si Liu

机构 * Beihang University（北航大学） ； National University of Singapore（新加坡国立大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

Comments 25 pages, 18 figures, Accepted by NeurIPS 2025

Set Smoothness Unlocks Clarke Hyper-stationarity in Bilevel Optimization

He Chen, Jiajin Li, Anthony Man-Cho So

Comments Accepted by NeurIPS 2025

Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner

Runa Eschenhagen, Aaron Defazio, Tsung-Hsien Lee, Richard E. Turner, Hao-Jun Michael Shi

机构 * Department of Engineering, University of Cambridge（剑桥大学工程系） ； Meta Platforms, Inc.（Meta公司） ； Fundamental AI Research, Meta Superintelligence Labs（Meta超智能实验室基础人工智能研究部） ； AI and Systems Co-Design, Meta Platforms（Meta平台人工智能与系统联合设计） ； The Alan Turing Institute（艾伦·图灵研究所） ； Infrastructure Optimizations, Meta Superintelligence Labs, Meta Platforms, Inc.（Meta超智能实验室基础设施优化） 纠错

Comments NeurIPS 2025

Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization

Xingyu Chen, Bokun Wang, Ming Yang, Qihang Lin, Tianbao Yang

机构 * Department of CSE, Texas A&M University（计算机科学与工程系，德克萨斯农工大学） ； Tippie College of Business, The University of Iowa（泰普斯商学院，爱荷华大学） 纠错

Comments Accepted to Neurips 2025

Doubly Robust Alignment for Large Language Models

Erhan Xu, Kai Ye, Hongyi Zhou, Luhan Zhu, Francesco Quinzan, Chengchun Shi

机构 * Department of Statistics（统计系） ； LSE London, UK（伦敦大学学院） ； Department of Mathematics（数学系） ； Tsinghua University（清华大学） ； School of Design LCC, UAL London, UK（伦敦艺术大学设计学院） ； Department of Engineering Science（工程科学系） ； University of Oxford（牛津大学） 纠错

Comments Accepted to NeurIPS 2025

Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting

Wei Chen, Yuxuan Liang

机构 * INTR \& DSA Thrust, The Hong Kong University of Science 纠错

Comments Accepted by NeurIPS 2025 (Spotlight)

Adaptive Frontier Exploration on Graphs with Applications to Network-Based Disease Testing

Davin Choo, Yuqi Pan, Tonghan Wang, Milind Tambe, Alastair van Heerden, Cheryl Johnson

机构 * Harvard University（哈佛大学） ； University of Witwatersrand（韦茨大学） ； Wits Health Consortium（韦茨健康联盟） ； World Health Organization（世界卫生组织） 纠错

Comments Accepted into NeurIPS 2025

Learning-Augmented Online Bipartite Fractional Matching

Davin Choo, Billy Jin, Yongho Shin

机构 * Harvard John A. Paulson School Of Engineering And Applied Sciences（哈佛大学约翰·A·保罗森工程与应用科学学院） ； Harvard University（哈佛大学） ； Daniels School of Business（丹尼尔斯商学院） ； Purdue University（普渡大学） ； Institute of Computer Science（计算机科学研究所） ； University of Wrocław（沃里克大学） ； National University of Singapore（新加坡国立大学） ； University of Chicago Booth School of Business（芝加哥大学博世商学院） ； Yonsei University（延世大学） 纠错

Comments To appear in NeurIPS 2025. Full version

PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions

Daeun Kyung, Hyunseung Chung, Seongsu Bae, Jiho Kim, Jae Ho Sohn, Taerim Kim, Soo Kyung Kim, Edward Choi

机构 * KAIST（韩国科学技术院） ； UCSF（旧金山大学） ； Samsung Medical Center（三星医疗中心） ； Ewha Womans University（成均馆大学） 纠错

Comments Accepted as a Spotlight at NeurIPS 2025 Datasets and Benchmarks Track (10 pages for main text, 4 pages for references, 36 pages for supplementary materials)

Efficient Adaptive Experimentation with Noncompliance

Miruna Oprescu, Brian M Cho, Nathan Kallus

机构 * Cornell University（康奈尔大学） ； Netflix（网飞） 纠错

Comments 37 pages, 4 figures, 2 tables, NeurIPS 2025

Creativity or Brute Force? Using Brainteasers as a Window into the Problem-Solving Abilities of Large Language Models

Simeng Han, Howard Dai, Stephen Xia, Grant Zhang, Chen Liu, Lichang Chen, Hoang Huy Nguyen, Hongyuan Mei, Jiayuan Mao, R. Thomas McCoy

机构 * Yale University（耶鲁大学） ； Meta Superintelligence Labs（Meta超智能实验室） ； Georgia Institute of Technology（佐治亚理工学院） ； TTIC ； Massachusetts Institute of Technology（麻省理工学院） 纠错

Comments NeurIPS 2025

S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning

Hanqing Zeng, Yinglong Xia, Zhuokai Zhao, Chuan Jiang, Qiang Zhang, Jiayi Liu, Qunshu Zhang, Lizhu Zhang, Xiangjun Fan, Benyu Zhang

机构 * Meta AI 纠错

Comments NeurIPS 2025

L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery

Ziwei Shi, Xiaoran Zhang, Wenjing Xu, Yan Xia, Yu Zang, Siqi Shen, Cheng Wang

机构 * Fujian Key Laboratory of Sensing and Computing for Smart Cities, Xiamen University, China（福建智能城市感知与计算重点实验室，厦门大学，中国） ； Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, China（多媒体可信感知与高效计算重点实验室，中华人民共和国教育部，厦门大学，中国） ； University of Science and Technology of China, China（中国科学技术大学，中国） 纠错

Comments 17 pages, 7 figures, NeurIPS 2025

Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation

Qijiong Liu, Jieming Zhu, Lu Fan, Kun Wang, Hengchang Hu, Wei Guo, Yong Liu, Xiao-Ming Wu

机构 * PolyU Hong Kong（香港 PolyU） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； NTU Singapore（新加坡国立大学） ； NUS Singapore（新加坡国立大学） 纠错

Comments NeurIPS 2025 DB Track Accepted Paper

Non-Markovian Discrete Diffusion with Causal Language Models

Yangtian Zhang, Sizhuang He, Daniel Levine, Lawrence Zhao, David Zhang, Syed A Rizvi, Shiyang Zhang, Emanuele Zappala, Rex Ying, David van Dijk

机构 * Yale University（耶鲁大学） 纠错

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

HyperMARL: Adaptive Hypernetworks for Multi-Agent RL

Kale-ab Abebe Tessera, Arrasy Rahman, Amos Storkey, Stefano V. Albrecht

机构 * School of Informatics, University of Edinburgh（爱丁堡大学信息学院） ； School of Computer Science, University of Texas at Austin（德克萨斯大学奥斯汀分校计算机科学学院） ； DeepFlow 纠错

Comments To appear at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025). A preliminary version of this work was presented at the CoCoMARL workshop, RLC 2025

Greedy Sampling Is Provably Efficient for RLHF

Di Wu, Chengshuai Shi, Jing Yang, Cong Shen

机构 * Electrical and Computer Engineering University of Virginia（电气与计算机工程大学弗吉尼亚大学） ； Princeton Language and Intelligence Princeton University（普林斯顿语言与智能普林斯顿大学） 纠错

Comments NeurIPS 2025