NeurIPS

FlowTIE: Flow-based Transport of Intensity Equation for Phase Gradient Estimation from 4D-STEM Data

Arya Bangun, Maximilian Töllner, Xuan Zhao, Christian Kübel, Hanno Scharr

机构 * Karlsruhe Nano Micro Facility (KNMF)（卡尔斯鲁厄纳米微设施） ； KIT Department of Materials Science（卡尔斯鲁厄理工学院材料科学系） ； TU Darmstadt（德累斯顿技术大学） 纠错

Comments 7 pages, 3 figures, Machine Learning and the Physical Sciences Workshop, NeurIPS 2025

FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models

Pukang Ye, Junwei Luo, Xiaolei Dong, Yunbo Yang

机构 * East China Normal University（华东师范大学） ； Wuhan University（武汉大学） ； Zhejiang University（浙江大学） ； ZStack ； Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security Q（杭州高新区（滨江）区块链与数据安全研究院） 纠错

Comments Accepted at NeurIPS 2025. Code is available at https://github.com/Hecateto/FedRW

Slimmable NAM: Neural Amp Models with adjustable runtime computational cost

Steven Atkinson

机构 * Atkinson Advanced Modeling, LLC（阿特金森先进建模公司） 纠错

Comments 2 pages, 2 figures. Accepted to NeurIPS 2025 workshop on AI for Music

Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning

Achleshwar Luthra, Tianbao Yang, Tomer Galanti

机构 * Texas A&M University（德克萨斯农工大学） 纠错

Comments Published at NeurIPS 2025

On the generalization of language models from in-context learning and finetuning: a controlled study

Andrew K. Lampinen, Arslan Chaudhry, Stephanie C. Y. Chan, Cody Wild, Diane Wan, Alex Ku, Jörg Bornschein, Razvan Pascanu, Murray Shanahan, James L. McClelland

机构 * Google DeepMind（谷歌DeepMind） ； Google DeepMind & Stanford University（谷歌DeepMind与斯坦福大学） 纠错

Comments FoRLM workshop, NeurIPS 2025

Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization

Yu Huang, Zixin Wen, Aarti Singh, Yuejie Chi, Yuxin Chen

Comments This is the full version of a paper published at NeurIPS 2025

Self-Evaluating LLMs for Multi-Step Tasks: Stepwise Confidence Estimation for Failure Detection

Vaibhav Mavi, Shubh Jaroria, Weiqi Sun

机构 * Dyania Health（Dyania健康） 纠错

Comments Accepted at NeurIPS 2025 Workshop on Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling

Inference-Time Scaling of Diffusion Models for Infrared Data Generation

Kai A. Horstmann, Maxim Clouser, Kia Khezeli

机构 * Cornell University（康奈尔大学） ； YRIKKA, Inc.（YRIKKA公司） 纠错

Comments Peer-reviewed workshop paper

Journal ref 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Learning to Sense

E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis

Zhisheng Zhang, Derui Wang, Yifan Mi, Zhiyong Wu, Jie Gao, Yuxin Cao, Kai Ye, Minhui Xue, Jie Hao

机构 * Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院） ； Beijing University of Posts and Telecommunications（北京邮电大学） ； CSIRO’s Data61（CSIRO数据61） ； Responsible AI Research (RAIR) Centre, The University of Adelaide（阿德莱德大学负责任人工智能研究（RAIR）中心） ； National University of Singapore（新加坡国立大学） ； The University of Hong Kong（香港大学） 纠错

Comments Accepted to NeurIPS 2025

Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification

Xinpeng Lv, Yunxin Mao, Haoxuan Li, Ke Liang, Jinxuan Yang, Wanrong Huang, Haoang Chi, Huan Chen, Long Lan, Yuanlong Chen, Wenjing Yang, Haotian Wang

机构 * College of Computer Science and Technology, National University of Defense Technology（国防科技大学计算机科学与技术学院） ； Center for Data Science, Peking University（北京大学数据科学中心） ； Faculty of Engineering, the University of Sydney（悉尼大学工程学院） ； Faculty of Computing, Harbin Institute of Technology（哈尔滨工业大学计算机学院） 纠错

Comments Accepted by NeurIPS 2025

Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings

Erel Naor, Ofir Lindenbaum

机构 * Bar-Ilan University（巴伊兰大学） 纠错

Comments accepted to neurips 2025, main text is 10 pages

Learning to Focus: Prioritizing Informative Histories with Structured Attention Mechanisms in Partially Observable Reinforcement Learning

Daniel De Dios Allegue, Jinke He, Frans A. Oliehoek

机构 * Delft University of Technology（代尔夫特理工大学） 纠错

Comments Accepted to Embodied World Models for Decision Making (EWM) Workshop at NeurIPS 2025

Gaussian-Augmented Physics Simulation and System Identification with Complex Colliders

Federico Vasile, Ri-Zhao Qiu, Lorenzo Natale, Xiaolong Wang

机构 * Istituto Italiano di Tecnologia（意大利技术研究院） ； UC San Diego（加州大学圣地亚哥分校） 纠错

Comments Accepted to NeurIPS 2025. Project website: https://as-diffmpm.github.io/

Coupling Agent-based Modeling and Life Cycle Assessment to Analyze Trade-offs in Resilient Energy Transitions

Beichen Zhang, Mohammed T. Zaki, Hanna Breunig, Newsha K. Ajami

机构 * Lawrence Berkeley National Laboratory（伯克利劳伦斯国家实验室） 纠错

Comments 4 pages (+4 pages in appendix), 3 figures (+ 2 figures in appendix), 8 tables in appendix, NeurIPS Workshop on Tackling Climate Change with Machine Learning, 2025

Rank-1 LoRAs Encode Interpretable Reasoning Signals

Jake Ward, Paul Riechers, Adam Shai

机构 * MATS 纠错

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Mechanistic Interpretability Workshop

Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality

Yu-Hu Yan, Peng Zhao, Zhi-Hua Zhou

机构 * National Key Laboratory for Novel Software Technology, Nanjing University, China（新型软件技术国家实验室，南京大学，中国） ； School of Artificial Intelligence, Nanjing University, China（人工智能学院，南京大学，中国） 纠错

Comments NeurIPS 2025

FractalBench: Diagnosing Visual-Mathematical Reasoning Through Recursive Program Synthesis

Jan Ondras, Marek Šuppa

机构 * MIT（麻省理工学院） ； Comenius University in Bratislava（布拉迪斯拉发孔院大学） 纠错

Comments Accepted to The 5th Workshop on Mathematical Reasoning and AI at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025); 25 pages, 14 figures, 8 tables; Code available at https://github.com/NaiveNeuron/FractalBench

ConnectomeBench: Can LLMs Proofread the Connectome?

Jeff Brown, Andrew Kirjner, Annika Vivekananthan, Ed Boyden

机构 * MIT（麻省理工学院） ； HHMI（霍华德·休斯医学研究所） ； McGovern Institute（麦戈文研究所） ； MIT Departments of Brain and Cognitive Sciences（麻省理工学院脑科学与认知科学系） 纠错

Comments To appear in NeurIPS 2025 Datasets and Benchmarks Track

Matchings Under Biased and Correlated Evaluations

Amit Kumar, Nisheeth K. Vishnoi

Comments To appear in NeurIPS 2025

Bridging the gap to real-world language-grounded visual concept learning

Whie Jung, Semin Kim, Junee Kim, Seunghoon Hong

机构 * School of Computing, KAIST（计算机学院，韩国科学技术院） 纠错

Journal ref Advances in Neural Information Processing Systems (NeurIPS), 2025

Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning

Jeff Shen, Francois Lanusse, Liam Holden Parker, Ollie Liu, Tom Hehir, Leopoldo Sarra, Lucas Meyer, Micah Bowles, Sebastian Wagner-Carena, Sebastian Wagner-Carena, Helen Qu, Siavash Golkar, Alberto Bietti, Hatim Bourfoune, Nathan Cassereau, Pierre Cornette, Keiya Hirashima, Geraud Krawezik, Ruben Ohana, Nicholas Lourie, Michael McCabe, Rudy Morel, Payel Mukhopadhyay, Mariel Pettee, Bruno Régaldo-Saint Blancard, Kyunghyun Cho, Miles Cranmer, Shirley Ho

Comments Accepted at NeurIPS 2025 Machine Learning and the Physical Sciences Workshop; v2: added collaboration

Lagrangian neural ODEs: Measuring the existence of a Lagrangian with Helmholtz metrics

Luca Wolf, Tobias Buck, Bjoern Malte Schaefer

机构 * Interdisciplinary Center for Scientific Computing（交叉科学计算中心） ； Heidelberg University（海德堡大学） ； Astronomisches Rechen-Institut der Universität Heidelberg（海德堡大学天文计算研究所） 纠错

Comments Accepted for the NeurIPS 2025 Machine Learning and the Physical Sciences workshop. 6 pages, 3 figures

UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning

Ye Liu, Zongyang Ma, Junfu Pu, Zhongang Qi, Yang Wu, Ying Shan, Chang Wen Chen

机构 * The Hong Kong Polytechnic University（香港理工大学） ； ARC Lab, Tencent PCG（腾讯PCG ARC实验室） ； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； vivo Mobile Communication Co.（vivo移动通信公司） ； MindWingman Technology (Shenzhen) Co., Ltd.（深圳MindWingman技术有限公司） 纠错

Comments NeurIPS 2025 Camera Ready. Project Page: https://polyu-chenlab.github.io/unipixel/

Visual Structures Helps Visual Reasoning: Addressing the Binding Problem in VLMs

Amirmohammad Izadi, Mohammad Ali Banayeeanzade, Fatemeh Askari, Ali Rahimiakbar, Mohammad Mahdi Vahedi, Hosein Hasani, Mahdieh Soleymani Baghshah

Comments Accepted to NeurIPS 2025 (Thirty-ninth Conference on Neural Information Processing Systems)

Consistent Story Generation: Unlocking the Potential of Zigzag Sampling

Mingxiao Li, Mang Ning, Marie-Francine Moens

机构 * KU Leuven（库勒芬大学） ； Utrecht University（乌得勒支大学） 纠错

Comments 20 pages, 10 figures

Journal ref published at NeurIPS 2025

Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

Xun Huang, Zhengqi Li, Guande He, Mingyuan Zhou, Eli Shechtman

机构 * Adobe Research（Adobe研究院） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Comments NeurIPS 2025 spotlight. Project website: http://self-forcing.github.io/

DeepDiver: Adaptive Search Intensity Scaling via Open-Web Reinforcement Learning

Wenxuan Shi, Haochen Tan, Chuqiao Kuang, Xiaoguang Li, Xiaozhe Ren, Chen Zhang, Hanting Chen, Yasheng Wang, Lu Hou, Lifeng Shang

机构 * Huawei Language Model Lab（华为语言模型实验室） 纠错

Comments Accepted as NeurIPS 2025 Spotlight

Robust Hallucination Detection in LLMs via Adaptive Token Selection

Mengjia Niu, Hamed Haddadi, Guansong Pang

机构 * Imperial College London, UK（伦敦帝国学院） ； Singapore Management University（新加坡管理大学） 纠错

Comments Accepted by NeurIPS 2025

Learning Temporal 3D Semantic Scene Completion via Optical Flow Guidance

Meng Wang, Fan Wu, Ruihui Li, Yunchuan Qin, Zhuo Tang, Kenli Li

机构 * College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机科学与电子工程学院） ； State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle, Hunan University（车辆先进设计与制造技术国家重点实验室） 纠错

Comments Accepted by NeurIPS 2025

Smooth Sailing: Lipschitz-Driven Uncertainty Quantification for Spatial Association

David R. Burt, Renato Berlinghieri, Stephen Bates, Tamara Broderick

机构 * MIT LIDS（麻省理工学院LIDS） 纠错

Comments The first two authors contributed equally; 39 pages, 14 figures

Journal ref NeurIPS 2025