NeurIPS

Bridging Tool Dependencies and Domain Knowledge: A Graph-Based Framework for In-Context Planning

Shengjie Liu, Li Dong, Zhenyu Zhang

机构 * Amazon（亚马逊） 纠错

Comments 4 pages, 2 figures, short paper, NeurIPS 2025 workshop on Bridging Language, Agent, and World Models for Reasoning and Planning

The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets

Yujun Kim, Chaewon Moon, Chulhee Yun

Comments Accepted to NeurIPS 2025, 72 pages, 8 figures

Coreset for Robust Geometric Median: Eliminating Size Dependency on Outliers

Ziyi Fang, Lingxiao Huang, Runkai Yang

机构 * Nanjing University（南京大学） 纠错

Comments This paper has been accepted by NeurIPS 2025

Can LLMs Write Faithfully? An Agent-Based Evaluation of LLM-generated Islamic Content

Abdullah Mushtaq, Rafay Naeem, Ezieddin Elmahjub, Ibrahim Ghaznavi, Shawqi Al-Maliki, Mohamed Abdallah, Ala Al-Fuqaha, Junaid Qadir

机构 * Information Technology University（信息科技大学） ； Qatar University（卡塔尔大学） ； Hamad Bin Khalifa University（哈马德·本·卡西姆大学） 纠错

Comments Accepted at 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: 5th Muslims in Machine Learning (MusIML) Workshop

PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer

Zhiwei Yang, Chen Gao, Mike Zheng Shou

机构 * Xidian University（西安电子科技大学） ； Show Lab, National University of Singapore（新加坡国立大学Show实验室） 纠错

Comments Accepted by NeurIPS 2025

Uni-LoRA: One Vector is All You Need

Kaiyang Li, Shaobo Han, Qing Su, Wei Li, Zhipeng Cai, Shihao Ji

机构 * School of Computing University of Connecticut（计算机学院 美国康涅狄格大学） ； NEC Labs America（NEC美国实验室） ； Dept. of Computer Science Georgia State University（计算机科学系 美国佐治亚州立大学） 纠错

Comments NeurIPS 2025 Spotlight

Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning

Amit Peleg, Naman Deep Singh, Matthias Hein

机构 * Tübingen AI Center, University of Tübingen（图宾根人工智能中心，图宾根大学） 纠错

Comments Accepted at NeurIPS 2025

GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection

Pingbang Hu, Joseph Melkonian, Weijing Tang, Han Zhao, Jiaqi W. Ma

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Womp Labs（Womp实验室） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

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

URB -- Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles

Ahmet Onur Akman, Anastasia Psarou, Michał Hoffmann, Łukasz Gorczyca, Łukasz Kowalski, Paweł Gora, Grzegorz Jamróz, Rafał Kucharski

机构 * Doctoral School of Exact and Natural Sciences, Jagiellonian University（杰尔吉利亚大学精确与自然科学博士学院） ； Faculty of Mathematics and Computer Science, Jagiellonian University（杰尔吉利亚大学数学与计算机科学学院） ； Urban Policy Observatory, Institute of Urban and Regional Development（城市政策观察所，城市与区域发展研究所） 纠错

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

Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training

Tony Bonnaire, Raphaël Urfin, Giulio Biroli, Marc Mézard

机构 * LPENS Université PSL, Paris（LPENS巴黎大学） ； Department of Computing Sciences Bocconi University, Milano（计算机科学系博科尼大学） 纠错

Comments Accepted as an oral at Neurips 2025. 40 pages, 15 figures

The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness

Sahar Abdelnabi, Ahmed Salem

机构 * Microsoft（微软公司） ； ELLIS Institute Tübingen & MPI for Intelligent Systems（图宾根ELLIS研究所及智能系统马克斯·普朗克研究所） ； Tübingen AI Center（图宾根人工智能中心） 纠错

Comments NeurIPS 2025 (Spotlight). Code is available at: https://github.com/microsoft/Test_Awareness_Steering

Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs

Xuannan Liu, Zekun Li, Zheqi He, Peipei Li, Shuhan Xia, Xing Cui, Huaibo Huang, Xi Yang, Ran He

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Beijing Academy of Artificial Intelligence（北京人工智能研究院） ； University of California, Santa Barbara（加州大学圣芭芭拉分校） ； Center for Research on Intelligent Perception and Computing, NLPR, CASIA（中国科学院CASIA智能感知与计算中心） 纠错

Comments Accepted by NeurIPS 2025 Dataset and Benchmark Track, Project page: https://liuxuannan.github.io/Video-SafetyBench.github.io/

Group-in-Group Policy Optimization for LLM Agent Training

Lang Feng, Zhenghai Xue, Tingcong Liu, Bo An

机构 * Nanyang Technological University（南洋理工大学） ； Skywork AI 纠错

Comments NeurIPS 2025

ADMN: A Layer-Wise Adaptive Multimodal Network for Dynamic Input Noise and Compute Resources

Jason Wu, Yuyang Yuan, Kang Yang, Lance Kaplan, Mani Srivastava

机构 * Electrical and Computer Engineering University of California, Los Angeles（电气与计算机工程大学加州大学洛杉矶分校） ； DEVCOM Army Research Laboratory（国防部陆军研究实验室） ； University of California, Los Angeles（加州大学洛杉矶分校） ； Amazon（亚马逊） 纠错

Comments Accepted to Neurips 2025

GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding

Miruna Oprescu, David K. Park, Xihaier Luo, Shinjae Yoo, Nathan Kallus

机构 * Cornell University（康奈尔大学） ； Brookhaven National Laboratory（布鲁克海文国家实验室） ； Netflix 纠错

Comments 29 pages, 6 figures, 6 tables, NeurIPS 2025

A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning

Qingyue Zhang, Haohao Fu, Guanbo Huang, Yaoyuan Liang, Chang Chu, Tianren Peng, Yanru Wu, Qi Li, Yang Li, Shao-Lun Huang

机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学） 纠错

Comments NeurIPS 2025 Poster

Provable Scaling Laws for the Test-Time Compute of Large Language Models

Yanxi Chen, Xuchen Pan, Yaliang Li, Bolin Ding, Jingren Zhou

机构 * Alibaba Group（阿里巴巴集团） 纠错

Comments NeurIPS 2025 camera-ready version

DeltaPhi: Physical States Residual Learning for Neural Operators in Data-Limited PDE Solving

Xihang Yue, Yi Yang, Linchao Zhu

机构 * College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） ； The State Key Lab of Brain-Machine Intelligence, Zhejiang University（浙江大学脑机智能国家重点实验室） 纠错

Comments Neurips 2025

TIDMAD: Time Series Dataset for Discovering Dark Matter with AI Denoising

J. T. Fry, Xinyi Hope Fu, Zhenghao Fu, Kaliroe M. W. Pappas, Lindley Winslow, Aobo Li

Comments Accepted by NeurIPS 2025 (Spotlight)

Zero-Shot Tokenizer Transfer

Benjamin Minixhofer, Edoardo Maria Ponti, Ivan Vulić

机构 * University of Cambridge（剑桥大学） ； University of Edinburgh（爱丁堡大学） 纠错

Comments NeurIPS 2024

Diffusion Models Meet Contextual Bandits

Imad Aouali

机构 * Criteo AI Lab（Criteo人工智能实验室） ； CREST（CREST研究所） ； ENSAE（ENSAE学院） ； IP Paris（IP巴黎研究所） 纠错

Comments Neurips 2025

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

Problem-Parameter-Free Decentralized Bilevel Optimization

Zhiwei Zhai, Wenjing Yan, Ying-Jun Angela Zhang

Comments Accepted by NeurIPS 2025

UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation

Jiyu Guo, Shuo Yang, Yiming Huang, Yancheng Long, Xiaobo Xia, Xiu Su, Bo Zhao, Zeke Xie, Liqiang Nie

机构 * Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）） ； National University of Singapore（新加坡国立大学） ； MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China（中国科学技术大学脑科学与智能感知认知教育部重点实验室） ； Central South University（中南大学） ； Shanghai Jiao Tong University（上海交通大学） ； Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） 纠错

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

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

DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation

Jingyi Tian, Le Wang, Sanping Zhou, Sen Wang, Jiayi Li, Gang Hua

机构 * National Key Laboratory of Human-Machine Hybrid Augmented Intelligence（人机混合增强智能国家重点实验室） ； National Engineering Research Center for Visual Information and Applications（视觉信息与应用国家工程研究中心） ； Institute of Artificial Intelligence and Robotics（人工智能与机器人研究院） ； Xi’an Jiaotong University（西安交通大学） 纠错

Comments Accepted to NeurIPS 2025

SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMs

Jinhong Deng, Wen Li, Joey Tianyi Zhou, Yang He

机构 * University of Electronic Science and Technology of China（电子科技大学） ； Shenzhen Institute for Advanced Study（深圳先进研究 institute） ； CFAR, Agency for Science, Technology and Research (A*STAR)（科技研究局（A*STAR）认知与人工智能研究中心） ； IHPC, Agency for Science, Technology and Research (A*STAR)（科技研究局（A*STAR）人工智能中心） 纠错

Comments NeurIPS 2025

SPEAR++: Scaling Gradient Inversion via Sparsely-Used Dictionary Learning

Alexander Bakarsky, Dimitar I. Dimitrov, Maximilian Baader, Martin Vechev

机构 * ETH Zurich（苏黎世联邦理工学院） ； INSAIT, Sofia University "St. Kliment Ohridski"（INSAIT，索菲亚大学"圣克莱门特·欧赫里迪斯基"） 纠错

Comments Published at the Workshop on Regulatable ML at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2

Ziqi Zhou, Yifan Hu, Yufei Song, Zijing Li, Shengshan Hu, Leo Yu Zhang, Dezhong Yao, Long Zheng, Hai Jin

机构 * National Engineering Research Center for Big Data Technology and System（大数据技术与系统国家工程研究中心） ； Services Computing Technology and System Lab（服务计算技术与系统实验室） ； Cluster and Grid Computing Lab（集群与网格计算实验室） ； Hubei Engineering Research Center on Big Data Security（湖北省大数据安全工程研究中心） ； Hubei Key Laboratory of Distributed System Security（湖北省分布式系统安全重点实验室） ； School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院） ； School of Cyber Science and Engineering, Huazhong University of Science and Technology（华中科技大学网络科学与工程学院） ； School of Software Engineering, Huazhong University of Science and Technology（华中科技大学软件工程学院） ； School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院） 纠错

Comments Accepted by NeurIPS 2025

EddyFormer: Accelerated Neural Simulations of Three-Dimensional Turbulence at Scale

Yiheng Du, Aditi S. Krishnapriyan

机构 * UC Berkeley（伯克利大学） ； UC Berkeley, LBNL（伯克利大学、劳伦斯伯克利国家实验室） 纠错

Comments NeurIPS 2025

Self-supervised Synthetic Pretraining for Inference of Stellar Mass Embedded in Dense Gas

Keiya Hirashima, Shingo Nozaki, Naoto Harada

机构 * Center for Interdisciplinary Theoretical and Mathematical Sciences (iTHEMS) RIKEN（交叉学科理论与数学科学中心（iTHEMS）RIKEN） ； Department of Earth and Planetary Sciences（地球与行星科学系） ； Department of Astronomy（天文学系） 纠错

Comments 6 pages, 3 figures, 1 table, accepted for NeurIPS 2025 ML4PS workshop

Reinforcement Learning for Long-Horizon Multi-Turn Search Agents

Vivek Kalyan, Martin Andrews

机构 * Red Cat Labs, Singapore（红猫实验室（新加坡）） ； Singapore（新加坡） 纠错

Comments 4 pages plus references and appendices. Accepted into the First Workshop on Multi-Turn Interactions in Large Language Models at NeurIPS 2025