NeurIPS

Efficient Verified Machine Unlearning For Distillation

Yijun Quan, Zushu Li, Giovanni Montana

机构 * University of Warwick（沃里克大学） 纠错

Comments Accepted at The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)

HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation

Haoran Luo, Haihong E, Guanting Chen, Yandan Zheng, Xiaobao Wu, Yikai Guo, Qika Lin, Yu Feng, Zemin Kuang, Meina Song, Yifan Zhu, Luu Anh Tuan

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Nanyang Technological University（南洋理工大学） ； Beijing Institute of Computer Technology and Application（北京计算机技术与应用研究所） ； National University of Singapore（新加坡国立大学） ； China Mobile Research Institute（中国移动研究院） ； Beijing Anzhen Hospital, Capital Medical University（首都医科大学北京安贞医院） 纠错

Comments Accepted by NeurIPS 2025 main conference

Journal ref NeurIPS 2025

Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Learnable Linear Extrapolation

Jiawei Zhang, Ziyuan Liu, Leon Yan, Gen Li, Yuantao Gu

机构 * Tsinghua University（清华大学） ； CUHK（香港中文大学） 纠错

Comments Accepted by NeurIPS 2025

Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples

Suqin Yuan, Lei Feng, Bo Han, Tongliang Liu

机构 * Sydney AI Centre, The University of Sydney（悉尼人工智能中心，悉尼大学） ； Southeast University（东南大学） ； Hong Kong Baptist University（香港 Baptist 大学） 纠错

Comments Accepted by NeurIPS 2025

In-Context Learning of Linear Dynamical Systems with Transformers: Approximation Bounds and Depth-Separation

Frank Cole, Yuxuan Zhao, Yulong Lu, Tianhao Zhang

机构 * School of Mathematics University of Minnesota, Twin Cities（数学系 明尼苏达大学 Twin Cities分校） 纠错

Comments NeurIPS 2025 camera ready version. Slight change to title and author order from earlier version. Added experiments and acknowledgements section

Beyond Benign Overfitting in Nadaraya-Watson Interpolators

Daniel Barzilai, Guy Kornowski, Ohad Shamir

机构 * Weizmann Institute of Science（魏茨曼科学研究所） 纠错

Comments NeurIPS 2025

VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching

Siyu Xu, Yunke Wang, Chenghao Xia, Dihao Zhu, Tao Huang, Chang Xu

机构 * School of Computer Science, University of Sydney（悉尼大学计算机科学学院） ； John Hopcropt Center for Computer Science, Shanghai Jiao Tong University（上海交通大学约翰·霍普克罗夫特计算机科学中心） 纠错

Comments Accepted to NeurIPS 2025

The $φ$ Curve: The Shape of Generalization through the Lens of Norm-based Capacity Control

Yichen Wang, Yudong Chen, Lorenzo Rosasco, Fanghui Liu

机构 * Malga - DIBRIS, University of Genova（马尔加-迪布里斯，热那亚大学） ； Istituto Italiano di Tecnologia, IT（意大利技术研究院） ； Department of Computer Science, and DIMAP University of Warwick（计算机科学系，沃里克大学） 纠错

Comments Accepted by NeurIPS'25

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model

Jinwei Hu, Zhenglin Huang, Xiangyu Yin, Wenjie Ruan, Guangliang Cheng, Yi Dong, Xiaowei Huang

机构 * School of Computer Science and Informatics, University of Liverpool, UK（计算机科学与信息学学院，利物浦大学） 纠错

Comments Accepted at NeurIPS 2025 with minor revisions

LLM Safety Alignment is Divergence Estimation in Disguise

Rajdeep Haldar, Ziyi Wang, Qifan Song, Guang Lin, Yue Xing

机构 * Department of Statistics, Purdue University（普渡大学统计系） ； Department of Statistics, Michigan State University（密歇根州立大学统计系） 纠错

Comments Accepted to NeurIPS 2025

Foundation Cures Personalization: Improving Personalized Models' Prompt Consistency via Hidden Foundation Knowledge

Yiyang Cai, Zhengkai Jiang, Yulong Liu, Chunyang Jiang, Wei Xue, Yike Guo, Wenhan Luo

机构 * Hong Kong University of Science and Technology (HKUST)（香港科技大学） ； Tencent Hunyuan（腾讯文元） 纠错

Comments Accepted to NeurIPS 2025

3D Audio-Visual Segmentation

Artem Sokolov, Swapnil Bhosale, Xiatian Zhu

机构 * University of Surrey, UK（Surrey大学） 纠错

Comments Accepted at the NeurIPS 2024 Workshop on Audio Imagination; this version updates the project page link

Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis

Abhinav Nippani, Dongyue Li, Haotian Ju, Haris N. Koutsopoulos, Hongyang R. Zhang

Comments 22 pages. Appeared in NeurIPS 2023

Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks

Chaoyue Liu, Han Bi, Like Hui, Xiao Liu

机构 * Elmore Family School of Electrical and Computer Engineering（埃尔莫尔电气与计算机工程学院） ； Purdue University（普渡大学） ； Department of Physics and Astronomy（物理与天文学系） ； Halıcıoğlu Data Science Institute（哈利奇奥格卢数据科学研究所） ； University of California San Diego（加州大学圣地亚哥分校） ； Rosen Center For Advanced Computing（罗森先进计算中心） 纠错

Comments NeurIPS 2025

AION-1: Omnimodal Foundation Model for Astronomical Sciences

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

Comments Accepted at Neural Information Processing Systems (2025)

CLAWS:Creativity detection for LLM-generated solutions using Attention Window of Sections

Keuntae Kim, Eunhye Jeong, Sehyeon Lee, Seohee Yoon, Yong Suk Choi

机构 * Department of Computer Science（计算机科学系） ； Department of Artificial Intelligence（人工智能系） ； Department of Future Mobility（未来移动部门） 纠错

Comments NeurIPS 2025

Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch

Xu Cai, Yang Wu, Qianli Chen, Haoran Wu, Lichuan Xiang, Hongkai Wen

机构 * AI Research Center, iHuman Inc.（人工智能研究中心，iHuman公司） 纠错

Comments NeurIPS 2025

CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization

Yichen Yan, Ming Zhong, Qi Zhu, Xiaoling Gu, Jinpeng Chen, Huan Li

机构 * The State Key Laboratory of Blockchain and Data Security（区块链与数据安全国家重点实验室） ； Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院） ； Hangzhou Dianzi University（杭州电子科技大学） ； School of Computer Science (National Pilot Software Engineering School), BUPT（计算机学院（国家级试点软件工程学院），北京邮电大学） 纠错

Comments 22 pages, 8 figures, 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

MAT-Agent: Adaptive Multi-Agent Training Optimization

Jusheng Zhang, Kaitong Cai, Yijia Fan, Ningyuan Liu, Keze Wang

机构 * Sun Yat-sen University（中山大学） 纠错

Comments Acceptance to NeurIPS 2025 Main Track

Towards 3D Objectness Learning in an Open World

Taichi Liu, Zhenyu Wang, Ruofeng Liu, Guang Wang, Desheng Zhang

机构 * Rutgers University（罗格斯大学） ； Tsinghua University（清华大学） ； Michigan State University（密歇根州立大学） ； Florida State University（佛罗里达州立大学） 纠错

Comments Accepted by NeurIPS 2025

ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling

Shuyuan Zhang, Chenhan Jiang, Zuoou Li, Jiankang Deng

机构 * Imperial College London（伦敦帝国学院） ； Hong Kong University of Science and Technology（香港科学与技术大学） 纠错

Comments NeurIPS 2025 Poster

How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?

Wei Huang, Andi Han, Yujin Song, Yilan Chen, Denny Wu, Difan Zou, Taiji Suzuki

机构 * RIKEN AIP ； The Institute of Statistical Mathematics（统计数学研究所） ； The University of Sydney（悉尼大学） ； The University of Tokyo（东京大学） ； University of California San Diego（圣地亚哥大学） ； New York University（纽约大学） ； Flatiron Institute（Flatiron 机构） ； The University of Hong Kong（香港大学） 纠错

Comments 40 pages

Journal ref NeurIPS 2025

The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis

Hoang Pham, The-Anh Ta, Tom Jacobs, Rebekka Burkholz, Long Tran-Thanh

机构 * University of Warwick（沃里克大学） ； CSIRO’s Data61（CSIRO数据61部门） ； CISPA Helmholtz Center for Information Security（信息安全海德堡研究中心） 纠错

Comments NeurIPS 2025 Spotlight

DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning

Yongxin He, Shan Zhang, Yixuan Cao, Lei Ma, Ping Luo

机构 * Key Lab of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences（智能信息处理重点实验室，计算技术研究所，中国科学院） ； State Key Lab of AI Safety, Beijing, China（人工智能安全国家重点实验室，北京，中国） ； University of Chinese Academy of Sciences, CAS, Beijing, China（中国科学院大学，中国科学院，北京，中国） ； Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China（复杂系统认知与决策智能重点实验室，自动化研究所，中国科学院，北京，中国） ； School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China（人工智能学院，中国科学院大学，北京，中国） 纠错

Comments To appear in NeurIPS 2025

Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models

Li Sun, Zhenhao Huang, Ming Zhang, Philip S. Yu

机构 * North China Electric Power University（华北电力大学） ； University of Illinois Chicago（伊利诺伊大学芝加哥分校） 纠错

Comments Accept by NeurIPS 25

Rethinking Nighttime Image Deraining via Learnable Color Space Transformation

Qiyuan Guan, Xiang Chen, Guiyue Jin, Jiyu Jin, Shumin Fan, Tianyu Song, Jinshan Pan

机构 * Dalian Polytechnic University（大连工业大学） ； Nanjing University of Science and Technology（南京理工大学） ； Dalian Martime University（大连 Maritime University） 纠错

Comments Accepted by NeurIPS 2025

Bridging Embodiment Gaps: Deploying Vision-Language-Action Models on Soft Robots

Haochen Su, Cristian Meo, Francesco Stella, Andrea Peirone, Kai Junge, Josie Hughes

机构 * EPFL（苏黎世联邦理工学院） ； LatentWorlds AI ； TUDelft（代尔夫特理工大学） ； Embodied AI SA（具身人工智能股份有限公司） 纠错

Comments Accepted by NeurIPS 2025 SpaVLE workshop. 4 pages, 2 figures(in main paper, excluding references and supplements)

Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs

Vaggelis Dorovatas, Soroush Seifi, Gunshi Gupta, Rahaf Aljundi

机构 * Toyota Motor Europe（丰田欧洲公司） ； Archimedes RU, Athena RC（阿奇米德 RU、阿泰纳 RC） ； University of Oxford（牛津大学） 纠错

Comments NeurIPS 2025

Optimal Best Arm Identification under Differential Privacy

Marc Jourdan, Achraf Azize

机构 * EPFL（瑞士联邦理工学院） ； FairPlay Joint Team, CREST, ENSAE Paris（FairPlay联合团队，CREST，巴黎国家科学研究中心） 纠错

Comments 92 pages, 2 figures, 2 tables. To be published in the Thirty-Ninth Annual Conference on Neural Information Processing Systems

Exploring Structural Degradation in Dense Representations for Self-supervised Learning

Siran Dai, Qianqian Xu, Peisong Wen, Yang Liu, Qingming Huang

Comments Accepted by NeurIPS 2025