NeurIPS

A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers

Zhixiao Wu, Yao Lu, Jie Wen, Hao Sun, Qi Zhou, Guangming Lu

机构 * Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）） 纠错

Comments 31 pages, 16 figures, accepted in Neurips 2025

GeoRemover: Removing Objects and Their Causal Visual Artifacts

Zixin Zhu, Haoxiang Li, Xuelu Feng, He Wu, Chunming Qiao, Junsong Yuan

机构 * University at Buffalo（布法罗大学） ； Pixocial Technology（Pixocial科技） 纠错

Comments Accepted as Spotlight at NeurIPS 2025

Large-Scale Training Data Attribution for Music Generative Models via Unlearning

Woosung Choi, Junghyun Koo, Kin Wai Cheuk, Joan Serrà, Marco A. Martínez-Ramírez, Yukara Ikemiya, Naoki Murata, Yuhta Takida, Wei-Hsiang Liao, Yuki Mitsufuji

机构 * Sony AI（索尼人工智能） ； Sony Group Corporation（索尼集团） 纠错

Comments accepted at NeurIPS 2025 Creative AI Track

AVerImaTeC: A Dataset for Automatic Verification of Image-Text Claims with Evidence from the Web

Rui Cao, Zifeng Ding, Zhijiang Guo, Michael Schlichtkrull, Andreas Vlachos

机构 * University of Cambridge（剑桥大学） ； Queen Mary University of London（伦敦大学玛丽女王学院） 纠错

Comments accepted at NeurIPS 2025 Datasets and Benchmarks Track

Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning

Yiqun Chen, Lingyong Yan, Weiwei Sun, Xinyu Ma, Yi Zhang, Shuaiqiang Wang, Dawei Yin, Yiming Yang, Jiaxin Mao

机构 * Renmin University of China（中国人民大学） ； Baidu Inc.（百度公司） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments NeurIPS 2025

Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training

Shahrad Mohammadzadeh, Juan David Guerra, Marco Bonizzato, Reihaneh Rabbany, Golnoosh Farnadi

机构 * McGill University（麦吉尔大学） ； Polytechnique Montréal（蒙特利尔理工学院） ； Université de Montréal（蒙特利尔大学） ； Mila - Quebec Artificial Intelligence Institute（魁北克人工智能研究所） ； CIFAR AI Chair（CIFAR人工智能主席） 纠错

Comments Accepted to ACL 2025, accepted to Safe Generative AI Workshop @ NeurIPS 2024. Camera-ready version for ACL 2025 (to appear). Submitted July 2025

Journal ref Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5538-5554, 2025

Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models

Wenzhuo Tang, Haitao Mao, Danial Dervovic, Ivan Brugere, Saumitra Mishra, Yuying Xie, Jiliang Tang

机构 * Michigan State University（密歇根州立大学） ； Amazon（亚马逊） ； J.P. Morgan AI Research（摩根大通人工智能研究） 纠错

Comments NeurIPS'25

How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning

Haotian Gao, Zheng Dong, Jiawei Yong, Shintaro Fukushima, Kenjiro Taura, Renhe Jiang

机构 * The University of Tokyo（东京大学） ； Toyota Motor Corporation（丰田汽车公司） 纠错

Comments Accepted at NeurIPS 2025

Hybrid-Balance GFlowNet for Solving Vehicle Routing Problems

Ni Zhang, Zhiguang Cao

机构 * School of Computing and Information Systems, Singapore Management University（计算与信息系统学院，新加坡管理大学） 纠错

Comments Accepted by NeurIPS 2025

Parameter-free Algorithms for the Stochastically Extended Adversarial Model

Shuche Wang, Adarsh Barik, Peng Zhao, Vincent Y. F. Tan

机构 * Institute of Operations Research and Analytics, National University of Singapore（新加坡国立大学运营研究与分析研究所） ； Department of Computer Science and Engineering, Indian Institute of Technology Delhi（印度理工学院德里分校计算机科学与工程系） ； National Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室） ； School of Artificial Intelligence, Nanjing University（南京大学人工智能学院） ； Department of Mathematics, National University of Singapore（新加坡国立大学数学系） ； Department of Electrical and Computer Engineering, National University of Singapore（新加坡国立大学电气与计算机工程系） 纠错

Comments Accepted to NeurIPS 2025

Silent Tokens, Loud Effects: Padding in LLMs

Rom Himelstein, Amit LeVi, Yonatan Belinkov, Avi Mendelson

机构 * Department of Data and Decision Science, Technion - Israel Institute of Technology（数据与决策科学系，技术离子理工学院） ； Department of Computer Science, Technion - Israel Institute of Technology（计算机科学系，技术离子理工学院） 纠错

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

ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering

Yuki Imajuku, Kohki Horie, Yoichi Iwata, Kensho Aoki, Naohiro Takahashi, Takuya Akiba

机构 * Sakana AI ； The University of Tokyo（东京大学） ； AtCoder 纠错

Comments Accepted at NeurIPS 2025 Datasets & Benchmarks Track

MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly

Zhaowei Wang, Wenhao Yu, Xiyu Ren, Jipeng Zhang, Yu Zhao, Rohit Saxena, Liang Cheng, Ginny Wong, Simon See, Pasquale Minervini, Yangqiu Song, Mark Steedman

机构 * CSE Department, HKUST（香港科技大学计算机科学与工程系） ； Tencent AI Seattle Lab（腾讯AI西雅图实验室） ； University of Edinburgh（爱丁堡大学） ； NVIDIA AI Technology Center (NVAITC), NVIDIA, Santa Clara, USA（英伟达圣克拉拉人工智能技术中心） 纠错

Comments Accepted as a spotlight at NeurIPS 2025

Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning

Zhe Hu, Jing Li, Zhongzhu Pu, Hou Pong Chan, Yu Yin

机构 * The Hong Kong Polytechnic University（香港理工大学） ； Tsinghua University（清华大学） ； InspireOmni AI ； Alibaba Group（阿里巴巴集团） ； Case Western Reserve University（凯斯西储大学） 纠错

Comments Accepted at NeurIPS 2025

Deep vs. Shallow: Benchmarking Physics-Informed Neural Architectures on the Biharmonic Equation

Akshay Govind Srinivasan, Vikas Dwivedi, Balaji Srinivasan

机构 * Department of Mechanical Engineering（机械工程系） ； Indian Institute of Technology, Madras（印度理工学院马德拉斯分校） ； Creatis Biomedical Imaging Laboratory（生物医学成像实验室） ； INSA-Lyon, France（法国里昂国立应用科学学院） ； Department of Data Science and AI（数据科学与人工智能系） 纠错

Comments 16 Pages, 7 Figures and 1 Table. Submitted and accepted at Machine Learning and the Physical Sciences Workshop at the 39th conference on Neural Information Processing Systems (NeurIPS)

Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions

Wenyuan Zhao, Adithya Balachandran, Chao Tian, Paul Pu Liang

机构 * Texas A&M University（德克萨斯大学） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

Comments NeurIPS 2025

Improving Consistency in Retrieval-Augmented Systems with Group Similarity Rewards

Faisal Hamman, Chenyang Zhu, Anoop Kumar, Xujun Peng, Sanghamitra Dutta, Daben Liu, Alfy Samuel

机构 * University of Maryland, College Park（马里兰大学学院公园分校） ； Capital One 纠错

Comments Accepted at NeurIPS 2025 Workshop on Reliable ML from Unreliable Data

CARE-PD: A Multi-Site Anonymized Clinical Dataset for Parkinson's Disease Gait Assessment

Vida Adeli, Ivan Klabucar, Javad Rajabi, Benjamin Filtjens, Soroush Mehraban, Diwei Wang, Hyewon Seo, Trung-Hieu Hoang, Minh N. Do, Candice Muller, Claudia Oliveira, Daniel Boari Coelho, Pieter Ginis, Moran Gilat, Alice Nieuwboer, Joke Spildooren, Lucas Mckay, Hyeokhyen Kwon, Gari Clifford, Christine Esper, Stewart Factor, Imari Genias, Amirhossein Dadashzadeh, Leia Shum, Alan Whone, Majid Mirmehdi, Andrea Iaboni, Babak Taati

机构 * University of Toronto（多伦多大学） ； Vector Institute（向量研究所） ； KITE Research Institute-UHN（KITE研究 institute-UHN） ； University of Strasbourg（斯特拉斯堡大学） ； University Hospitals of Strasbourg（斯特拉斯堡大学医院） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Federal University of ABC（巴西ABC联邦大学） ； KU Leuven（鲁文大学） ； Hasselt University（哈瑟尔特大学） ； Emory University（埃默里大学） ； University of Bristol（布里斯托尔大学） 纠错

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

Concept-Based Masking: A Patch-Agnostic Defense Against Adversarial Patch Attacks

Ayushi Mehrotra, Derek Peng, Dipkamal Bhusal, Nidhi Rastogi

机构 * California Institute of Technology（加州理工学院） ； University of California, Berkeley（加州大学伯克利分校） ； Rochester Institute of Technology（罗切斯特理工学院） 纠错

Comments neurips workshop

ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation

Haoqi Wu, Wei Dai, Ming Xu, Li Wang, Qiang Yan

机构 * TikTok Inc.（TikTok公司） ； National University of Singapore（新加坡国立大学） 纠错

Comments Accepted by NeurIPS 2025

MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition

Umberto Cappellazzo, Minsu Kim, Pingchuan Ma, Honglie Chen, Xubo Liu, Stavros Petridis, Maja Pantic

机构 * Imperial College London（伦敦帝国学院） ； Meta AI ； NatWest AI Research（NatWest人工智能研究） 纠错

Comments NeurIPS 2025

MetaFind: Scene-Aware 3D Asset Retrieval for Coherent Metaverse Scene Generation

Zhenyu Pan, Yucheng Lu, Han Liu

机构 * Northwestern University（西北大学） ； New York University（纽约大学） 纠错

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

SITCOM: Scaling Inference-Time COMpute for VLAs

Ayudh Saxena, Harsh Shah, Sandeep Routray, Rishi Rajesh Shah, Esha Pahwa

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments Accepted at the NeurIPS 2025 Workshop on Space in Vision, Language, and Embodied AI (SpaVLE). *Equal contribution

Multi-Class Support Vector Machine with Differential Privacy

Jinseong Park, Yujin Choi, Jaewook Lee

机构 * Korea Institute for Advanced Study（韩国高级研究院） ； Seoul National University（首尔国立大学） 纠错

Comments NeurIPS 2025

Rare Text Semantics Were Always There in Your Diffusion Transformer

Seil Kang, Woojung Han, Dayun Ju, Seong Jae Hwang

Comments Accepted to NeurIPS 2025

H-DDx: A Hierarchical Evaluation Framework for Differential Diagnosis

Seungseop Lim, Gibaeg Kim, Hyunkyung Lee, Wooseok Han, Jean Seo, Jaehyo Yoo, Eunho Yang

机构 * AITRICS ； KAIST（韩国科学技术院） 纠错

Comments GenAI4Health @NeurIPS 2025

AutoPrune: Each Complexity Deserves a Pruning Policy

Hanshi Wang, Yuhao Xu, Zekun Xu, Jin Gao, Yufan Liu, Weiming Hu, Ke Wang, Zhipeng Zhang

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), CASIA（多模态人工智能系统国家重点实验室（MAIS），中国科学院自动化所） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； AutoLab, School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院AutoLab） ； Anyverse Intelligence ； Beijing Key Laboratory of Super Intelligent Security of Multi-Modal Information（北京多模态信息超智能安全重点实验室） ； School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院） 纠错

Comments 13 pages, 2 figures

Journal ref NeurIPS 2025

Do Sparse Subnetworks Exhibit Cognitively Aligned Attention? Effects of Pruning on Saliency Map Fidelity, Sparsity, and Concept Coherence

Sanish Suwal, Dipkamal Bhusal, Michael Clifford, Nidhi Rastogi

机构 * Rochester Institute of Technology（罗切斯特技术学院） ； Toyota InfoTech Labs（丰田信息科技实验室） 纠错

Comments 4 pages, neurips workshop

K-DeCore: Facilitating Knowledge Transfer in Continual Structured Knowledge Reasoning via Knowledge Decoupling

Yongrui Chen, Yi Huang, Yunchang Liu, Shenyu Zhang, Junhao He, Tongtong Wu, Guilin Qi, Tianxing Wu

机构 * School of Computer Science and Engineering, Southeast University, China（东南大学计算机科学与工程学院） ； Key Laboratory of New Generation Artificial Intelligence Technology and its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及 interdisciplinary 应用关键实验室（东南大学）） ； China Mobile Research Institute（中国移动研究院） ； Department of Data Science & AI, Monash University, Australia（莫纳什大学数据科学与人工智能系） 纠错

Comments Accepted in Neurips 2025 (poster)

time2time: Causal Intervention in Hidden States to Simulate Rare Events in Time Series Foundation Models

Debdeep Sanyal, Aaryan Nagpal, Dhruv Kumar, Murari Mandal, Saurabh Deshpande

机构 * Birla AI Labs, Office of Ananya Birla（Birla AI实验室，Ananya Birla办公室） ； BITS Pilani ； KIIT Bhubaneswar（KIIT巴尔班格斯） 纠错

Journal ref NeurIPS 2025 Workshop on Recent Advances in Time Series Foundation Models (BERT2S)