NeurIPS

Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization

Chenrui Wang, Junyi Shu, Billy Chiu, Yu Li, Saleh Alharbi, Min Zhang, Jing Li

机构 * Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学（深圳）） ； Lingnan University（岭大大学） ； Zhejiang University（浙江大学） ； Shaqra University, Saudi Arabia（沙迦大学） 纠错

Comments 28 pages, 11 figures, NeurIPS 2025 Poster

Predict Training Data Quality via Its Geometry in Metric Space

Yang Ba, Mohammad Sadeq Abolhasani, Rong Pan

Comments Accepted to the NeurIPS 2025 Workshop on New Perspectives in Graph Machine Learning

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model

Mohan Zhang, Yihua Zhang, Jinghan Jia, Zhangyang Wang, Sijia Liu, Tianlong Chen

机构 * University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） ； Michigan State University（密歇根州立大学） ； University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Comments NeurIPS 2025

Revisiting the UID Hypothesis in LLM Reasoning Traces

Minju Gwak, Guijin Son, Jaehyung Kim

机构 * Department of Artificial Intelligence（人工智能系） ； Yonsei University（延世大学） ； OneLine AI 纠错

Journal ref The 5th Workshop on Mathematical Reasoning and AI, NeurIPS 2025

MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference

Wenyuan Zhang, Jimin Tang, Weiqi Zhang, Yi Fang, Yu-Shen Liu, Zhizhong Han

机构 * School of Software, Tsinghua University, Beijing, China（清华大学软件学院） ； Center for AI and Robotics (CAIR), NYU Abu Dhabi, UAE（纽约大学阿布扎比分校人工智能与机器人中心） ； Department of Computer Science, Wayne State University, Detroit, USA（韦恩州立大学计算机科学系） 纠错

Comments Accepted by NeurIPS 2025. Project Page: https://wen-yuan-zhang.github.io/MaterialRefGS

HOI-Dyn: Learning Interaction Dynamics for Human-Object Motion Diffusion

Lin Wu, Zhixiang Chen, Jianglin Lan

机构 * James Watt School of Engineering University of Glasgow（詹姆斯·瓦特工程学院格拉斯哥大学） ； School of Computer Science University of Sheffield（计算机科学学院谢菲尔德大学） 纠错

Comments Accepted by NeurIPS 2025

Rao-Blackwellised Reparameterisation Gradients

Kevin H. Lam, Thang D. Bui, George Deligiannidis, Yee Whye Teh

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

CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching

Leying Zhang, Yao Qian, Xiaofei Wang, Manthan Thakker, Dongmei Wang, Jianwei Yu, Haibin Wu, Yuxuan Hu, Jinyu Li, Yanmin Qian, Sheng Zhao

机构 * Shanghai Jiao Tong University（上海交通大学） ； Microsoft（微软公司） 纠错

Comments Neural Information Processing Systems 2025, poster

MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction

Yunkee Chae, Kyogu Lee

机构 * Music and Audio Research Group (MARG)（音乐与音频研究组） ； Interdisciplinary Program in Artificial Intelligence (IPAI)（人工智能跨学科项目） ； AIIS（人工智能研究所） ； Department of Intelligence and Information（智能与信息系） 纠错

Comments Accepted by NeurIPS 2025

Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning

Haolin Yang, Hakaze Cho, Yiqiao Zhong, Naoya Inoue

机构 * University of Chicago（芝加哥大学） ； JAIST ； University of Wisconsin - Madison（威斯康星大学麦迪逊分校） ； RIKEN（日本研究机构） 纠错

Comments 52 pages, 70 figures, 24 tables, NeurIPS 2025

Understanding Prompt Tuning and In-Context Learning via Meta-Learning

Tim Genewein, Li Kevin Wenliang, Jordi Grau-Moya, Anian Ruoss, Laurent Orseau, Marcus Hutter

机构 * Google DeepMind（谷歌DeepMind） 纠错

Comments Accepted and presented at NeurIPS 2025

MergeBench: A Benchmark for Merging Domain-Specialized LLMs

Yifei He, Siqi Zeng, Yuzheng Hu, Rui Yang, Tong Zhang, Han Zhao

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

Comments NeurIPS 2025 Track on Datasets and Benchmarks

Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Inverse Problems

Deliang Wei, Peng Chen, Haobo Xu, Jiale Yao, Fang Li, Tieyong Zeng

机构 * School of Mathematical Sciences, East China Normal University（东华大学数学系） ； School of Mathematical Sciences, Key Laboratory of MEA (Ministry of Education), Shanghai Key Laboratory of PMMP, East China Normal University（东华大学数学系） ； Institute for Advanced Study, Beijing Normal-Hong Kong Baptist University（北京师范大学-香港 Baptist大学高级研究院） ； School of Mathematics and Statistics, Guangzhou Nanfang College（广州南方学院数学系） 纠错

Comments 31 pages. This paper has been accepted by NeurIPs 2025

Online Feedback Efficient Active Target Discovery in Partially Observable Environments

Anindya Sarkar, Binglin Ji, Yevgeniy Vorobeychik

Comments 31 pages, 28 figures, Accepted to NeurIPS 2025

Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation

Jiyuan Wang, Chunyu Lin, Cheng Guan, Lang Nie, Jing He, Haodong Li, Kang Liao, Yao Zhao

机构 * BJTU（北京工业大学） ； NTU（国立台湾大学） ； HKUST（香港科技大学） ； CQUPT（重庆邮电大学） 纠错

Comments Accepted to NeurIPS 2025. 23 pages, with the appendix

GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images

Xiang Lan, Feng Wu, Kai He, Qinghao Zhao, Shenda Hong, Mengling Feng

机构 * National University of Singapore（新加坡国立大学） ； Peking University People’s Hospital（北京大学人民医院） ； Peking University（北京大学） 纠错

Comments NeurIPS 2025 Camera-Ready

MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference

Wenxuan Zeng, Ye Dong, Jinjin Zhou, Jin Tan, Lei Wang, Tao Wei, Runsheng Wang, Meng Li

Comments Accepted by NeurIPS 2025

VisualLens: Personalization through Task-Agnostic Visual History

Wang Bill Zhu, Deqing Fu, Kai Sun, Yi Lu, Zhaojiang Lin, Seungwhan Moon, Kanika Narang, Mustafa Canim, Yue Liu, Anuj Kumar, Xin Luna Dong

机构 * Meta ； University of Southern California（南加州大学） 纠错

Comments Accepted by NeurIPS 2025

Delta-Influence: Unlearning Poisons via Influence Functions

Wenjie Li, Jiawei Li, Pengcheng Zeng, Christian Schroeder de Witt, Ameya Prabhu, Amartya Sanyal

机构 * ShanghaiTech University（上海科技大学） ； Tsinghua University（清华大学） ； University of Oxford（牛津大学） ； Tübingen AI Center, University of Tübingen（图宾根人工智能中心，图宾根大学） ； University of Copenhagen（哥本哈根大学） 纠错

Comments Accepted at NeurIPS Workshop on Attributing Model Behavior at Scale (ATTRIB @ NeurIPS 2024)

Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning

Chongyu Fan, Jiancheng Liu, Licong Lin, Jinghan Jia, Ruiqi Zhang, Song Mei, Sijia Liu

机构 * Michigan State University（密歇根州立大学） ； University of California, Berkeley（加州大学伯克利分校） ； IBM Research（IBM研究院） 纠错

Comments Accepted by NeurIPS 2025

Channel Matters: Estimating Channel Influence for Multivariate Time Series

Muyao Wang, Zeke Xie, Bo Chen, Hongwei Liu, James Kwok

机构 * Intitute of Information Sensing（信息感知研究所） ； School of Electronic Engineering, Xidian University（西安电子科技大学电子工程学院） ； Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； Hong Kong University of Science and Technology（香港科学与技术大学） 纠错

Comments Accepted by Neurips 2025

Emergence of Linear Truth Encodings in Language Models

Shauli Ravfogel, Gilad Yehudai, Tal Linzen, Joan Bruna, Alberto Bietti

机构 * New York University（纽约大学） ； Flatiron Institute（Flatiron研究所） 纠错

Comments Accepted in Neurips 2025

ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection

Haowei Zhu, Tianxiang Pan, Rui Qin, Jun-Hai Yong, Bin Wang

机构 * Tsinghua University（清华大学） ； Li Auto Inc.（力汽车公司） ； BNRist（BNR机构） 纠错

Comments Accepted to NeurIPS 2025 (spotlight)

Demo: Guide-RAG: Evidence-Driven Corpus Curation for Retrieval-Augmented Generation in Long COVID

Philip DiGiacomo, Haoyang Wang, Jinrui Fang, Yan Leng, W Michael Brode, Ying Ding

机构 * Department of Computer Science University of Texas at Austin（计算机科学系得克萨斯大学奥斯汀分校） ； School of Information University of Texas at Austin（信息学院得克萨斯大学奥斯汀分校） ； McCombs School of Business University of Texas at Austin（麦库姆斯商学院得克萨斯大学奥斯汀分校） ； Dell Medical School University of Texas at Austin（德克萨斯大学奥斯汀分校戴尔医学学院） 纠错

Comments Accepted to 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: The Second Workshop on GenAI for Health: Potential, Trust, and Policy Compliance

FACE: A General Framework for Mapping Collaborative Filtering Embeddings into LLM Tokens

Chao Wang, Yixin Song, Jinhui Ye, Chuan Qin, Dazhong Shen, Lingfeng Liu, Xiang Wang, Yanyong Zhang

Comments Accepted by NeurIPS 2025

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning

Zhi Zhou, Yuhao Tan, Zenan Li, Yuan Yao, Lan-Zhe Guo, Yu-Feng Li, Xiaoxing Ma

机构 * State Key Laboratory of Novel Software Technology, Nanjing University, China（新型软件技术国家重点实验室，南京大学，中国） ； Department of Computer Science, ETH Zurich, Switzerland（苏黎世联邦理工学院计算机科学系，瑞士） ； School of Intelligence Science and Technology, Nanjing University, China（智能科学与技术学院，南京大学，中国） ； School of Artifical Intelligence, Nanjing University, China（人工智能学院，南京大学，中国） 纠错

Comments Accepted by NeurIPS 2025

DroneAudioset: An Audio Dataset for Drone-based Search and Rescue

Chitralekha Gupta, Soundarya Ramesh, Praveen Sasikumar, Kian Peen Yeo, Suranga Nanayakkara

机构 * School of Computing, National University of Singapore（computing学院，新加坡国立大学） 纠错

Comments Accepted in Neurips (Datasets and Benchmarks Track) 2025. The first two authors are equal contributors

Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition

Fan Liu, Jindong Han, Tengfei Lyu, Weijia Zhang, Zhe-Rui Yang, Lu Dai, Cancheng Liu, Hao Liu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； The Hong Kong University of Science and Technology（香港科技大学） 纠错

Comments NeurIPS 2025

Semi-Supervised Regression with Heteroscedastic Pseudo-Labels

Xueqing Sun, Renzhen Wang, Quanziang Wang, Yichen Wu, Xixi Jia, Deyu Meng

机构 * Xi’an Jiaotong University（西安交通大学） ； City University of Hong Kong（香港城市大学） ； Harvard University（哈佛大学） ； Xidian University（西安电子科技大学） ； Pazhou Laboratory (Huangpu)（黄埔实验室） 纠错

Comments Accepted by NeurIPS 2025

AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory

Jitesh Jain, Shubham Maheshwari, Ning Yu, Wen-mei Hwu, Humphrey Shi

机构 * Adobe（Adobe公司） ； Netflix Eyeline Studios（Netflix Eyeline工作室） ； UIUC（伊利诺伊大学香槟分校） 纠错

Comments LAW 2025 Workshop at NeurIPS 2025. Work done from late 2023 to early 2024