NeurIPS

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens

Ruichuan An, Sihan Yang, Renrui Zhang, Zijun Shen, Ming Lu, Gaole Dai, Hao Liang, Ziyu Guo, Shilin Yan, Yulin Luo, Bocheng Zou, Chaoqun Yang, Wentao Zhang

机构 * Peking University（北京大学） ； Xi’an JiaoTong University（西安交通大学） ； CUHK（香港中文大学） ； Intel Labs, China（中国英特尔实验室） ； Nanjing University（南京大学） ； University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； Tsinghua University（清华大学） 纠错

Journal ref NeurIPS 2025

Visual Instruction Bottleneck Tuning

Changdae Oh, Jiatong Li, Shawn Im, Sharon Li

机构 * Department of Computer Sciences, University of Wisconsin–Madison（计算机科学系，威斯康星大学麦迪逊分校） 纠错

Comments NeurIPS 2025

Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving on Inequalities

Haoyu Zhao, Yihan Geng, Shange Tang, Yong Lin, Bohan Lyu, Hongzhou Lin, Chi Jin, Sanjeev Arora

机构 * Princeton Language and Intelligence（普林斯顿语言与智能） ； Princeton University（普林斯顿大学） ； Peking University（北京大学） ； Tsinghua University（清华大学） ； Amazon（亚马逊） 纠错

Comments To appear in NeurIPS 2025 Track on Datasets and Benchmarks. 28 pages

RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics

Jie Zhang, Cezara Petrui, Kristina Nikolić, Florian Tramèr

机构 * ETH Zurich（苏黎世联邦理工学院） 纠错

Comments Accepted at NeurIPS 2025

Is Artificial Intelligence Generated Image Detection a Solved Problem?

Ziqiang Li, Jiazhen Yan, Ziwen He, Kai Zeng, Weiwei Jiang, Lizhi Xiong, Zhangjie Fu

机构 * School of Computer Science, Nanjing University of Information Science and Technology（南京信息工程大学计算机学院） ； University of Siena（锡耶纳大学） 纠错

Comments Accepted by NeurIPS 2025 Datasets and Benchmarks Track

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling

Tsung-Han Wu, Heekyung Lee, Jiaxin Ge, Joseph E. Gonzalez, Trevor Darrell, David M. Chan

机构 * UC Berkeley（加州大学伯克利分校） ； POSTECH 纠错

Comments Accepted to NeurIPS 2025; Project Page: https://reverse-vlm.github.io

Leveraging Robust Optimization for LLM Alignment under Distribution Shifts

Mingye Zhu, Yi Liu, Zheren Fu, Yongdong Zhang, Zhendong Mao

机构 * University of Science and Technology of China（中国科学技术大学） ； State Key Laboratory of Communication Content Cognition（通信内容认知国家重点实验室） 纠错

Comments NeurIPS 2025

$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training

Jin Peng Zhou, Kaiwen Wang, Jonathan Chang, Zhaolin Gao, Nathan Kallus, Kilian Q. Weinberger, Kianté Brantley, Wen Sun

Comments NeurIPS 2025

SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization

Xiaofeng Tan, Hongsong Wang, Xin Geng, Pan Zhou

机构 * Department of Computer Science and Engineering, Southeast University, Nanjing, China（东南大学计算机科学与工程系） ； Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China（新一代人工智能技术及其交叉应用国家重点实验室（东南大学）） 纠错

Journal ref Advances in Neural Information Processing Systems, 2025

Diffusion Transformers as Open-World Spatiotemporal Foundation Models

Yuan Yuan, Chonghua Han, Jingtao Ding, Guozhen Zhang, Depeng Jin, Yong Li

机构 * Department of Electronic Engineering, BNRist, Tsinghua University（电子工程系，BNRist，清华大学） 纠错

Comments Accepted by NeurIPS 2025

Parameter Efficient Fine-tuning via Explained Variance Adaptation

Fabian Paischer, Lukas Hauzenberger, Thomas Schmied, Benedikt Alkin, Marc Peter Deisenroth, Sepp Hochreiter

机构 * ELLIS Unit, LIT AI Lab, Institute for Machine Learning, JKU Linz（ELLIS单位、LIT人工智能实验室、机器学习研究所、JKU林茨） ； University College London（伦敦大学学院） ； EMMI AI, Linz（EMMI AI、林茨） ； NXAI GmbH, Linz, Austria（NXAI GmbH、林茨、奥地利） 纠错

Comments Accepted at NeurIPS 2025, Shared first authorship, Code available at https://github.com/ml-jku/EVA

Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees

Chenguang Duan, Yuling Jiao, Huazhen Lin, Wensen Ma, Jerry Zhijian Yang

机构 * School of Mathematics and Statistics, Wuhan University（武汉大学数学与统计学学院） ； School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院） ； National Center for Applied Mathematics in Hubei, Wuhan University（湖北省应用数学中心） ； Hubei Key Laboratory of Computational Science, Wuhan University（湖北省计算科学重点实验室） ； Center of Statistical Research, Southwestern University of Finance and Economics（西南财经大学统计研究中心） ； School of Statistics and Data Science, Southwestern University of Finance and Economics（西南财经大学统计与数据科学学院） ； New Cornerstone Science Laboratory, Southwestern University of Finance and Economics（西南财经大学新基石科学实验室） ； Institute for Math & AI, Wuhan University（武汉大学数学与人工智能研究院） 纠错

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

GIST: Greedy Independent Set Thresholding for Max-Min Diversification with Submodular Utility

Matthew Fahrbach, Srikumar Ramalingam, Morteza Zadimoghaddam, Sara Ahmadian, Gui Citovsky, Giulia DeSalvo

机构 * Google（谷歌） 纠错

Comments 21 pages, 3 figures

Journal ref Proceedings of the 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025)

Attention for Causal Relationship Discovery from Biological Neural Dynamics

Ziyu Lu, Anika Tabassum, Shruti Kulkarni, Lu Mi, J. Nathan Kutz, Eric Shea-Brown, Seung-Hwan Lim

机构 * University of Washington（华盛顿大学） ； Oak Ridge National Laboratory（奥本海默国家实验室） ； Allen Institute for Brain Science（艾伦脑科学研究所） 纠错

Comments Accepted to the NeurIPS 2023 Workshop on Causal Representation Learning

Active Target Discovery under Uninformative Prior: The Power of Permanent and Transient Memory

Anindya Sarkar, Binglin Ji, Yevgeniy Vorobeychik

机构 * Washington University in St. Louis, USA（华盛顿大学圣路易斯分校） 纠错

Comments 32 pages, 20 figures, Accepted to NeurIPS 2025

Infinite Neural Operators: Gaussian processes on functions

Daniel Augusto de Souza, Yuchen Zhu, Harry Jake Cunningham, Yuri Saporito, Diego Mesquita, Marc Peter Deisenroth

机构 * University College London（伦敦大学学院） ； Fundação Getulio Vargas（古特雷斯基金会） 纠错

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

All You Need is One: Capsule Prompt Tuning with a Single Vector

Yiyang Liu, James C. Liang, Heng Fan, Wenhao Yang, Yiming Cui, Xiaotian Han, Lifu Huang, Dongfang Liu, Qifan Wang, Cheng Han

机构 * University of Missouri-Kansas City（密苏里大学堪萨斯城分校） ； U.S. Naval Research Laboratory（美国海军研究实验室） ； University of North Texas（北卡罗来纳州立大学） ； Lamar University（拉马尔大学） ； ByteDance（字节跳动） ； Case Western Reserve University（凯斯西储大学） ； University of California, Davis（加州大学戴维斯分校） ； Rochester Institute of Technology（罗切斯特理工学院） ； Meta AI 纠错

Comments NeurIPS 2025

Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?

Junchi Yu, Yujie Liu, Jindong Gu, Philip Torr, Dongzhan Zhou

机构 * Department of Engineering Science, University of Oxford, UK（牛津大学工程科学系） ； Shanghai Artificial Intelligence Laboratory, China（上海人工智能实验室） 纠错

Comments NeurIPS 2025 (Spotlight)

NeurIPT: Foundation Model for Neural Interfaces

Zitao Fang, Chenxuan Li, Hongting Zhou, Shuyang Yu, Guodong Du, Ashwaq Qasem, Yang Lu, Jing Li, Junsong Zhang, Sim Kuan Goh

机构 * Xiamen University Malaysia（马来西亚厦门大学） ； Columbia University（哥伦比亚大学） ； The Hong Kong Polytechnic University（香港理工大学） ； Xiamen University（厦门大学） ； Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）） 纠错

Comments Accepted by The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025). Project Page: https://ZzzitaoFang.github.io/projects/NeurIPT/

Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions

Jihoon Kwon, Kyle Min, Jy-yong Sohn

机构 * Seoul National University（首尔国立大学） ； Oracle（Oracle公司） ； Yonsei University（延世大学） ； Intel Labs（英特尔实验室） 纠错

Comments Accepted at NeurIPS 2025 (poster). This is the camera-ready version

Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection

Dongchan Cho, Jiho Han, Keumyeong Kang, Minsang Kim, Honggyu Ryu, Namsoon Jung

机构 * Industrial AI Lab, SimPlatform Co. Ltd.（SimPlatform公司工业AI实验室） ； Affiliate Research Institute（附属研究机构） 纠错

Comments Accepted by NeurIPS 2025

VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion

Jaekyun Park, Hye Won Chung

Comments NeurIPS 2025

MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization

Rizhen Hu, Yutong He, Ran Yan, Mou Sun, Binghang Yuan, Kun Yuan

Comments NeurIPS 2025 poster

Conformal Prediction in The Loop: A Feedback-Based Uncertainty Model for Trajectory Optimization

Han Wang, Chao Ning

机构 * School of Automation and Intelligent Sensing（自动化与智能感知学院） ； Shanghai Jiao Tong University（上海交通大学） 纠错

Comments Accepted by NeurIPS 2025 Main Track

The Burden of Interactive Alignment with Inconsistent Preferences

Ali Shirali

机构 * UC Berkeley（伯克利大学） 纠错

Comments Published as a conference paper at NeurIPS 2025

Time-Embedded Algorithm Unrolling for Computational MRI

Junno Yun, Yaşar Utku Alçalar, Mehmet Akçakaya

Comments Neural Information Processing Systems (NeurIPS), 2025

QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models

Yutong Wang, Haiyu Wang, Sai Qian Zhang

机构 * Tandon School of Engineering, New York University（纽约大学工程学院） ； Courant Institute of Mathematical Sciences, New York University（纽约大学数学科学学院） 纠错

Comments Accepted as Spotlight paper by NeurIPS 2025

Disentangling Hyperedges through the Lens of Category Theory

Yoonho Lee, Junseok Lee, Sangwoo Seo, Sungwon Kim, Yeongmin Kim, Chanyoung Park

机构 * KAIST（韩国科学技术院） 纠错

Comments Accepted to NeurIPS 2025

GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer

Sayan Deb Sarkar, Sinisa Stekovic, Vincent Lepetit, Iro Armeni

机构 * Stanford University（斯坦福大学） ； ENPC, IP Paris（巴黎理工学院） 纠错

Comments NeurIPS 2025. Project Page: https://sayands.github.io/guideflow3d/

DAWP: A framework for global observation forecasting via Data Assimilation and Weather Prediction in satellite observation space

Junchao Gong, Jingyi Xu, Ben Fei, Fenghua Ling, Wenlong Zhang, Kun Chen, Wanghan Xu, Weidong Yang, Xiaokang Yang, Lei Bai

机构 * Shanghai Jiao Tong University（上海交通大学） ； Fudan University（复旦大学） ； The Chinese University of Hong Kong Shanghai AI Laboratory（香港中文大学上海人工智能实验室） ； Shanghai AI Laboratory（上海人工智能实验室） 纠错

Journal ref https://neurips.cc/virtual/2025/poster/120074