NeurIPS

Locally Optimal Private Sampling: Beyond the Global Minimax

Hrad Ghoukasian, Bonwoo Lee, Shahab Asoodeh

机构 * Department of Computing and Software（计算与软件系） ； McMaster University（麦斯特大学） ； Department of Mathematical Sciences（数学科学系） ； Korea Advanced Institute of Science & Technology（韩国科学技术院） 纠错

Comments 44 pages, 11 figures. Accepted at NeurIPS 2025

BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception

Junyan Ye, Dongzhi Jiang, Jun He, Baichuan Zhou, Zilong Huang, Zhiyuan Yan, Hongsheng Li, Conghui He, Weijia Li

机构 * Sun Yat-sen University（中山大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； CUHK MMLab（香港中文大学多模态实验室） ； Peking University（北京大学） 纠错

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

Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark

Jinyuan Liu, Zihang Chen, Zhu Liu, Zhiying Jiang, Long Ma, Xin Fan, Risheng Liu

机构 * School of Software Engineering, Dalian University of Technology（大连理工大学软件学院） ； Information Science and Technology College, Dalian Martime University（大连海事大学信息科学与技术学院） 纠错

Comments This paper has been accepted by NeurIPS 2025

Learning Neural Exposure Fields for View Synthesis

Michael Niemeyer, Fabian Manhardt, Marie-Julie Rakotosaona, Michael Oechsle, Christina Tsalicoglou, Keisuke Tateno, Jonathan T. Barron, Federico Tombari

机构 * Google（谷歌） 纠错

Comments Accepted to NeurIPS 2025. Project page available at https://m-niemeyer.github.io/nexf/index.html

CAFL-L: Constraint-Aware Federated Learning with Lagrangian Dual Optimization for On-Device Language Models

Dongqi Zheng, Wenjin Fu

机构 * Purdue University（普渡大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments Accepted by 39th NeurIPS - Constrained Optimization for Machine Learning

ARS: Adaptive Reasoning Suppression for Efficient Large Reasoning Language Models

Dongqi Zheng

机构 * Independent Researcher（独立研究者） 纠错

Comments Accepted by 39th NeurIPS - Foundations of Reasoning in Language Models

Robustness in Both Domains: CLIP Needs a Robust Text Encoder

Elias Abad Rocamora, Christian Schlarmann, Naman Deep Singh, Yongtao Wu, Matthias Hein, Volkan Cevher

Comments Accepted in NeurIPS 2025

CausalDynamics: A large-scale benchmark for structural discovery of dynamical causal models

Benjamin Herdeanu, Juan Nathaniel, Carla Roesch, Jatan Buch, Gregor Ramien, Johannes Haux, Pierre Gentine

机构 * Columbia University（哥伦比亚大学） ； kausable GmbH（kausable公司） ； Aeolus Labs（Aeolus实验室） 纠错

Comments NeurIPS 2025

Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning

Dipam Goswami, Simone Magistri, Kai Wang, Bartłomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer

机构 * Department of Computer Science, Universitat Autònoma de Barcelona（巴塞罗那自治大学计算机科学系） ； Computer Vision Center（计算机视觉中心） ； Media Integration and Communication Center (MICC), University of Florence（佛罗伦萨大学媒体整合与通信中心） ； IDEAS Research Institute（IDEAS研究机构） ； City University of Hong Kong（香港城市大学） ； Program of Computer Science, City University of Hong Kong (Dongguan)（香港城市大学（东莞）计算机科学项目） 纠错

Comments Accepted at NeurIPS 2025

Provable Watermarking for Data Poisoning Attacks

Yifan Zhu, Lijia Yu, Xiao-Shan Gao

机构 * State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences（数学科学国家重点实验室，数学与系统科学研究院，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） ； Institute of AI for Industries, Nanjing, China（产业人工智能研究院，南京，中国） 纠错

Comments 42 pages, NeurIPS 2025

Journal ref NeurIPS 2025

Beyond Pairwise Connections: Extracting High-Order Functional Brain Network Structures under Global Constraints

Ling Zhan, Junjie Huang, Xiaoyao Yu, Wenyu Chen, Tao Jia

机构 * College of Computer and Information Science, Southwest University（西南大学计算机与信息科学学院） ； Chongqing Key Laboratory of Brain-Inspired Cognitive Computing and Educational Rehabilitation for Children with Special Needs, Chongqing Normal University（重庆脑启发认知计算与特殊需要儿童教育康复重点实验室，重庆师范大学） ； School of Science, Guangxi University of Science and Technology（广西科技大学科学学院） ； College of Computer and Information Science, Chongqing Normal University（重庆师范大学计算机与信息科学学院） 纠错

Comments 33 pages, 10 figures, NeurIPS

RADAR: Mechanistic Pathways for Detecting Data Contamination in LLM Evaluation

Ashish Kattamuri, Harshwardhan Fartale, Arpita Vats, Rahul Raja, Ishita Prasad

机构 * Proofpoint ； Indian Institute of Science（印度科学研究院） ； Linkedin ； Meta FAIR 纠错

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

The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective

Thai-Hoang Pham, Jiayuan Chen, Seungyeon Lee, Yuanlong Wang, Sayoko Moroi, Xueru Zhang, Ping Zhang

机构 * Department of Computer Science and Engineering, The Ohio State University（计算机科学与工程系，俄亥俄州立大学） ； Department of Biomedical Informatics, The Ohio State University（生物医学信息学系，俄亥俄州立大学） ； Department of Ophthalmology and Visual Sciences, The Ohio State University（眼科学与视觉科学系，俄亥俄州立大学） 纠错

Comments Accepted at NeurIPS 2025

Long-Tailed Recognition via Information-Preservable Two-Stage Learning

Fudong Lin, Xu Yuan

机构 * Department of Computer & Information Sciences University of Delaware（计算机与信息科学系 大田纳西大学） 纠错

Comments Accepted by NeurIPS 2025 as Spotlight

Conformal Risk Training: End-to-End Optimization of Conformal Risk Control

Christopher Yeh, Nicolas Christianson, Adam Wierman, Yisong Yue

Comments accepted to NeurIPS 2025

When to Reason: Semantic Router for vLLM

Chen Wang, Xunzhuo Liu, Yuhan Liu, Yue Zhu, Xiangxi Mo, Junchen Jiang, Huamin Chen

机构 * IBM Research（IBM研究院） ； Tencent（腾讯） ； University of Chicago（芝加哥大学） ； UC Berkeley（伯克利大学） ； Red Hat（红帽公司） 纠错

Comments 5 pages, excluding references and appendix. To be appeared at Workshop on ML for Systems at NeurIPS 2025, December 6, 2025 https://mlforsystems.org/

Next Semantic Scale Prediction via Hierarchical Diffusion Language Models

Cai Zhou, Chenyu Wang, Dinghuai Zhang, Shangyuan Tong, Yifei Wang, Stephen Bates, Tommi Jaakkola

机构 * Massachusetts Institute of Technology（麻省理工学院） ； Microsoft Research（微软研究院） ； Mila - Quebec AI Institute（魁北克AI研究所） 纠错

Comments Accepted to NeurIPS 2025

LLMs Show Surface-Form Brittleness Under Paraphrase Stress Tests

Juan Miguel Navarro Carranza

机构 * Stanford University（斯坦福大学） 纠错

Comments NeurIPS 2025 Workshop. Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling. Selected for contributed talk

Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection

Cong Zeng, Shengkun Tang, Yuanzhou Chen, Zhiqiang Shen, Wenchao Yu, Xujiang Zhao, Haifeng Chen, Wei Cheng, Zhiqiang Xu

机构 * MBZUAI ； UCLA（加州大学洛杉矶分校） ； NEC Lab（日本电装实验室） 纠错

Journal ref NeurIPS 2025

Systematic Diagnosis of Brittle Reasoning in Large Language Models

V. S. Raghu Parupudi

机构 * University of California, San Diego（加州大学圣地亚哥分校） 纠错

Comments Submitted to NEURIPS-2025 MATHAI workshop

Benchmarking AI-evolved cosmological structure formation

Xiaofeng Dong, Nesar Ramachandra, Salman Habib, Katrin Heitmann

Comments Expanded and thoroughly revised version of our prior NeurIPS submission (arXiv:2112.05681; which has no DOI), with new sections, experiments, and analyses

Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention

Xin Zou, Di Lu, Yizhou Wang, Yibo Yan, Yuanhuiyi Lyu, Xu Zheng, Linfeng Zhang, Xuming Hu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； The Hong Kong University of Science and Technology（香港科学与技术大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

Comments Accepted by NeurIPS 2025 main

Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning

Lei Wang, Jieming Bian, Letian Zhang, Jie Xu

机构 * University of Florida（佛罗里达大学） ； Middle Tennessee State University（中田纳西州立大学） 纠错

Comments Accepted to NeurIPS 2025

TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation

Zhekai Chen, Ruihang Chu, Yukang Chen, Shiwei Zhang, Yujie Wei, Yingya Zhang, Xihui Liu

机构 * HKU MMLab（香港大学多模态实验室） ； Tongyi Lab, Alibaba Group（阿里云实验室） 纠错

Comments Accepted to NeurIPS 2025

RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models

Yeongtak Oh, Dohyun Chung, Juhyeon Shin, Sangha Park, Johan Barthelemy, Jisoo Mok, Sungroh Yoon

Comments Accepted to NeurIPS 2025

Multi-Scale Finetuning for Encoder-based Time Series Foundation Models

Zhongzheng Qiao, Chenghao Liu, Yiming Zhang, Ming Jin, Quang Pham, Qingsong Wen, P. N. Suganthan, Xudong Jiang, Savitha Ramasamy

机构 * Nanyang Technological University（南洋理工大学） ； Institute for Infocomm Research, A*STAR（信息通信研究所，A*STAR） ； Salesforce AI Research（Salesforce人工智能研究） ； Griffith University（格里菲斯大学） ； Squirrel Ai Learning（Squirrel AI学习） ； Qatar University（卡塔尔大学） 纠错

Comments Accepted by NeurIPS 2025

DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models

Ziyi Wu, Anil Kag, Ivan Skorokhodov, Willi Menapace, Ashkan Mirzaei, Igor Gilitschenski, Sergey Tulyakov, Aliaksandr Siarohin

机构 * Snap Research ； University of Toronto（多伦多大学） ； Vector Institute（向量研究所） 纠错

Comments NeurIPS 2025 Spotlight. Project page: https://snap-research.github.io/DenseDPO/

System Prompt Optimization with Meta-Learning

Yumin Choi, Jinheon Baek, Sung Ju Hwang

机构 * KAIST（韩国科学技术院） 纠错

Comments NeurIPS 2025

CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection

Zhichao Sun, Huazhang Hu, Yidong Ma, Gang Liu, Yibo Chen, Xu Tang, Yao Hu, Yongchao Xu

Comments Accepted at NeurIPS 2025

Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research

Xiang Liu, Penglei Sun, Shuyan Chen, Longhan Zhang, Peijie Dong, Huajie You, Yongqi Zhang, Chang Yan, Xiaowen Chu, Tong-yi Zhang

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； Guangzhou Municipal Key Laboratory of Materials Informatics（广州市材料信息学重点实验室） 纠错

Comments EMNLP 2025 Findings; NeurIPS 2025 AI for Science Workshop