NeurIPS

AdaptGrad: Adaptive Sampling to Reduce Noise

Linjiang Zhou, Chao Ma, Zepeng Wang, Libing Wu, Xiaochuan Shi

机构 * Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education School of Cyber Science and Engineering, Wuhan University（航天信息安全与可信计算重点实验室，教育部网络安全科学与工程学院，武汉大学） ； School of Cyber Science and Engineering, Wuhan University（网络安全科学与工程学院，武汉大学） 纠错

Comments Accepted by NeurIPS 2025

LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits

Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal

机构 * UNC Chapel Hill（杜克大学夏洛特分校） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

Comments NeurIPS 2025 camera-ready. First two authors contributed equally. Code: https://github.com/duykhuongnguyen/LASeR-MAB

PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization

Federico Berto, Chuanbo Hua, Laurin Luttmann, Jiwoo Son, Junyoung Park, Kyuree Ahn, Changhyun Kwon, Lin Xie, Jinkyoo Park

机构 * KAIST（韩国科学技术院） ； Omelet ； Radical Numerics ； Leuphana University（莱普大学） ； Brandenburg University of Technology（勃兰登堡技术大学） 纠错

Comments Accepted at NeurIPS 2025

Towards Context-Aware Domain Generalization: Understanding the Benefits and Limits of Marginal Transfer Learning

Jens Müller, Lars Kühmichel, Martin Rohbeck, Stefan T. Radev, Ullrich Köthe

机构 * Independent Researcher（独立研究者） ； Computational Statistics TU Dortmund University（计算统计学 TU Dortmund 大学） ； Division of Computational Genomics and Systems Genetics（计算基因组学和系统遗传学 division） ； DKFZ（德国医学科学院） ； Department of Cognitive Science（认知科学系） ； Rensselaer Polytechnic Institute（伦斯勒理工学院） ； Computer Vision and Learning Lab（计算机视觉与学习实验室） ； Heidelberg University（海德堡大学） 纠错

Comments 10 pages, 4 figures, NeurIPS Workshop: Reliable ML from Unreliable Data

DP$^2$O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution

Rongyuan Wu, Lingchen Sun, Zhengqiang Zhang, Shihao Wang, Tianhe Wu, Qiaosi Yi, Shuai Li, Lei Zhang

机构 * The Hong Kong Polytechnic University（香港理工大学） ； OPPO Research Institute（OPPO研究院） ； City University of Hong Kong（香港城市大学） 纠错

Comments Accept by NeurIPS 2025

Unifying and Enhancing Graph Transformers via a Hierarchical Mask Framework

Yujie Xing, Xiao Wang, Bin Wu, Hai Huang, Chuan Shi

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Beihang University（北航） 纠错

Comments Accepted by NeurIPS 2025 (Poster)

Detection and Simulation of Urban Heat Islands Using a Fine-Tuned Geospatial Foundation Model for Microclimate Impact Prediction

Jannis Fleckenstein, David Kreismann, Tamara Rosemary Govindasamy, Thomas Brunschwiler, Etienne Vos, Mattia Rigotti

机构 * IBM Research – Europe（IBM欧洲研究院） ； IBM Research – Africa（IBM非洲研究院） 纠错

Comments 10 pages, 9 figures. Accepted at the NeurIPS 2025 Workshop on Tackling Climate Change with Machine Learning

SEAL: Semantic-Aware Hierarchical Learning for Generalized Category Discovery

Zhenqi He, Yuanpei Liu, Kai Han

机构 * Visual AI Lab, The University of Hong Kong（香港大学视觉人工智能实验室） 纠错

Comments Accepted to NeurIPS 2025

OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales

Tung Nguyen, Tuan Pham, Troy Arcomano, Veerabhadra Kotamarthi, Ian Foster, Sandeep Madireddy, Aditya Grover

机构 * UCLA（加州大学洛杉矶分校） ； UCI（加州大学洛杉矶分校） ； Argonne National Laboratory（阿贡国家实验室） ； Allen Institute for AI（人工智能研究院） 纠错

Comments Neural Information Processing Systems (NeurIPS 2025)

Learning Task-Agnostic Representations through Multi-Teacher Distillation

Philippe Formont, Maxime Darrin, Banafsheh Karimian, Jackie CK Cheung, Eric Granger, Ismail Ben Ayed, Mohammadhadi Shateri, Pablo Piantanida

机构 * Universite Paris-Saclay（巴黎-萨克雷大学） ； Mila - Quebec AI Institute（魁北克AI研究所） ； McGill University（麦吉尔大学） ； ETS Montreal（蒙特利尔工程师学院） ； ILLS ； CNRS - CentraleSupelec - Universite Paris-Saclay（国家科学研究中心-中央超导大学-巴黎-萨克雷大学） 纠错

Comments NeurIPS-2025

Journal ref Advances in Neural Information Processing Systems 38 (NeurIPS 2025)

CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder

Yongmin Lee, Hye Won Chung

Comments NeurIPS 2025

Crucible: Quantifying the Potential of Control Algorithms through LLM Agents

Lianchen Jia, Chaoyang Li, Qian Houde, Tianchi Huang, Jiangchuan Liu, Lifeng Sun

机构 * Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） ； Simon Fraser University（西蒙 Fraser大学） 纠错

Comments NeurIPS 2025

Simple and Efficient Heterogeneous Temporal Graph Neural Network

Yili Wang, Tairan Huang, Changlong He, Qiutong Li, Jianliang Gao

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

Comments Accepted by Neurips 2025

Heterogeneous Adversarial Play in Interactive Environments

Manjie Xu, Xinyi Yang, Jiayu Zhan, Wei Liang, Chi Zhang, Yixin Zhu

机构 * Institute for Artificial Intelligence, Peking University（人工智能研究院，北京大学） ； School of Psychological and Cognitive Sciences, Peking University（心理与认知科学学院，北京大学） ； School of Computer Science & Technology, Beijing Institute of Technology（计算机科学与技术学院，北京理工大学） ； State Key Lab of General AI, Peking University（通用人工智能国家重点实验室，北京大学） ； Beijing Key Laboratory of Behavior and Mental Health, Peking University（北京行为与心理健康重点实验室，北京大学） ； Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing（北京理工大学长江三角洲地区研究院，嘉兴） ； Embodied Intelligence Lab, PKU-Wuhan Institute for Artificial Intelligence（具身智能实验室，北京大学-武汉人工智能研究院） 纠错

Comments NeurIPS 2025

Towards Unsupervised Open-Set Graph Domain Adaptation via Dual Reprogramming

Zhen Zhang, Bingsheng He

机构 * Nanjing University（南京大学） ； National University of Singapore（新加坡国立大学） 纠错

Comments Accepted by NeurIPS 2025

Learning to Flow from Generative Pretext Tasks for Neural Architecture Encoding

Sunwoo Kim, Hyunjin Hwang, Kijung Shin

机构 * Kim Jaechul Graduate School of AI（金 Jaechul人工智能研究生院） ； School of Electrical Engineering（电气工程学院） ； Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院） 纠错

Comments Published as a conference paper at NeurIPS 2025

Computable universal online learning

Dariusz Kalociński, Tomasz Steifer

机构 * Institute of Computer Science Polish Academy of Sciences（计算机科学研究所波兰科学院） ； Institute of Fundamental Technological Research Polish Academy of Sciences（基础技术研究所波兰科学院） 纠错

Comments Accepted for presentation at NeurIPS 2025

Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching

Zhong Li, Qi Huang, Yuxuan Zhu, Lincen Yang, Mohammad Mohammadi Amiri, Niki van Stein, Matthijs van Leeuwen

机构 * The Leiden Institute of Advanced Computer Science (LIACS), Leiden University（莱顿先进计算机科学研究所（LIACS）、莱顿大学） ； Department of Computer Science, Rensselaer Polytechnic Institute（伦斯勒理工学院计算机科学系） ； The Intelligent Computing Research Center, Great Bay University（大湾大学智能计算研究中心） 纠错

Comments Paper accepted by NeurIPS 2025

Fostering the Ecosystem of AI for Social Impact Requires Expanding and Strengthening Evaluation Standards

Bryan Wilder, Angela Zhou

机构 * Bryan Wilder Machine Learning Department（比尔·韦尔德机器学习部门） ； Carnegie Mellon University（卡内基梅隆大学） ； Angela Zhou Department of Data Sciences and Operations（安杰莉娅·周数据科学与运营部门） ； Department of Computer Science University of Southern California（计算机科学系美国南加州大学） 纠错

Comments Accepted at NeurIPS 2025

AgentChangeBench: A Multi-Dimensional Evaluation Framework for Goal-Shift Robustness in Conversational AI

Manik Rana, Calissa Man, Anotida Expected Msiiwa, Jeffrey Paine, Kevin Zhu, Sunishchal Dev, Vasu Sharma, Ahan M R

机构 * Algoverse ； Microsoft 纠错

Comments Accepted to 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Multi-Turn Interactions in Large Language Models

Journal ref Neural Information Processing Systems (NeurIPS 2025)

Hearing Health in Home Healthcare: Leveraging LLMs for Illness Scoring and ALMs for Vocal Biomarker Extraction

Yu-Wen Chen, William Ho, Sasha M. Vergez, Grace Flaherty, Pallavi Gupta, Zhihong Zhang, Maryam Zolnoori, Margaret V. McDonald, Maxim Topaz, Zoran Kostic, Julia Hirschberg

机构 * The Fu Foundation School of Engineering and Applied Science, Columbia University（哥伦比亚大学福基金会工程与应用科学学院） ； School of Nursing, Columbia University（哥伦比亚大学护理学院） ； Center for Home Care Policy & Research, VNS Health（VNS健康居家护理政策与研究中心） 纠错

Comments The Second Workshop on GenAI for Health at NeurIPS 2025

Learning from Generalization Patterns: An Evaluation-Driven Approach to Enhanced Data Augmentation for Fine-Tuning Small Language Models

Huan Song, Deeksha Razdan, Yiyue Qian, Arijit Ghosh Chowdhury, Parth Patwa, Aman Chadha, Shinan Zhang, Sharlina Keshava, Hannah Marlowe

机构 * AWS Generative AI Innovation Center（AWS生成式AI创新中心） 纠错

Comments Neural Information Processing Systems (NeurIPS 2025) Workshop: Evaluating the Evolving LLM Lifecycle

Rethinking PCA Through Duality

Jan Quan, Johan Suykens, Panagiotis Patrinos

Comments NeurIPS 2025 poster

Gradient Variance Reveals Failure Modes in Flow-Based Generative Models

Teodora Reu, Sixtine Dromigny, Michael Bronstein, Francisco Vargas

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

CaMiT: A Time-Aware Car Model Dataset for Classification and Generation

Frédéric LIN, Biruk Abere Ambaw, Adrian Popescu, Hejer Ammar, Romaric Audigier, Hervé Le Borgne

机构 * Université Paris-Saclay, CEA, List（巴黎-萨克雷大学，CEA，List） 纠错

Comments To be published in NeurIPS 2025 Track on Datasets and Benchmarks

Offline Policy Evaluation of Multi-Turn LLM Health Coaching with Real Users

Melik Ozolcer, Sang Won Bae

机构 * Stevens Institute of Technology（史蒂文斯理工学院） 纠错

Comments Accepted to the NeurIPS 2025 Workshop on Multi-Turn Interactions in Large Language Models

Uncertain Knowledge Graph Completion via Semi-Supervised Confidence Distribution Learning

Tianxing Wu, Shutong Zhu, Jingting Wang, Ning Xu, Guilin Qi, Haofen Wang

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跨学科应用重点实验室（东南大学）） ； College of Design and Innovation, Tongji University, China（同济大学设计与创新学院） 纠错

Comments 13 pages, accepted by NeurIPS 2025 (spotlight)

Fair Minimum Labeling: Efficient Temporal Network Activations for Reachability and Equity

Lutz Oettershagen, Othon Michail

机构 * University of Liverpool（利物浦大学） 纠错

Comments Accepted at NeurIPS 2025

Evaluating Program Semantics Reasoning with Type Inference in System F

Yifeng He, Luning Yang, Christopher Castro Gaw Gonzalo, Hao Chen

机构 * University of California, Davis（加州大学戴维斯分校） ； University of Hong Kong（香港大学） 纠错

Comments NeurIPS '25, package released at: https://github.com/SecurityLab-UCD/TF-Bench

Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning

Zhuang Qi, Pan Yu, Lei Meng, Sijin Zhou, Han Yu, Xiaoxiao Li, Xiangxu Meng

机构 * School of Software, Shandong University（山东大学软件学院） ； AIM Lab, Faculty of Engineering, Monash University（莫纳什大学工程学院AIM实验室） ； College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院） ； Department of Electrical and Computer Engineering, University of British Columbia（不列颠哥伦比亚大学电气与计算机工程系） ； Vector Institute, Canada（加拿大向量研究所） 纠错

Comments NeurIPS'25 accepted