DP$^2$O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
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）
Comments Accept by NeurIPS 2025
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Unifying and Enhancing Graph Transformers via a Hierarchical Mask Framework
机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Beihang University（北航）
Comments Accepted by NeurIPS 2025 (Poster)
Detection and Simulation of Urban Heat Islands Using a Fine-Tuned Geospatial Foundation Model for Microclimate Impact Prediction
机构 * IBM Research – Europe（IBM欧洲研究院） ； IBM Research – Africa（IBM非洲研究院）
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
机构 * Visual AI Lab, The University of Hong Kong（香港大学视觉人工智能实验室）
Comments Accepted to NeurIPS 2025
OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales
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）
Comments Neural Information Processing Systems (NeurIPS 2025)
Learning Task-Agnostic Representations through Multi-Teacher Distillation
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）
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
Comments NeurIPS 2025
Crucible: Quantifying the Potential of Control Algorithms through LLM Agents
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）
Comments NeurIPS 2025
Simple and Efficient Heterogeneous Temporal Graph Neural Network
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））
Comments Accepted by Neurips 2025
Heterogeneous Adversarial Play in Interactive Environments
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）
Comments NeurIPS 2025
Towards Unsupervised Open-Set Graph Domain Adaptation via Dual Reprogramming
机构 * Nanjing University（南京大学） ； National University of Singapore（新加坡国立大学）
Comments Accepted by NeurIPS 2025
Learning to Flow from Generative Pretext Tasks for Neural Architecture Encoding
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）
Comments Published as a conference paper at NeurIPS 2025
Computable universal online learning
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）
Comments Accepted for presentation at NeurIPS 2025
Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching
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）
Comments Paper accepted by NeurIPS 2025
Fostering the Ecosystem of AI for Social Impact Requires Expanding and Strengthening Evaluation Standards
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）
Comments Accepted at NeurIPS 2025
AgentChangeBench: A Multi-Dimensional Evaluation Framework for Goal-Shift Robustness in Conversational AI
机构 * Algoverse ； Microsoft
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
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）
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
机构 * AWS Generative AI Innovation Center（AWS生成式AI创新中心）
Comments Neural Information Processing Systems (NeurIPS 2025) Workshop: Evaluating the Evolving LLM Lifecycle
Rethinking PCA Through Duality
Comments NeurIPS 2025 poster
Gradient Variance Reveals Failure Modes in Flow-Based Generative Models
Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025)
CaMiT: A Time-Aware Car Model Dataset for Classification and Generation
机构 * Université Paris-Saclay, CEA, List（巴黎-萨克雷大学，CEA，List）
Comments To be published in NeurIPS 2025 Track on Datasets and Benchmarks
Offline Policy Evaluation of Multi-Turn LLM Health Coaching with Real Users
机构 * Stevens Institute of Technology（史蒂文斯理工学院）
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
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）
Comments 13 pages, accepted by NeurIPS 2025 (spotlight)
Fair Minimum Labeling: Efficient Temporal Network Activations for Reachability and Equity
机构 * University of Liverpool（利物浦大学）
Comments Accepted at NeurIPS 2025
Evaluating Program Semantics Reasoning with Type Inference in System F
机构 * University of California, Davis（加州大学戴维斯分校） ； University of Hong Kong（香港大学）
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
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）
Comments NeurIPS'25 accepted
The Narcissus Hypothesis: Descending to the Rung of Illusion
Comments NeurIPS 2025 Workshop on Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling
Program Synthesis via Test-Time Transduction
机构 * Dept. of ECE, Seoul National University（电子工程系，首尔国立大学） ； IPAI, Seoul National University（IPAI，首尔国立大学） ； Adobe Research（Adobe研究院）
Comments NeurIPS 2025
Every Camera Effect, Every Time, All at Once: 4D Gaussian Ray Tracing for Physics-based Camera Effect Data Generation
机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； National Yang Ming Chiao Tung University（国立阳明交通大学） ； National Central University（国立中央大学） ； Research Center for Information Technology Innovation, Academia Sinica（学术院资讯科技创新研究中心）
Comments Paper accepted to NeurIPS 2025 Workshop SpaVLE. Project page: https://shigon255.github.io/4DGRT-project-page/
Can Large Language Models Master Complex Card Games?
机构 * Nankai University（南开大学） ； Tsinghua University（清华大学） ； Beijing University of Posts and Telecommunications（北京邮电大学） ； Zhipu AI（智谱AI） ； Bosch Center for Artificial Intelligence（博世人工智能中心）
Comments Accepted by NeurIPS 2025
