DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images
机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Comments Accepted to NeurIPS 2025
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Training a Foundation Model for Materials on a Budget
机构 * Department of Electrical Engineering and Computer Science（电气工程与计算机科学系）
Comments To appear at the NeurIPS 2025 Workshop on AI for Accelerated Materials Discovery
Feedback Guidance of Diffusion Models
机构 * Ghent University - imec（根特大学 - imec） ； Donders Institute for Brain Cognition and Behaviour（大脑认知与行为研究所）
Comments Article accepeted as poster at the 39th Annual Conference on Neural Information Processing Systems (NeurIPS25). Code is available at: https://github.com/FelixKoulischer/FBG_using_edm2
Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL
机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； Pengcheng Laboratory（鹏城实验室） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Journal ref NeurIPS 2025
Multi-Turn Human-LLM Interaction Through the Lens of a Two-Way Intelligibility Protocol
机构 * Dept. of Electrical and Electronics Engineering（电子工程系） ； BITS Pilani, K.K. Birla Goa Campus（比斯汉学院，戈阿校园） ； Machine Learning Department（机器学习系） ； Carnegie Mellon University（卡内基梅隆大学） ； Centre for Health Informatics（健康信息学中心） ； Macquarie University, Sydney（麦考瑞大学，悉尼） ； Dept. of Computer Science & Information Systems（计算机科学与信息系统系）
Comments Multi-Turn Interactions in Large Language Models (MTI-LLM) Workshop at NeurIPS 2025
DemandCast: Global hourly electricity demand forecasting
机构 * Open Energy Transition（开放能源转型）
Comments 7 pages, 4 figures, accepted at the NeurIPS 2025 Workshop: Tackling Climate Change with Machine Learning
Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training
机构 * State Key Laboratory of Digital Intelligent Modeling and Simulation（数字智能建模与仿真国家重点实验室） ； National University of Defense Technology（国防科技大学） ； School of Cyber Science and Technology（网络安全科学与技术学院） ； Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）
Comments This paper has been accepted by NeurIPS 2025 (Spotlight)
PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimation
机构 * Shanghai Jiao Tong University（上海交通大学） ； Westlake University（西湖大学） ； AIMS Lab, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）AIMS实验室） ； The Hong Kong University of Science and Technology（香港科技大学）
Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025)
Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers
机构 * School of Information and Software Engineering University of Electronic Science and Technology of China（信息与软件工程学院 电子科技大学）
Comments Accepted by NeurIPS 2025
MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation
Comments Accepted By NeurIPS 2025
SIMU: Selective Influence Machine Unlearning
机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Comments Accepted to NeurIPS 2025 Workshop: Constrained Optimization for Machine Learning (COML)
Rectified-CFG++ for Flow Based Models
机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Comments Accepted at NeurIPS 2025
Evaluating and Learning Optimal Dynamic Treatment Regimes under Truncation by Death
Comments 30 pages, 5 figures, 6 tables, The Thirty-Ninth Annual Conference on Neural Information Processing Systems
ExpertAgent: Enhancing Personalized Education through Dynamic Planning and Retrieval-Augmented Long-Chain Reasoning
机构 * Department of Computer Science（计算机科学系） ； San Francisco State University（旧金山州立大学） ； Department of Mechanical & Industrial Engineering（机械与工业工程系） ； Louisiana State University（路易斯安那州立大学）
Comments Manuscript previously submitted to the NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models (LAW 2025)
Simulation-based inference for neutrino interaction model parameter tuning
Comments Accepted contribution to NeurIPS 2025 Workshop on Machine Learning and the Physical Sciences. 7 pages, 1 figure
MacroBench: A Novel Testbed for Web Automation Scripts via Large Language Models
机构 * KAIST（韩国科学技术院）
Comments NeurIPS 2025 Workshop on Lock-LLM
Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding
Comments Accepted by NeurIPS 2025
DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm
机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院） ； University International College, Macau University of Science and Technology（澳门科技大学国际学院） ； Cyberspace Institute of Advanced Technology, Guangzhou University（广州大学网络安全技术研究所） ； Institute of Computing Science, Chinese Academy of Sciences（中国科学院计算科学研究所）
Comments NeurIPS 2025 Spotlight
FireGNN: Neuro-Symbolic Graph Neural Networks with Trainable Fuzzy Rules for Interpretable Medical Image Classification
机构 * Imperial College London（伦敦帝国学院）
Comments Accepted at NeurIPS 2025 Conference (Workshop Track), San Diego, USA
X-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates
机构 * AIM Intelligence（AIM智能）
Comments NeurIPS 2025 Workshop on Lock-LLM
Adaptive Originality Filtering: Rejection Based Prompting and RiddleScore for Culturally Grounded Multilingual Riddle Generation
机构 * Algoverse AI Research（Algoverse AI研究院）
Comments Paper was accepted in to NeurIPS 2025 Workshop GenProCC
ObjexMT: Objective Extraction and Metacognitive Calibration for LLM-as-a-Judge under Multi-Turn Jailbreaks
Comments NeurIPS 2025 Workshop on MTI-LLM
Martingale Posterior Neural Networks for Fast Sequential Decision Making
机构 * Oxford-Man Institute of Quantitative Finance（牛津-曼定量金融研究所） ； Mathematical Institute, University of Oxford（牛津大学数学研究所） ； Google Deepmind（谷歌DeepMind）
Journal ref Advances in Neural Information Processing Systems 39 (NeurIPS 2025)
Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English Varieties
机构 * KAIST（韩国科学技术院） ； Suresoft Technologies（Suresoft技术公司） ； Seoul National University（首尔国立大学）
Comments NeurIPS 2025 Track on Datasets and Benchmarks (27 pages, 6 figures, 16 tables)
SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning
Comments Accepd by NeurIPS 2025
Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks
机构 * School of Computer and Artificial Intelligence, Zhengzhou University（计算机与人工智能学院，郑州大学） ； Wuhan University（武汉大学） ； Harbin Institution of Technology（哈尔滨理工大学） ； Dalian Maritime University（大连海事大学） ； National Tsinghua University（清华大学）
Comments Accepted by NeurIPS 2025
It's All in the Mix: Wasserstein Classification and Regression with Mixed Features
Comments 61 pages (34 main + proofs), 8 tables, 2 colored plots, an early version appeared in NeurIPS 2022 main track (arXiv 2205.13501)
Mass Conservation on Rails -- Rethinking Physics-Informed Learning of Ice Flow Vector Fields
机构 * School of Computer Science（计算机科学学院） ； The University of Sydney（悉尼大学） ； Human Technology Institute（人机技术研究所） ； University of Technology Sydney（技术大学悉尼分校） ； NVIDIA（NVIDIA公司）
Comments Accepted at the Tackling Climate Change with Machine Learning Workshop at NeurIPS 2025. 9 pages, 4 figures
RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation
机构 * University of Surrey（塞雷尔大学） ； Simon Fraser University（西蒙弗雷泽大学） ； University of Copenhagen（哥本哈根大学）
Comments Accepted at NeurIPS 2025
Valid Inference with Imperfect Synthetic Data
机构 * Machine Learning Department, Carnegie Mellon University（卡内基梅隆大学机器学习系） ； University of Zurich（苏黎世大学）
Comments NeurIPS 2025
