NeurIPS

Scene-Aware Urban Design: A Human-AI Recommendation Framework Using Co-Occurrence Embeddings and Vision-Language Models

Rodrigo Gallardo, Oz Fishman, Alexander Htet Kyaw

机构 * Department of Architecture（建筑系） ； Department of EECS（电子工程与计算机科学系） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

Comments Accepted to NEURIPS 2025 Creative AI Track

Approximating Shapley Explanations in Reinforcement Learning

Daniel Beechey, Özgür Şimşek

机构 * University of Bath（巴斯大学） 纠错

Comments Camera-ready version. Published at the Conference on Neural Information Processing Systems (NeurIPS 2025)

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

Visual Exploration of Feature Relationships in Sparse Autoencoders with Curated Concepts

Xinyuan Yan, Shusen Liu, Kowshik Thopalli, Bei Wang

机构 * University of Utah（犹他大学） ； Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室） 纠错

Comments 8 pages (5 main paper+3 refernce), 2 figures, pulished at Mechanistic Interpretability Workshop at NeurIPS 2025

Who Gets Heard? Rethinking Fairness in AI for Music Systems

Atharva Mehta, Shivam Chauhan, Megha Sharma, Gus Xia, Kaustuv Kanti Ganguli, Nishanth Chandran, Zeerak Talat, Monojit Choudhury

机构 * MBZUAI, UAE（MBZUAI，阿联酋） ； Zayed University, UAE（扎耶德大学，阿联酋） ； Microsoft, India（微软，印度） ； University of Edinburgh, UK（爱丁堡大学，英国） 纠错

Comments 7 pages, Accepted at NeurIPS'25 workshop on AI for Music

Interaction-Centric Knowledge Infusion and Transfer for Open-Vocabulary Scene Graph Generation

Lin Li, Chuhan Zhang, Dong Zhang, Chong Sun, Chen Li, Long Chen

机构 * HKUST（香港科技大学） ； AI Chip Center for Emerging Smart Systems（新兴智能系统人工智能芯片中心） ； Tencent（腾讯） 纠错

Comments Accepted by NeurIPS 2025

Near-Exponential Savings for Mean Estimation with Active Learning

Julian M. Morimoto, Jacob Goldin, Daniel E. Ho

机构 * University of California, Berkeley（加州大学伯克利分校） ； Stanford Law School（斯坦福法学院） ； World Bank Group（世界银行集团） ； University of Chicago（芝加哥大学） ； Stanford University（斯坦福大学） 纠错

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

VMDT: Decoding the Trustworthiness of Video Foundation Models

Yujin Potter, Zhun Wang, Nicholas Crispino, Kyle Montgomery, Alexander Xiong, Ethan Y. Chang, Francesco Pinto, Yuqi Chen, Rahul Gupta, Morteza Ziyadi, Christos Christodoulopoulos, Bo Li, Chenguang Wang, Dawn Song

机构 * University of California, Berkeley（加州大学伯克利分校） ； University of California, Santa Cruz（加州大学圣克ruz分校） ； University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； University of Chicago（芝加哥大学） ； Amazon（亚马逊） ； Information Commissioner’s Office（信息专员办公室） 纠错

Comments NeurIPS 2025 Datasets & Benchmarks

Physics-Guided Machine Learning for Uncertainty Quantification in Turbulence Models

Minghan Chu, Weicheng Qian

机构 * Department of Mechanical and Materials Engineering, Queen’s University（皇后大学机械与材料工程系） ； Institute of Mechanics, Chinese Academy of Sciences（中国科学院力学研究所） 纠错

Comments Accepted to NeurIPS 2025 Workshop on Machine Learning and the Physical Sciences (ML4PS), non-archival

Grounding Foundational Vision Models with 3D Human Poses for Robust Action Recognition

Nicholas Babey, Tiffany Gu, Yiheng Li, Cristian Meo, Kevin Zhu

机构 * Arizona State University（亚利桑那州立大学） ； Emory University（埃默里大学） ； University of California, Berkeley（加州大学伯克利分校） ； Delft University of Technology（代尔夫特理工大学） ； Algoverse AI Research（Algoverse AI 研究） 纠错

Comments Accepted at NeurIPS 2025 SpaVLE, for code see https://github.com/nbabey20/groundactrec , 9 pages, 1 figure

Frequency Matters: When Time Series Foundation Models Fail Under Spectral Shift

Tianze Wang, Sofiane Ennadir, John Pertoft, Gabriela Zarzar Gandler, Lele Cao, Zineb Senane, Styliani Katsarou, Sahar Asadi, Axel Karlsson, Oleg Smirnov

机构 * King AI Labs, Microsoft Gaming（King AI实验室，微软游戏） ； KTH Royal Institute of Technology（皇家理工学院） ； Kreditz AB（Kreditz公司） ； Fever Energy（Fever能源） 纠错

Comments Accepted and presented at NeurIPS 2025 Workshop on Recent Advances in Time Series Foundation Models (BERT2S)

Personalized Image Editing in Text-to-Image Diffusion Models via Collaborative Direct Preference Optimization

Connor Dunlop, Matthew Zheng, Kavana Venkatesh, Pinar Yanardag

机构 * Virginia Tech（弗吉尼亚理工大学） 纠错

Comments Published at NeurIPS'25 Main Conference

Walking the Schrödinger Bridge: A Direct Trajectory for Text-to-3D Generation

Ziying Li, Xuequan Lu, Xinkui Zhao, Guanjie Cheng, Shuiguang Deng, Jianwei Yin

机构 * Zhejiang University（浙江大学） ； University of Western Australia（西澳大学） 纠错

Comments NeurIPS 2025; https://github.com/emmaleee789/TraCe.git

AutoHood3D: A Multi-Modal Benchmark for Automotive Hood Design and Fluid-Structure Interaction

Vansh Sharma, Harish Jai Ganesh, Maryam Akram, Wanjiao Liu, Venkat Raman

机构 * University of Michigan Ann Arbor（密歇根大学安娜堡分校） ； Ford Research and Innovation Center（福特研究与创新中心） 纠错

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

GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning

Haonan Yuan, Qingyun Sun, Junhua Shi, Xingcheng Fu, Bryan Hooi, Jianxin Li, Philip S. Yu

机构 * SKLCCSE, School of Computer Science and Engineering, Beihang University（北京航空航天大学信息与电子技术学院） ； Key Lab of Education Blockchain and Intelligent Technology, Guangxi Normal University（广西师范大学教育区块链与智能技术重点实验室） ； School of Computing, National University of Singapore（新加坡国立大学计算机学院） ； Department of Computer Science, University of Illinois, Chicago（伊利诺伊大学芝加哥分校计算机科学系） 纠错

Comments Accepted by the NeurIPS 2025

SMAGDi: Socratic Multi Agent Interaction Graph Distillation for Efficient High Accuracy Reasoning

Aayush Aluru, Myra Malik, Samarth Patankar, Spencer Kim, Kevin Zhu, Sean O'Brien, Vasu Sharma

机构 * Algoverse AI Research（Algoverse AI研究） 纠错

Comments Multi-Turn Interactions in Large Language Models (MTI-LLM) Workshop at NeurIPS 2025

Emergency Response Measures for Catastrophic AI Risk

James Zhang, Miles Kodama, Zongze Wu, Michael Chen, Yue Zhu, Geng Hong

Comments Accepted to the Workshop on Regulatable ML at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment

Abhiram Kusumba, Maitreya Patel, Kyle Min, Changhoon Kim, Chitta Baral, Yezhou Yang

机构 * Arizona State University（亚利桑那州立大学） ； Capital One（Capital One公司） ； Oracle（Oracle公司） ； Soongsil University（顺天大学） 纠错

Comments NeurIPS'25 Spotlight | Project page: https://eraseflow.github.io/

GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining

Chunyu Wei, Wenji Hu, Xingjia Hao, Xin Wang, Yifan Yang, Yueguo Chen, Yang Tian, Yunhai Wang

机构 * Renmin University of China（中国人民大学） ； Guangxi University（广西大学） ； Beijing Jiaotong University（北京交通大学） 纠错

Comments Accepted by NeurIPS 2025

From Generation to Attribution: Music AI Agent Architectures for the Post-Streaming Era

Wonil Kim, Hyeongseok Wi, Seungsoon Park, Taejun Kim, Sangeun Keum, Keunhyoung Kim, Taewan Kim, Jongmin Jung, Taehyoung Kim, Gaetan Guerrero, Mael Le Goff, Julie Po, Dongjoo Moon, Juhan Nam, Jongpil Lee

Comments Accepted to the NeurIPS 2025 AI4Music Workshop

Hallucination as an Upper Bound: A New Perspective on Text-to-Image Evaluation

Seyed Amir Kasaei, Mohammad Hossein Rohban

机构 * Department of Computer Engineering, Sharif University of Technology（谢里夫理工大学计算机工程系） 纠错

Comments Accepted at GenProCC NeurIPS 2025 Workshop

Evaluating the Evaluators: Metrics for Compositional Text-to-Image Generation

Seyed Amir Kasaei, Ali Aghayari, Arash Marioriyad, Niki Sepasian, MohammadAmin Fazli, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban

机构 * Department of Computer Engineering, Sharif University of Technology（谢里夫理工大学计算机工程系） 纠错

Comments Accepted at GenProCC NeurIPS 2025 Workshop

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation

Chen Wang, Chuhao Chen, Yiming Huang, Zhiyang Dou, Yuan Liu, Jiatao Gu, Lingjie Liu

机构 * University of Pennsylvania（宾夕法尼亚大学） ； HKU（香港大学） ； HKUST（香港科技大学） 纠错

Comments NeurIPS 2025 Camera Ready Version

DevFD: Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces

Tianshuo Zhang, Li Gao, Siran Peng, Xiangyu Zhu, Zhen Lei

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所MAIS部门） ； China Mobile Financial Technology Co., Ltd.（中国移动金融科技有限公司） ； CAIR, HKSIS, Chinese Academy of Sciences（中国科学院CAIR部门，香港创新技术研究所） ； School of Computer Science and Engineering, the Faculty of Innovation Engineering, M.U.S.T（澳门科技大学计算机科学与工程学院，创新工程学院） 纠错

Comments Accepted by NeurIPS 2025

Tree-Guided Diffusion Planner

Hyeonseong Jeon, Cheolhong Min, Jaesik Park

机构 * Department of Computer Science & Engineering（计算机科学与工程系） ； Interdisciplinary Program of AI（人工智能跨学科项目） 纠错

Comments NeurIPS 2025

MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control

Yuchen Zhu, Wei Guo, Jaemoo Choi, Guan-Horng Liu, Yongxin Chen, Molei Tao

机构 * Georgia Institute of Technology（佐治亚理工学院） ； FAIR at Meta（Meta的FAIR） 纠错

Comments NeurIPS 2025

Beyond Parallelism: Synergistic Computational Graph Effects in Multi-Head Attention

Haitz Sáez de Ocáriz Borde

机构 * Supermodel 纠错

Comments 16 pages, 4 figures, 6 tables. Accepted at NeurIPS 2025 Workshop on Symmetry and Geometry in Neural Representations

DynaGuide: Steering Diffusion Polices with Active Dynamic Guidance

Maximilian Du, Shuran Song

机构 * Stanford University（斯坦福大学） 纠错

Comments 9 pages main, 21 pages with appendix and citations. 9 figures. Presented at Neurips 2025

FlashMoE: Fast Distributed MoE in a Single Kernel

Osayamen Jonathan Aimuyo, Byungsoo Oh, Rachee Singh

机构 * Cornell University（康奈尔大学） 纠错

Comments To appear at NeurIPS '25

From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications

Yang Cai, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng

机构 * Yale University（耶鲁大学） ； University of Southern California（南加州大学） ； University of Virginia（弗吉尼亚大学） 纠错

Comments NeurIPS 2025. 24 pages. Updated version with more discussions and robustness in the bandit feedback setting

Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations

Chaofan Gan, Yuanpeng Tu, Xi Chen, Tieyuan Chen, Yuxi Li, Mehrtash Harandi, Weiyao Lin

机构 * Shanghai Jiao Tong University（上海交通大学） ； Monash University（墨尔本大学） ； The University of Hong Kong（香港大学） 纠错

Comments NeurIPS 2025, code: https://github.com/ganchaofan0000/DiTF