NeurIPS

Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular Objectives

Qixin Zhang, Yan Sun, Can Jin, Xikun Zhang, Yao Shu, Puning Zhao, Li Shen, Dacheng Tao

机构 * College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算机与数据科学学院） ； The University of Sydney（悉尼大学） ； Hong Kong University of Science and Technology(Guangzhou)（香港科技大学（广州）） ； Rutgers University（罗格斯大学） ； Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区） 纠错

Comments Accepted to NeurIPS 2025

Orochi: Versatile Biomedical Image Processor

Gaole Dai, Chenghao Zhou, Yu Zhou, Rongyu Zhang, Yuan Zhang, Chengkai Hou, Tiejun Huang, Jianxu Chen, Shanghang Zhang

Comments accepted by 39th Conference on Neural Information Processing Systems (NeurIPS 2025) as spotlight paper

SoDaDE: Solvent Data-Driven Embeddings with Small Transformer Models

Gabriel Kitso Gibberd, Jose Pablo Folch, Antonio Del Rio Chanona

机构 * Imperial College London（帝国理工学院伦敦分校） ； SOLVE Chemistry（SOLVE化学） 纠错

Comments 7 pages, 2 figures, 3 tables, to be presented as a poster at the NeurIPS 2025 Workshop on Machine Learning and the Physical Sciences

MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning

Jinkun Hao, Naifu Liang, Zhen Luo, Xudong Xu, Weipeng Zhong, Ran Yi, Yichen Jin, Zhaoyang Lyu, Feng Zheng, Lizhuang Ma, Jiangmiao Pang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； SII Southern University of Science and Technology（南方科技大学） ； Peking University（北京大学） 纠错

Comments Accepted by NeurIPS 2025; Project page: https://mesatask.github.io/

DualFocus: Depth from Focus with Spatio-Focal Dual Variational Constraints

Sungmin Woo, Sangyoun Lee

机构 * Yonsei University（延世大学） 纠错

Comments Accepted by NeurIPS 2025

Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation

Abdelrahman Eldesokey, Aleksandar Cvejic, Bernard Ghanem, Peter Wonka

机构 * KAUST, Saudi Arabia（卡士大学） 纠错

Comments NeurIPS 2025 (Spotlight). Project Page: https://abdo-eldesokey.github.io/mind-the-glitch/

Structural Information-based Hierarchical Diffusion for Offline Reinforcement Learning

Xianghua Zeng, Hao Peng, Angsheng Li, Yicheng Pan

机构 * State Key Laboratory of Software Development Environment（软件开发环境国家重点实验室） ； Beihang University（北京航空航天大学） ； Zhongguancun Laboratory（中关村实验室） 纠错

Comments Accepted by NeurIPS 2025

DynaNav: Dynamic Feature and Layer Selection for Efficient Visual Navigation

Jiahui Wang, Changhao Chen

机构 * College of Design and Engineering, National University of Singapore（设计与工程学院，新加坡国立大学） ； PEAK-Lab, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）PEAK实验室） 纠错

Comments Accepted as a poster in NeurIPS 2025

SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference

Jiahui Wang, Haiyue Zhu, Haoren Guo, Abdullah Al Mamun, Cheng Xiang, Tong Heng Lee

机构 * College of Design and Engineering, National University of Singapore（新加坡国立大学设计与工程学院） ； SIMTech, Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局SIMTech） 纠错

Comments Accepted as a poster in NeurIPS 2025

Spatial Reasoning in Foundation Models: Benchmarking Object-Centric Spatial Understanding

Vahid Mirjalili, Ramin Giahi, Sriram Kollipara, Akshay Kekuda, Kehui Yao, Kai Zhao, Jianpeng Xu, Kaushiki Nag, Sinduja Subramaniam, Topojoy Biswas, Evren Korpeoglu, Kannan Achan

机构 * Walmart Global Tech（沃尔玛全球科技） 纠错

Comments 4 pages, NeurIPS Workshop SpaVLE

SpecMER: Fast Protein Generation with K-mer Guided Speculative Decoding

Thomas Walton, Darin Tsui, Aryan Musharaf, Amirali Aghazadeh

机构 * Georgia Institute of Technology（佐治亚理工学院） 纠错

Comments Accepted as spotlight at NeurIPS 2025

Understanding and Enhancing Mask-Based Pretraining towards Universal Representations

Mingze Dong, Leda Wang, Yuval Kluger

机构 * Yale University（耶鲁大学） 纠错

Comments NeurIPS 2025

Accelerate Creation of Product Claims Using Generative AI

Po-Yu Liang, Yong Zhang, Tatiana Hwa, Aaron Byers

机构 * Department of Computer Science University of Cincinnati（计算机科学系 奥克兰大学） ； Corporate Functions R&D, Discovery& Innovation Platforms, P&G（企业职能研发、发现与创新平台，宝洁公司） ； Beauty Care IT, P&G（美容护理IT，宝洁公司） ； Beauty Care R&D, P&G（美容护理研发，宝洁公司） 纠错

Comments This paper has been accepted at the GenProCC workshop (NeurIPS 2025)

4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming

Zihan Zheng, Zhenlong Wu, Houqiang Zhong, Yuan Tian, Ning Cao, Lan Xu, Jiangchao Yao, Xiaoyun Zhang, Qiang Hu, Wenjun Zhang

机构 * Cooperative Medianet Innovation Center, Shanghai Jiaotong University（合作中位网创新中心，上海交通大学） ； Department of Electronics, Shanghai Jiaotong University（电子工程系，上海交通大学） ； Shanghai AI Lab（上海人工智能实验室） ； Cloud platform department, E-surfing Vision Technology Co., Ltd.（云平台部门，E-surfing Vision Technology有限公司） ； School of Information Science and Technology, ShanghaiTech University（信息科学与技术学院，上海科技大学） 纠错

Comments NeurIPS 2025

SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment

Qi Xu, Dongxu Wei, Lingzhe Zhao, Wenpu Li, Zhangchi Huang, Shunping Ji, Peidong Liu

机构 * Wuhan University（武汉大学） ； Westlake University（西湖大学） ； Westlake Institute for Advanced Study（西湖研究所以及先进科学研究所） ； Zhejiang University（浙江大学） 纠错

Comments Accepted to NeurIPS'25 (Spotlight). Project page: https://insomniaaac.github.io/siu3r/

OrthoGrad Improves Neural Calibration

C. Evans Hedges

机构 * University of Denver（丹佛大学） 纠错

Comments Accepted at Opt2025 at NeurIPS 2025

Geometry aware inference of steady state PDEs using Equivariant Neural Fields representations

Giovanni Catalani, Michael Bauerheim, Frédéric Tost, Xavier Bertrand, Joseph Morlier

机构 * Airbus（空客） ； ISAE-Supaero（ISAE-苏普尔摩） ； Université de Toulouse（图卢兹大学） 纠错

Comments NeurIPS 2025 AI for Science workshop

On the Value of Cross-Modal Misalignment in Multimodal Representation Learning

Yichao Cai, Yuhang Liu, Erdun Gao, Tianjiao Jiang, Zhen Zhang, Anton van den Hengel, Javen Qinfeng Shi

机构 * Australian Institute for Machine Learning（澳大利亚机器学习研究所） ； The University of Adelaide（阿德莱德大学） 纠错

Comments NeurIPS 2025 camera-ready version (with checklist removed for presentation clarity)

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models

Haizhou Shi, Yibin Wang, Ligong Han, Huan Zhang, Hao Wang

机构 * Rutgers University（新泽西罗格斯大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Red Hat AI Innovation（红帽AI创新） 纠错

Comments Accepted at NeurIPS 2025

DOTA: Distributional Test-Time Adaptation of Vision-Language Models

Zongbo Han, Jialong Yang, Guangyu Wang, Junfan Li, Qianli Xu, Mike Zheng Shou, Changqing Zhang

机构 * State Key Laboratory of Networking and Switching Technology（网络与交换技术国家重点实验室） ； Beijing University of Posts and Telecommunications（北京邮电大学） ； College of Intelligence and Computing（智能与计算学院） ； Tianjin University（天津大学） ； School of Computer Science and Technology（计算机科学与技术学院） ； Harbin Institute of Technology Shenzhen（哈尔滨工业大学深圳学院） ； Institute for Infocomm Research, A*STAR（信息通信研究机构，A*STAR） ； Show Lab, National University of Singapore（新加坡国立大学Show实验室） ； National University of Singapore（新加坡国立大学） 纠错

Comments Accepted by NeurIPS 2025

The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization

Constantinos Daskalakis, Ioannis Panageas

机构 * MIT（麻省理工学院） 纠错

Comments Appeared in NeurIPS 2018. The new version fixes typos

SAGE: A Realistic Benchmark for Semantic Understanding

Samarth Goel, Reagan J. Lee, Kannan Ramchandran

机构 * University of California, Berkeley（加州大学伯克利分校） 纠错

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Evaluating the Evolving LLM Lifecycle: Benchmarks, Emergent Abilities, and Scaling

humancompatible.train: Implementing Optimization Algorithms for Stochastically-Constrained Stochastic Optimization Problems

Andrii Kliachkin, Jana Lepšová, Gilles Bareilles, Jakub Mareček

机构 * Artificial Intelligence Center, Czech Technical University in Prague（捷克技术大学布拉格分校人工智能中心） 纠错

Comments Accepted at NeurIPS workshop COML 2025

Learning to Look: Cognitive Attention Alignment with Vision-Language Models

Ryan L. Yang, Dipkamal Bhusal, Nidhi Rastogi

机构 * Brown University（布朗大学） ； Rochester Institute of Technology（罗切斯特理工大学） 纠错

Comments 7 pages, neurips workshop

CORE: Full-Path Evaluation of LLM Agents Beyond Final State

Panagiotis Michelakis, Yiannis Hadjiyiannis, Dimitrios Stamoulis

机构 * Synkrasis Labs（Synkrasis实验室） ； Harbin Institute of Technology（哈尔滨工业大学） 纠错

Comments Accepted: LAW 2025 Workshop NeurIPS 2025

AIBA: Attention-based Instrument Band Alignment for Text-to-Audio Diffusion

Junyoung Koh, Soo Yong Kim, Gyu Hyeong Choi, Yongwon Choi

机构 * Department of Artificial Intelligence, Yonsei University（人工智能系，延世大学） ； MAAP LAB, MODULABS（MODULABS 音频实验室） ； KRAFTON ； AI Matics ； Department of Media Software, Sungkyul University（媒体软件系，松谷大学） 纠错

Comments NeurIPS 2025 AI for Music Workshop

ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction

Jiabao Lei, Kewei Shi, Zhihao Liang, Kui Jia

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； The University of Hong Kong（香港大学） ； Tencent Hunyuan（腾讯文心） 纠错

Comments NeurIPS 2025, Project Page: https://jblei.site/proj/armesh

Implicit Augmentation from Distributional Symmetry in Turbulence Super-Resolution

Julia Balla, Jeremiah Bailey, Ali Backour, Elyssa Hofgard, Tommi Jaakkola, Tess Smidt, Ryley McConkey

机构 * Massachusetts Institute of Technology（麻省理工学院） 纠错

Comments Accepted to Machine Learning and the Physical Sciences Workshop at NeurIPS 2025

Bispectral OT: Dataset Comparison using Symmetry-Aware Optimal Transport

Annabel Ma, Kaiying Hou, David Alvarez-Melis, Melanie Weber

机构 * Harvard University（哈佛大学） 纠错

Comments Accepted to NeurIPS 2025 Workshop on Symmetry and Geometry in Neural Representations (NeurReps)

PIRF: Physics-Informed Reward Fine-Tuning for Diffusion Models

Mingze Yuan, Pengfei Jin, Na Li, Quanzheng Li

机构 * Harvard University（哈佛大学） ； Massachusetts General Hospital（麻省总医院） 纠错

Comments 18 pages, 6 figures; NeurIPS 2025 AI for science workshop