NeurIPS

GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies

Ziye Wang, Li Kang, Yiran Qin, Jiahua Ma, Zhanglin Peng, Lei Bai, Ruimao Zhang

机构 * Sun Yat-sen University（中山大学） ； The University of Hong Kong（香港大学） ； Shanghai Jiao Tong University（上海交通大学） ； The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； Shanghai AI Laboratory（上海人工智能实验室） 纠错

Comments Accepted by NeurIPS 2025. Project page: https://ziyeeee.github.io/gaudp.io/

A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis

Dongheng Lin, Mengxue Qu, Kunyang Han, Jianbo Jiao, Xiaojie Jin, Yunchao Wei

机构 * Institute of Information Science, Beijing Jiaotong University（信息科学学院，北京交通大学） ； The MIx Group, University of Birmingham（Birmingham大学的MIx组） 纠错

Comments NeurIPS 2025 poster

URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model

Zhe Li, Xiang Bai, Jieyu Zhang, Zhuangzhe Wu, Che Xu, Ying Li, Chengkai Hou, Shanghang Zhang

机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学） ； University of Washington（华盛顿大学） 纠错

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

The Biased Oracle: Assessing LLMs' Understandability and Empathy in Medical Diagnoses

Jianzhou Yao, Shunchang Liu, Guillaume Drui, Rikard Pettersson, Alessandro Blasimme, Sara Kijewski

机构 * Department of Chemistry and Applied Biosciences, ETH Zurich（应用生物科学系，苏黎世联邦理工学院） ； Department of Computer Science, ETH Zurich（计算机科学系，苏黎世联邦理工学院） ； Department of Health Sciences and Technology, ETH Zurich（健康科学与技术系，苏黎世联邦理工学院） 纠错

Comments Accepted by NeurIPS 2025 GenAI4Health Workshop

SpEx: A Spectral Approach to Explainable Clustering

Tal Argov, Tal Wagner

机构 * Tel Aviv University（特拉维夫大学） 纠错

Comments NeurIPS 2025

Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion

Jaehyun Park, Konyul Park, Daehun Kim, Junseo Park, Jun Won Choi

机构 * Seoul National University（首尔国立大学） 纠错

Comments Accepted to NeurIPS 2025

Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials

Yifan Pu, Jixuan Ying, Qixiu Li, Tianzhu Ye, Dongchen Han, Xiaochen Wang, Ziyi Wang, Xinyu Shao, Gao Huang, Xiu Li

机构 * Tsinghua University（清华大学） ； Peking University（北京大学） 纠错

Comments NeurIPS 2025

Fast PINN Eigensolvers via Biconvex Reformulation

Akshay Sai Banderwaar, Abhishek Gupta

机构 * School of Mechanical Sciences（机械科学学院） ； Indian Institute of Technology, Goa（印度理工学院，果阿） 纠错

Comments 7 pages, 3 figures, Machine Learning and the Physical Sciences Workshop NeurIPS 2025

Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective

Wei Feng, Zongyuan Ge

机构 * Monash University（墨尔本大学） ； Airdoc–Monash Research（Airdoc–Monash研究） 纠错

Comments 29 pages, 5 figures

Journal ref NeurIPS 2025

HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation

Panwang Pan, Tingting Shen, Chenxin Li, Yunlong Lin, Kairun Wen, Jingjing Zhao, Yixuan Yuan

机构 * Xiamen University（厦门大学） ； The Chinese University of Hong Kong（香港中文大学） 纠错

Comments Accepted to NeurIPS 2025; Project page: [this URL](https://paulpanwang.github.io/HumanCrafter)

ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training

Xin Yao, Haiyang Zhao, Yimin Chen, Jiawei Guo, Kecheng Huang, Ming Zhao

机构 * School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院） ； Miner School of Computer & Information Sciences, University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校Miner计算机与信息科学学院） 纠错

Comments Accepted by NeurIPS 2025

Reject Only Critical Tokens: Pivot-Aware Speculative Decoding

Amir Ziashahabi, Yavuz Faruk Bakman, Duygu Nur Yaldiz, Mostafa El-Khamy, Sai Praneeth Karimireddy, Salman Avestimehr

机构 * University of Southern California（南加州大学） ； Device Solutions Research America, Samsung Semiconductor, Inc.（三星半导体公司） 纠错

Comments Accepted at NeurIPS 2025 Efficient Reasoning Workshop

OSMGen: Highly Controllable Satellite Image Synthesis using OpenStreetMap Data

Amir Ziashahabi, Narges Ghasemi, Sajjad Shahabi, John Krumm, Salman Avestimehr, Cyrus Shahabi

机构 * University of Southern California（南加州大学） 纠错

Comments Accepted at NeurIPS 2025 UrbanAI Workshop

Merlin L48 Spectrogram Dataset

Aaron Sun, Subhransu Maji, Grant Van Horn

机构 * Manning College of Information and Computer Sciences（信息与计算机科学学院） 纠错

Comments Accepted to 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Track on Datasets and Benchmarks

Iterative Foundation Model Fine-Tuning on Multiple Rewards

Pouya M. Ghari, Simone Sciabola, Ye Wang

机构 * Biogen（百健） 纠错

Comments Accepted to NeurIPS 2025

BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing

Jinsu Kim, Yunhun Nam, Minseon Kim, Sangpil Kim, Jongheon Jeong

机构 * Korea University（韩国大学） ； Microsoft Research Montréal（微软蒙特利尔研究院） 纠错

Comments 36 pages; NeurIPS 2025; Code is available at https://github.com/jsu-kim/BlurGuard

DCcluster-Opt: Benchmarking Dynamic Multi-Objective Optimization for Geo-Distributed Data Center Workloads

Antonio Guillen-Perez, Avisek Naug, Vineet Gundecha, Sahand Ghorbanpour, Ricardo Luna Gutierrez, Ashwin Ramesh Babu, Munther Salim, Shubhanker Banerjee, Eoin H. Oude Essink, Damien Fay, Soumyendu Sarkar

Comments Submitted to the NeurIPS 2025 conference

LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers

Avisek Naug, Antonio Guillen, Vineet Kumar, Scott Greenwood, Wesley Brewer, Sahand Ghorbanpour, Ashwin Ramesh Babu, Vineet Gundecha, Ricardo Luna Gutierrez, Soumyendu Sarkar

Comments Submitted to the NeurIPS 2025 conference

Automated Discovery of Conservation Laws via Hybrid Neural ODE-Transformers

Vivan Doshi

机构 * Independent Researcher（独立研究者） 纠错

Comments 5th Math-AI Workshop - Neural Information Processing Systems (NeurIPS 2025)

Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving

Yuchen Zhang, Hanyue Du, Chun Cao, Jingwei Xu

Comments 26 pages including 10 pages of main text, 6 figures, 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

Automatically Finding Rule-Based Neurons in OthelloGPT

Aditya Singh, Zihang Wen, Srujananjali Medicherla, Adam Karvonen, Can Rager

机构 * University of Chicago（芝加哥大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

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

SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation

Gio Huh, Dhruv Sheth, Rayhan Zirvi, Frank Xiao

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

Pragmatic Heterogeneous Collaborative Perception via Generative Communication Mechanism

Junfei Zhou, Penglin Dai, Quanmin Wei, Bingyi Liu, Xiao Wu, Jianping Wang

机构 * Southwest Jiaotong University（西南交通大学） ； Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, China（可持续城市智能交通工程研究中心，教育部，中国） ； Wuhan University of Technology（武汉理工大学） ； City University of Hong Kong（香港城市大学） 纠错

Comments 26 pages, 10 figures, accepted to NeurIPS 2025

SpikeFit: Towards Optimal Deployment of Spiking Networks on Neuromorphic Hardware

Ivan Kartashov, Mariia Pushkareva, Iakov Karandashev

机构 * HSE University（俄罗斯高等经济大学） ； Center of Optical Neural Technologies（光学神经技术中心） 纠错

Comments Published at the European Conference on Neural Information Processing Systems (EurIPS 2025). 13 pages, 2 figures

A Generalized Bisimulation Metric of State Similarity between Markov Decision Processes: From Theoretical Propositions to Applications

Zhenyu Tao, Wei Xu, Xiaohu You

Comments This paper is accepted by the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

Lattice Boltzmann Model for Learning Real-World Pixel Dynamicity

Guangze Zheng, Shijie Lin, Haobo Zuo, Si Si, Ming-Shan Wang, Changhong Fu, Jia Pan

机构 * HKU（香港大学） ； Kunming Institute of Zoology, CAS（昆明动物研究所，中国科学院） ； Tongji University（同济大学） ； LimX Dynamics 纠错

Comments NeurIPS 2025. Project page: https://george-zhuang.github.io/lbm/

Learning to Steer: Input-dependent Steering for Multimodal LLMs

Jayneel Parekh, Pegah Khayatan, Mustafa Shukor, Arnaud Dapogny, Alasdair Newson, Matthieu Cord

机构 * ISIR, Sorbonne Université（ISIR，索邦大学） 纠错

Comments NeurIPS 2025

Keep It Real: Challenges in Attacking Compression-Based Adversarial Purification

Samuel Räber, Till Aczel, Andreas Plesner, Roger Wattenhofer

机构 * ETH Zürich（苏黎世联邦理工学院） 纠错

Comments Accepted to the Reliable ML from Unreliable Data workshop at NeurIPS 2025 (ReliableML@NeurIPS)

One Small Step with Fingerprints, One Giant Leap for De Novo Molecule Generation from Mass Spectra

Neng Kai Nigel Neo, Lim Jing, Ngoui Yong Zhau Preston, Koh Xue Ting Serene, Bingquan Shen

Comments Accepted at AI4Mat-NeurIPS-2025 Workshop

Music Arena: Live Evaluation for Text-to-Music

Yonghyun Kim, Wayne Chi, Anastasios N. Angelopoulos, Wei-Lin Chiang, Koichi Saito, Shinji Watanabe, Yuki Mitsufuji, Chris Donahue

机构 * Carnegie Mellon University（卡内基梅隆大学） ； LMArena ； Sony AI（索尼人工智能） ； Georgia Tech（佐治亚理工学院） 纠错

Comments NeurIPS 2025 Creative AI Track