NeurIPS

ORPO-Distill: Mixed-Policy Preference Optimization for Cross-Architecture LLM Distillation

Aasheesh Singh, Vishal Vaddina, Dagnachew Birru

机构 * Phi Labs, Quantiphi（Phi Labs，Quantiphi） 纠错

Comments Accepted at NeurIPS 2025, Efficient Reasoning Workshop

Is Sequence Information All You Need for Bayesian Optimization of Antibodies?

Sebastian W. Ober, Calvin McCarter, Aniruddh Raghu, Yucen Lily Li, Alan N. Amin, Andrew Gordon Wilson, Hunter Elliott

机构 * BigHat Biosciences（BigHat生物技术公司） ； NYU（纽约大学） 纠错

Comments Accepted into the AI for Science Workshop, NeurIPS 2025

ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation

Jiuhong Xiao, Roshan Nayak, Ning Zhang, Daniel Tortei, Giuseppe Loianno

机构 * New York University（纽约大学） ； Technology Innovation Institute（技术创新研究所） ； University of California, Berkeley（加州大学伯克利分校） 纠错

Comments 23 pages including the checklist and appendix. Accepted at NeurIPS 2025

StreamForest: Efficient Online Video Understanding with Persistent Event Memory

Xiangyu Zeng, Kefan Qiu, Qingyu Zhang, Xinhao Li, Jing Wang, Jiaxin Li, Ziang Yan, Kun Tian, Meng Tian, Xinhai Zhao, Yi Wang, Limin Wang

机构 * Nanjing University（南京大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； Zhejiang University（浙江大学） ； Noah’s Ark Lab, Huawei（华为诺亚实验室） ； Yinwang Intelligent Tech.（云网智能科技） 纠错

Comments Accepted as a Spotlight at NeurIPS 2025

Vision Function Layer in Multimodal LLMs

Cheng Shi, Yizhou Yu, Sibei Yang

机构 * Sun Yat-sen University（中山大学） ； School of Computing and Data Science（计算与数据科学学院） ； The University of Hong Kong（香港大学） 纠错

Comments Accepted at NeurIPS 2025 (preview; camera-ready in preparation)

Quantifying Generalisation in Imitation Learning

Nathan Gavenski, Odinaldo Rodrigues

Comments NeurIPS 2025 Datasets and Benchmarks Track poster

A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity

Giordano Cicchetti, Eleonora Grassucci, Danilo Comminiello

机构 * Department of Information Engineering, Electronics, and Telecommunications（信息工程、电子与电信系） 纠错

Comments NeurIPS 2025

Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens

Zijian Dong, Ruilin Li, Joanna Su Xian Chong, Niousha Dehestani, Yinghui Teng, Yi Lin, Zhizhou Li, Yichi Zhang, Yapei Xie, Leon Qi Rong Ooi, B. T. Thomas Yeo, Juan Helen Zhou

Comments NeurIPS 2025. The first two authors contributed equally

ScatterAD: Temporal-Topological Scattering Mechanism for Time Series Anomaly Detection

Tao Yin, Xiaohong Zhang, Shaochen Fu, Zhibin Zhang, Li Huang, Yiyuan Yang, Kaixiang Yang, Meng Yan

机构 * Chongqing University（重庆大学） ； South China University of Technology（华南理工大学） 纠错

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

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

Ran Xu, Yuchen Zhuang, Zihan Dong, Jonathan Wang, Yue Yu, Joyce C. Ho, Linjun Zhang, Haoyu Wang, Wenqi Shi, Carl Yang

机构 * Emory University（埃默里大学） ； Georgia Institute of Technology（佐治亚理工学院） ； Rutgers University（罗格斯大学） ； SUNY Albany（纽约州立大学阿尔巴尼分校） ； UT Southwestern Medical Center（德克萨斯西南医学中心） 纠错

Comments Accepted to NeurIPS 2025 (Spotlight)

ASTROCO: Self-Supervised Conformer-Style Transformers for Light-Curve Embeddings

Antony Tan, Pavlos Protopapas, Martina Cádiz-Leyton, Guillermo Cabrera-Vives, Cristobal Donoso-Oliva, Ignacio Becker

机构 * John A. Paulson School of Engineering and Applied Sciences, Harvard University, USA（哈佛大学约翰·A·保罗森工程与应用科学学校） ； Department of Biostatistics, Harvard T.H. Chan School of Public Health, USA（哈佛T.H. Chan公共卫生学院生物统计学系） ； Department of Computer Science, Universidad de Concepción, Chile（智利康塞普西翁大学计算机科学系） ； Center for Data and Artificial Intelligence, Universidad de Concepción, Chile（智利康塞普西翁大学数据与人工智能中心） ； Millennium Institute of Astrophysics (MAS), Santiago, Chile（智利Millennium天体物理研究所） ； Millennium Nucleus on Young Exoplanets and their Moons (YEMS), Chile（智利Millennium年轻系外行星及其卫星核） ； Department of Computer Science, Pontificia Universidad Católica de Chile, Santiago, Chile（智利天主教大学计算机科学系） 纠错

Comments Accepted at the NeurIPS 2025 Workshop on Machine Learning and the Physical Sciences (ML4PS), camera-ready version in progress

Dual-Head Reasoning Distillation: Improving Classifier Accuracy with Train-Time-Only Reasoning

Jillian Xu, Dylan Zhou, Vinay Shukla, Yang Yang, Junrui Ruan, Shuhuai Lin, Wenfei Zou, Yinxiao Liu, Karthik Lakshmanan

机构 * University of Waterloo（滑铁卢大学） ； Google（谷歌） ； DeepMind（深Mind） 纠错

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

Position: Thematic Analysis of Unstructured Clinical Transcripts with Large Language Models

Seungjun Yi, Joakim Nguyen, Terence Lim, Andrew Well, Joseph Skrovan, Mehak Beri, YongGeon Lee, Kavita Radhakrishnan, Liu Leqi, Mia Markey, Ying Ding

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Vanderbilt University School of Medicine（范德比大学医学院） 纠错

Comments Presented at GenAI4Health @ NeurIPS 2025

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search

Yuxian Gu, Qinghao Hu, Shang Yang, Haocheng Xi, Junyu Chen, Song Han, Han Cai

机构 * NVIDIA 纠错

Comments NeurIPS 2025

Contrastive Representations for Temporal Reasoning

Alicja Ziarko, Michal Bortkiewicz, Michal Zawalski, Benjamin Eysenbach, Piotr Milos

机构 * University of Warsaw（华沙大学） ； IDEAS NCBR ； IMPAN（波兰数学与计算机科学研究院） ； Warsaw University of Technology（华沙技术大学） ； Princeton University（普林斯顿大学） ； NVIDIA（英伟达公司） 纠错

Comments NeurIPS 2025, Project website: https://princeton-rl.github.io/CRTR/

DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion

Jin Li, Zezhong Ding, Xike Xie

机构 * School of Biomedical Engineering, University of Science and Technology of China（生物医学工程学院，中国科学技术大学） ； School of Artificial Intelligence and Data Science, USTC（人工智能与数据科学学院，中国科学技术大学） ； Data Darkness Lab, Suzhou Institute for Advanced Research, USTC（数据黑暗实验室，苏州先进研究院） 纠错

Comments Accepted by NeurIPS 2025

Hamiltonian Neural PDE Solvers through Functional Approximation

Anthony Zhou, Amir Barati Farimani

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments Published at NeurIPS 2025. Code and datasets are at http://github.com/anthonyzhou-1/hamiltonian_pdes/tree/main

MaintainCoder: Maintainable Code Generation Under Dynamic Requirements

Zhengren Wang, Rui Ling, Chufan Wang, Yongan Yu, Sizhe Wang, Zhiyu Li, Feiyu Xiong, Wentao Zhang

机构 * Center for Data Science（数据科学中心） ； McGill University（麦吉尔大学） ； Center for LLM, Institute for Advanced Algorithms Research（大语言模型中心，先进算法研究所） 纠错

Comments NeurIPS 2025

VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models

Haichao Zhang, Yun Fu

机构 * Northeastern University（东北大学） 纠错

Comments Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2025)

Recurrent Memory for Online Interdomain Gaussian Processes

Wenlong Chen, Naoki Kiyohara, Harrison Bo Hua Zhu, Jacob Curran-Sebastian, Samir Bhatt, Yingzhen Li

机构 * Imperial College London（伦敦帝国学院） ； Canon Inc.（佳能公司） ； University of Copenhagen（哥本哈根大学） 纠错

Comments Published at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces

Yuanshao Zhu, James Jianqiao Yu, Xiangyu Zhao, Xun Zhou, Liang Han, Xuetao Wei, Yuxuan Liang

机构 * Southern University of Science and Technology（南方科技大学） ； City University of Hong Kong（香港城市大学） ； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）） 纠错

Comments Accepted as a research paper by NeurIPS'25

Neuro-Symbolic Entity Alignment via Variational Inference

Shengyuan Chen, Zheng Yuan, Qinggang Zhang, Wen Hua, Jiannong Cao, Xiao Huang

机构 * Department of Computing（计算系） ； The Hong Kong Polytechnic University（香港理工大学） 纠错

Comments This paper has been accepted by NeurIPS 2025

The Prevalence of Neural Collapse in Neural Multivariate Regression

George Andriopoulos, Zixuan Dong, Li Guo, Zifan Zhao, Keith Ross

机构 * New York University Abu Dhabi（纽约大学阿布扎克分校） ； SFSC of AI and DL, NYU Shanghai（人工智能与深度学习学院（SFSC），纽约大学上海） ； New York University Shanghai（纽约大学上海） ； New York University（纽约大学） 纠错

Comments Published at NeurIPS 2024

Journal ref Published in 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

Position: Towards Bidirectional Human-AI Alignment

Hua Shen, Tiffany Knearem, Reshmi Ghosh, Kenan Alkiek, Kundan Krishna, Yachuan Liu, Ziqiao Ma, Savvas Petridis, Yi-Hao Peng, Li Qiwei, Sushrita Rakshit, Chenglei Si, Yutong Xie, Jeffrey P. Bigham, Frank Bentley, Joyce Chai, Zachary Lipton, Qiaozhu Mei, Rada Mihalcea, Michael Terry, Diyi Yang, Meredith Ringel Morris, Paul Resnick, David Jurgens

机构 * NYU Shanghai, New York University（纽约大学上海研究院，纽约大学） ； MBZUAI（穆桑大学人工智能研究所） ； Microsoft（微软公司） ； University of Michigan（密歇根大学） ； Apple（苹果公司） ； Google（谷歌公司） ； Carnegie Mellon University（卡内基梅隆大学） ； Stanford University（斯坦福大学） ； Google DeepMind（谷歌DeepMind） 纠错

Comments NeurIPS 2025 Position Paper

EWC-Guided Diffusion Replay for Exemplar-Free Continual Learning in Medical Imaging

Anoushka Harit, William Prew, Zhongtian Sun, Florian Markowetz

机构 * University of Cambridge（剑桥大学） ； University of Kent（肯特大学） 纠错

Comments Accepted at AI That Keeps Up: NeurIPS 2025 Workshop on Continual and Compatible Foundation Model Updates

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack

Yukun Chen, Boheng Li, Yu Yuan, Leyi Qi, Yiming Li, Tianwei Zhang, Zhan Qin, Kui Ren

机构 * State Key Laboratory of Blockchain and Data Security（区块链与数据安全国家重点实验室） ； Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院） ； Nanyang Technological University（南洋理工大学） 纠错

Comments The first three authors contributed equally to this work. To appear in NeurIPS 2025. 35 pages

DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation

Kefei Zhu, Fengshuo Bai, YuanHao Xiang, Yishuai Cai, Xinglin Chen, Ruochong Li, Xingtao Wang, Hao Dong, Yaodong Yang, Xiaopeng Fan, Yuanpei Chen

机构 * Harbin Institute of Technology（哈尔滨工业大学） ； PsiBot ； Peking University（北京大学） ； PKU-Psibot Lab（北京大学-PsiBot实验室） ； Harbin Institute of Technology Suzhou Research Institute（哈尔滨工业大学苏州研究所） 纠错

Comments NeurIPS 2025, Spotlight

STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning

Yao Luan, Ni Mu, Yiqin Yang, Bo Xu, Qing-Shan Jia

机构 * Beijing Key Laboratory of Embodied Intelligence Systems, Department of Automation, Tsinghua University, Beijing, China（北京智能体智能系统重点实验室，自动化系，清华大学，北京，中国） ； The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China（复杂系统认知与决策智能重点实验室，自动化研究所，中国科学院，北京，中国） 纠错

Comments NeurIPS 2025

GroupCoOp: Group-robust Fine-tuning via Group Prompt Learning

Nayeong Kim, Seong Joon Oh, Suha Kwak

机构 * Pohang University of Science and Technology (POSTECH)（釜山科学技术大学） ； Tübingen AI Center（图宾根人工智能中心） ； Universität Tübingen（图宾根大学） 纠错

Comments This paper was first submitted to NeurIPS 2024 in May 2024

ResAD++: Towards Class Agnostic Anomaly Detection via Residual Feature Learning

Xincheng Yao, Chao Shi, Muming Zhao, Guangtao Zhai, Chongyang Zhang

机构 * School of Information Science and Electronic Engineering, Shanghai Jiao Tong University（上海交通大学信息科学与电子工程学院） ； School of Information Science and Technology, Beijing Forestry University（北京林业大学信息科学与技术学院） 纠错

Comments This paper is an extended version of our NeurIPS 2024 paper, ResAD. arXiv admin note: substantial text overlap with arXiv:2410.20047