NeurIPS

Discovering and Reasoning of Causality in the Hidden World with Large Language Models

Chenxi Liu, Yongqiang Chen, Tongliang Liu, Mingming Gong, James Cheng, Bo Han, Kun Zhang

机构 * TMLR Group, Hong Kong Baptist University（香港 Baptist 大学 TMLR 组） ； Mohamed bin Zayed University of Artificial Intelligence（Mohamed bin Zayed 人工智能大学） ； Department of Philosophy, Carnegie Mellon University（哲学系，卡内基梅隆大学） ； School of Computer Science, The University of Sydney（悉尼大学计算机科学学院） ； School of Mathematics and Statistics, The University of Melbourne（墨尔本大学数学与统计学学院） ； The Chinese University of Hong Kong（香港中文大学） 纠错

Comments Extended version of our previous NeurIPS'24 conference paper (arXiv:2402.03941(2)); Chenxi and Yongqiang contributed equally; 78 pages, 44 figures; Project page: https://causalcoat.github.io/discovering-and-reasoning

ChipGPT: How far are we from natural language hardware design

Kaiyan Chang, Ying Wang, Haimeng Ren, Mengdi Wang, Shengwen Liang, Yinhe Han, Huawei Li, Xiaowei Li

机构 * State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, China（处理器国家重点实验室，计算技术研究所，中国科学院，中国） ； University of Chinese Academy of Sciences（中国科学院大学） ； School of Information Science and Technology, ShanghaiTech University, China（信息科学与技术学院，上海科技大学，中国） 纠错

Comments Accepted by 2023 NeurIPS SysML Workshop, retitled to "Improving Large Language Model Hardware Generating Quality through Post-LLM Search"

PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion

Linlian Jiang, Rui Ma, Li Gu, Ziqiang Wang, Xinxin Zuo, Yang Wang

机构 * Concordia University（康科迪亚大学） ； Jilin University（吉林大学） ； Mila - Quebec AI Institute（魁北克人工智能研究所） ； Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China（知识驱动人机智能工程研究中心，教育部，中国） 纠错

Comments NeurIPS 2025

From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries

Joy Hsu, Emily Jin, Jiajun Wu, Niloy J. Mitra

机构 * Department of Computer Science Stanford University（计算机科学系 斯坦福大学） ； Department of Computer Science University College London（计算机科学系 伦敦大学学院） 纠错

Comments NeurIPS 2025

PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models

Lancheng Zou, Shuo Yin, Zehua Pei, Tsung-Yi Ho, Farzan Farnia, Bei Yu

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

Comments Accepted by NeurIPS 2025

BurstDeflicker: A Benchmark Dataset for Flicker Removal in Dynamic Scenes

Lishen Qu, Zhihao Liu, Shihao Zhou, Yaqi Luo, Jie Liang, Hui Zeng, Lei Zhang, Jufeng Yang

机构 * Nankai International Advanced Research Institute (SHENZHEN·FUTIAN)（南开国际先进研究院（深圳·福田）） ； Peng Cheng Laboratory（鹏城实验室） ； College of Computer Science, Nankai University（南开大学计算机学院） ； The Hong Kong Polytechnic University（香港理工大学） ； OPPO Research Institute（OPPO研究院） 纠错

Comments Accepted by NeurIPS 2025

Learning Joint Embeddings of Function and Process Call Graphs for Malware Detection

Kartikeya Aneja, Nagender Aneja, Murat Kantarcioglu

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； Virginia Tech（弗吉尼亚理工学院） 纠错

Journal ref 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: New Perspectives in Advancing Graph Machine Learning

Conformal Sparsification for Bandwidth-Efficient Edge-Cloud Speculative Decoding

Payel Bhattacharjee, Fengwei Tian, Meiyu Zhong, Guangyi Zhang, Osvaldo Simeone, Ravi Tandon

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系；亚利桑那大学；美国亚利桑那州图森） ； University of Arizona（信息科学与电子工程学院；浙江大学；中国杭州310027） ； Tucson, AZ, USA（工程系；伦敦国王学院；英国伦敦） ； College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China ； Department of Engineering ； King’s College London ； London, UK 纠错

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: AI and ML for Next-Generation Wireless Communications and Networking (AI4NextG)

Agentic Property-Based Testing: Finding Bugs Across the Python Ecosystem

Muhammad Maaz, Liam DeVoe, Zac Hatfield-Dodds, Nicholas Carlini

机构 * MATS, Anthropic（MATS，Anthropic） ； Northeastern University（东北大学） ； Anthropic 纠错

Comments 4 pages (main), NeurIPS 2025, The 4th Deep Learning for Code Workshop

Exploration of Incremental Synthetic Non-Morphed Images for Single Morphing Attack Detection

David Benavente-Rios, Juan Ruiz Rodriguez, Gustavo Gatica

机构 * Dept. Ing. Industrial Universidad de Santiago（工业工程系，圣地亚哥大学） ； LAETEC - UPLA Universidad de Playa Ancha Valparaíso, Chile（LAETEC - UPLA，瓦尔帕莱索大学） ； Facultad de Ingeniería Universidad Andres Bello（工程学院，安德烈斯·贝洛大学） 纠错

Comments Workshop paper accepted NeurIPS 2025

Principled Operator Learning in Ocean Dynamics: The Role of Temporal Structure

Vahidreza Jahanmard, Ali Ramezani-Kebrya, Robinson Hordoir

机构 * Tallinn University of Technology, Department of Civil Engineering and Architecture（塔林技术大学土木工程与建筑系） ； Integreat - Norwegian Centre for knowledge-driven machine learning（挪威知识驱动机器学习中心） ； University of Oslo（奥斯陆大学） ； Institute of Marine Research（海洋研究所） ； Bjerknes Centre for Climate Research（比约克内斯气候研究中心） 纠错

Comments Accepted at NeurIPS ML4PS 2025

Reliable Active Learning from Unreliable Labels via Neural Collapse Geometry

Atharv Goel, Sharat Agarwal, Saket Anand, Chetan Arora

机构 * IIIT Delhi（印度德里理工学院） ； IIT Delhi（印度德里理工学院） 纠错

Comments Accepted to NeurIPS 2025 Workshop on Reliable ML from Unreliable Data

Stop DDoS Attacking the Research Community with AI-Generated Survey Papers

Jianghao Lin, Rong Shan, Jiachen Zhu, Yunjia Xi, Yong Yu, Weinan Zhang

机构 * Antai College of Economics and Management, Shanghai Jiao Tong University, China（上海交通大学安泰经济管理学院） ； School of Computer Science, Shanghai Jiao Tong University, China（上海交通大学计算机科学学院） 纠错

Comments Accepted by NeurIPS 2025 (Position Track)

Spatial Uncertainty Quantification in Wildfire Forecasting for Climate-Resilient Emergency Planning

Aditya Chakravarty

Journal ref NeurIPS 2025: Tackling Climate Change with Machine Learning Tackling Climate Change with Machine Learning: workshop at NeurIPS 2025

Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference

Zichen Wang, Haoyang Hong, Chuanhao Li, Haoxuan Li, Zhiheng Zhang, Huazheng Wang

机构 * Department of ECE and CSL, UIUC（UIUC电子工程系和 CSL部门） ； School of EECS, Oregon State University（俄勒冈州立大学电子工程与计算机科学学院） ； Department of Industrial Engineering, Tsinghua University（清华大学工业工程系） ； Center for Data Science, Peking University（北京大学数据科学中心） ； School of Statistics and Data Science, Shanghai University of Finance and Economics, Shanghai 200433, P.R. China（上海财经大学统计与数据科学学院） 纠错

Journal ref Neurips 2025

Bridging Graph and State-Space Modeling for Intensive Care Unit Length of Stay Prediction

Shuqi Zi, Haitz Sáez de Ocáriz Borde, Emma Rocheteau, Pietro Lio'

机构 * University of Cambridge, UK（剑桥大学） ； University of Oxford, UK（牛津大学） 纠错

Comments Accepted at the GenAI for Health Workshop @ NeurIPS 2025. Code available at: https://github.com/ShuqiZi1/S2G-Net

MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis

Mengxi Xiao, Ben Liu, He Li, Jimin Huang, Qianqian Xie, Xiaofen Zong, Mang Ye, Min Peng

机构 * School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院） ； Center for Language and Information Research, Wuhan University（武汉大学语言与信息研究所） ； School of Computer Science, Wuhan University（武汉大学计算机学院） ； Department of Psychiatry, Renmin Hospital of Wuhan University（武汉大学人民医院精神科） ； The Fin AI（Fin AI） ； Taikang Center for Life and Medical Sciences, Wuhan University（武汉大学泰康生命与医学科学中心） 纠错

Comments 46 pages, 11 figures

Journal ref NeurIPS 2025

Does Machine Unlearning Truly Remove Knowledge?

Haokun Chen, Yueqi Zhang, Yuan Bi, Yao Zhang, Tong Liu, Jinhe Bi, Jian Lan, Jindong Gu, Claudia Grosser, Denis Krompass, Nassir Navab, Volker Tresp

机构 * LMU Munich（慕尼黑大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） ； Technical University of Munich（慕尼黑技术大学） ； Siemens AG（西门子股份公司） ； University of Oxford（牛津大学） 纠错

Comments NeurIPS 2025 (Lock-LLM Workshop)

STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization

Haoyu Zhang, Wentao Zhang, Hao Miao, Xinke Jiang, Yuchen Fang, Yifan Zhang

机构 * City University of Hong Kong（香港城市大学） ； City University of Hong Kong (Dongguan)（香港城市大学（东莞）） ； Northeastern University（东北大学） ； The Hong Kong Polytechnic University（香港理工大学） ； University of Electronic Science and Technology of China（电子科技大学） ； SLAI 纠错

Comments This paper is accepted by NeurIPS 2025

Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization

Jiaqi Wei, Hao Zhou, Xiang Zhang, Di Zhang, Zijie Qiu, Wei Wei, Jinzhe Li, Wanli Ouyang, Siqi Sun

机构 * Zhejiang University（浙江大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； South China University of Technology（华南理工大学） ； University of British Columbia（不列颠哥伦比亚大学） ； Fudan University（复旦大学） ； University of Hong Kong（香港大学） 纠错

Comments Accepted by NeurIPS 2025

CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning

Man Ho Lam, Chaozheng Wang, Jen-tse Huang, Michael R. Lyu

机构 * The Chinese University of Hong Kong（香港中文大学） ； Johns Hopkins University（约翰霍普金斯大学） 纠错

Comments NeurIPS 2025; 10 pages of main text; 25 pages of appendices. Website - https://cuhk-arise.github.io/CodeCrash/

Learning to Instruct for Visual Instruction Tuning

Zhihan Zhou, Feng Hong, Jiaan Luo, Jiangchao Yao, Dongsheng Li, Bo Han, Ya Zhang, Yanfeng Wang

机构 * Cooperative Medianet Innovation Center, Shanghai Jiao Tong University（上海交通大学合作中元创新中心） ； Microsoft Research Asia（微软亚洲研究院） ； Hong Kong Baptist University（香港 Baptist 大学） ； School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院） 纠错

Comments NeurIPS 2025

InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques

Rohan Gupta, Iván Arcuschin, Thomas Kwa, Adrià Garriga-Alonso

机构 * University of Buenos Aires（布宜诺斯艾利斯大学） 纠错

Comments Published at the 38th Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks

Locally Optimal Private Sampling: Beyond the Global Minimax

Hrad Ghoukasian, Bonwoo Lee, Shahab Asoodeh

机构 * Department of Computing and Software（计算与软件系） ； McMaster University（麦斯特大学） ； Department of Mathematical Sciences（数学科学系） ； Korea Advanced Institute of Science & Technology（韩国科学技术院） 纠错

Comments 44 pages, 11 figures. Accepted at NeurIPS 2025

BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception

Junyan Ye, Dongzhi Jiang, Jun He, Baichuan Zhou, Zilong Huang, Zhiyuan Yan, Hongsheng Li, Conghui He, Weijia Li

机构 * Sun Yat-sen University（中山大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； CUHK MMLab（香港中文大学多模态实验室） ； Peking University（北京大学） 纠错

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

Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark

Jinyuan Liu, Zihang Chen, Zhu Liu, Zhiying Jiang, Long Ma, Xin Fan, Risheng Liu

机构 * School of Software Engineering, Dalian University of Technology（大连理工大学软件学院） ； Information Science and Technology College, Dalian Martime University（大连海事大学信息科学与技术学院） 纠错

Comments This paper has been accepted by NeurIPS 2025

Learning Neural Exposure Fields for View Synthesis

Michael Niemeyer, Fabian Manhardt, Marie-Julie Rakotosaona, Michael Oechsle, Christina Tsalicoglou, Keisuke Tateno, Jonathan T. Barron, Federico Tombari

机构 * Google（谷歌） 纠错

Comments Accepted to NeurIPS 2025. Project page available at https://m-niemeyer.github.io/nexf/index.html

CAFL-L: Constraint-Aware Federated Learning with Lagrangian Dual Optimization for On-Device Language Models

Dongqi Zheng, Wenjin Fu

机构 * Purdue University（普渡大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments Accepted by 39th NeurIPS - Constrained Optimization for Machine Learning

ARS: Adaptive Reasoning Suppression for Efficient Large Reasoning Language Models

Dongqi Zheng

机构 * Independent Researcher（独立研究者） 纠错

Comments Accepted by 39th NeurIPS - Foundations of Reasoning in Language Models

Robustness in Both Domains: CLIP Needs a Robust Text Encoder

Elias Abad Rocamora, Christian Schlarmann, Naman Deep Singh, Yongtao Wu, Matthias Hein, Volkan Cevher

Comments Accepted in NeurIPS 2025