NeurIPS

Instant4D: 4D Gaussian Splatting in Minutes

Zhanpeng Luo, Haoxi Ran, Li Lu

机构 * University of Pittsburgh（匹兹堡大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments Accepted by NeurIPS 25

Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties

Gouki Minegishi, Hiroki Furuta, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

机构 * The University of Tokyo（东京大学） 纠错

Comments Accepted to Neurips 2025

Prompt Tuning Decision Transformers with Structured and Scalable Bandits

Finn Rietz, Oleg Smirnov, Sara Karimi, Lele Cao

机构 * Örebro University（奥雷布罗大学） ； King AI Labs, Microsoft Gaming（King AI实验室，微软游戏） 纠错

Comments Accepted at NeurIPS 2025

Benchmarking Agentic Systems in Automated Scientific Information Extraction with ChemX

Anastasia Vepreva, Julia Razlivina, Maria Eremeeva, Nina Gubina, Anastasia Orlova, Aleksei Dmitrenko, Ksenya Kapranova, Susan Jyakhwo, Nikita Vasilev, Arsen Sarkisyan, Ivan Yu. Chernyshov, Vladimir Vinogradov, Andrei Dmitrenko

机构 * Center for AI in Chemistry, ITMO University（人工智能化学中心，ITMO大学） ； D ONE AG（D ONE公司） 纠错

Comments Accepted at The AI for Accelerated Materials Discovery (AI4Mat) Workshop, NeurIPS 2025

Efficient Multi-modal Large Language Models via Progressive Consistency Distillation

Zichen Wen, Shaobo Wang, Yufa Zhou, Junyuan Zhang, Qintong Zhang, Yifeng Gao, Zhaorun Chen, Bin Wang, Weijia Li, Conghui He, Linfeng Zhang

Comments Accepted by NeurIPS 2025

Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection

Anay Majee, Amitesh Gangrade, Rishabh Iyer

机构 * The University of Texas at Dallas（德克萨斯大学达拉斯分校） 纠错

Comments Accepted to NeurIPS'25. 22 pages, 6 figures

Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT

Guy Bar-Shalom, Fabrizio Frasca, Yaniv Galron, Yftah Ziser, Haggai Maron

机构 * Technion（技术离子大学） ； University of Groningen（格罗宁根大学） ； Nvidia Research（英伟达研究） 纠错

Comments Published in NeurIPS 2025

NeurIPS should lead scientific consensus on AI policy

Rishi Bommasani

机构 * Stanford Institute for Human-Centered Artificial Intelligence (HAI)（斯坦福大学人本人工智能研究所） 纠错

Comments Published at NeurIPS 2025

Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations

Sihao Ding, Santosh Vasa, Aditi Ramadwar

机构 * Mercedes-Benz Research & Development North America（梅赛德斯-奔驰研究与开发北美） 纠错

Comments NeurIPS 2025 workshop on Regulatable ML

Steering When Necessary: Flexible Steering Large Language Models with Backtracking

Zifeng Cheng, Jinwei Gan, Zhiwei Jiang, Cong Wang, Yafeng Yin, Xiang Luo, Yuchen Fu, Qing Gu

机构 * State Key Laboratory for Novel Software Technology, Nanjing University, China（新型软件技术国家重点实验室，南京大学，中国） 纠错

Comments NeurIPS 2025

Post Hoc Regression Refinement via Pairwise Rankings

Kevin Tirta Wijaya, Michael Sun, Minghao Guo, Hans-Peter Seidel, Wojciech Matusik, Vahid Babaei

机构 * MPI-INF（马克斯·普朗克研究所信息部门） ； MIT（麻省理工学院） 纠错

Comments NeurIPS 2025 camera-ready version

Robust Estimation Under Heterogeneous Corruption Rates

Syomantak Chaudhuri, Jerry Li, Thomas A. Courtade

机构 * University of California, Berkeley（加州大学伯克利分校） ； University of Washington（华盛顿大学） 纠错

Comments NeurIPS 2025, fixed PAC minimax definition

Precise Information Control in Long-Form Text Generation

Jacqueline He, Howard Yen, Margaret Li, Shuyue Stella Li, Zhiyuan Zeng, Weijia Shi, Yulia Tsvetkov, Danqi Chen, Pang Wei Koh, Luke Zettlemoyer

机构 * Paul G. Allen School of Computing Science & Engineering, University of Washington（保罗·G·艾伦计算科学与工程学院，华盛顿大学） ； Princeton Language and Intelligence (PLI), Princeton University（普林斯顿语言与智能（PLI），普林斯顿大学） ； Allen Institute for AI（艾伦人工智能研究所） 纠错

Comments NeurIPS 2025. 66 pages, 8 figures. Code is at https://github.com/jacqueline-he/precise-information-control

ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data

Xiaoyang Liu, Kangjie Bao, Jiashuo Zhang, Yunqi Liu, Yu Chen, Yuntian Liu, Yang Jiao, Tao Luo

Comments Accepted to NeurIPS 2025

A distributional simplicity bias in the learning dynamics of transformers

Riccardo Rende, Federica Gerace, Alessandro Laio, Sebastian Goldt

机构 * International School for Advanced Studies（国际先进研究学校） 纠错

Comments 10 pages, 5 figures, NeurIPS 2024

Journal ref NeurIPS 2024