Andrew Y. Ng

Prefix Sliding for efficient test-time scaling

用于高效测试时缩放的前缀滑动

Niklas Muennighoff, Zhengyang Wang, Zeyi Chen, Weijia Shi, Binyuan Hui, John Yang, Dapeng Jiang, Mika Senghaas, Fares Obeid, Johannes Hagemann, Sami Jaghouar, Ludwig Schmidt, Percy Liang, Jason Wei, Andrew Y. Ng, Luke Zettlemoyer, Yejin Choi, Mike Lewis

机构 * Stanford University（斯坦福大学） ； University of California at Santa Barbara（加州大学圣巴巴拉分校） ； Prime Intellect ； University of Washington（华盛顿大学） 纠错

AI总结 针对测试时推理内存成本过高问题，提出Prefix Sliding方法，通过丢弃非关键标记限制内存，无需训练可提速3倍，结合强化学习训练后性能更优且优于其他基线

Comments 28 pages (9 main), 22 figures, 3 tables

Outer automorphism groups and the Atiyah Conjecture

外自同构群与Atiyah猜想

Sam P. Fisher, Andrew Ng

AI总结 研究紧致曲面基本群、有限生成自由群或更一般的有限生成右角Artin群的外自同构群的von Neumann维数，通过建立有限指数无挠子群的强Atiyah猜想，并证明其群环嵌入除环。

Comments 28 pages, comments welcome

Improved algebraic fibrations of high-dimensional hyperbolic groups

高维双曲群的改进代数纤维化

Giovanni Italiano, Matteo Migliorini, Andrew Ng

AI总结 对于每个 d≥3，通过右角Coxeter群的有限指数子群构造无穷多个上同调维数为d的双曲群G，它们具有有限表现核的代数纤维化，并利用L^2-Betti数给出核的更高有限性障碍。

Comments 16 pages, 2 figures. Comments welcome!

Quasi-convex surface subgroups in some one-relator groups with torsion

某些带挠的一关系群中的拟凸面子群

Andrew Ng

AI总结 本文在特定带挠的一关系群中构造了面子群，并利用这一结果推导了自由群中一个词为原始词的一个profinite准则。

Comments v2: 7 pages, revised following referee comments

The AnIML Ontology: Enabling Semantic Interoperability for Large-Scale Experimental Data in Interconnected Scientific Labs

AnIML本体：实现互联科学实验室大规模实验数据的语义互操作性

Wilf Morlidge, Elliott Watkiss-Leek, George Hannah, Harry Rostron, Andrew Ng, Ewan Johnson, Andrew Mitchell, Terry R. Payne, Valentina Tamma, Jacopo de Berardinis

机构 * School of Computer Science & Informatics, University of Liverpool（利物浦大学计算机科学与信息学院） ； Unilever Plc. Materials Innovation Factory, University of Liverpool（联合利华公司材料创新工厂，利物浦大学） 纠错

AI总结 本文提出AnIML本体，通过专家在环方法结合LLM需求提取与协同本体工程，实现AnIML与Allotrope数据格式的语义对齐，解决异构实验数据系统的互操作性问题。

Comments Accepted at the 38th International Conference on Advanced Information Systems Engineering (CAiSE 2026)

IDEA2: Expert-in-the-loop competency question elicitation for collaborative ontology engineering

IDEA2: 专家在环的协作本体工程能力问题 elicitation

Elliott Watkiss-Leek, Reham Alharbi, Harry Rostron, Andrew Ng, Ewan Johnson, Andrew Mitchell, Terry R. Payne, Valentina Tamma, Jacopo de Berardinis

机构 * School of Computer Science and Informatics, University of Liverpool（利物浦大学计算机科学与信息学院） ； College of Computer Science and Engineering, Taibah University（塔伊巴大学计算机科学与工程学院） ； Unilever Plc., Materials Innovation Factory, University of Liverpool（联合利华公司，利物浦大学材料创新工厂） 纠错

AI总结 IDEA2通过整合大语言模型和专家反馈，解决本体工程中能力问题提取的瓶颈，提升问题相关性和可接受性。

Cobordism, spin structures, and profinite completions

Sam Hughes, Andrew Ng

Comments 24 pages

Spatiotemporal Pyramid Flow Matching for Climate Emulation

时空金字塔流匹配用于气候模拟

Jeremy Andrew Irvin, Jiaqi Han, Zikui Wang, Abdulaziz Alharbi, Yufei Zhao, Nomin-Erdene Bayarsaikhan, Daniele Visioni, Andrew Y. Ng, Duncan Watson-Parris

机构 * Stanford University（斯坦福大学） ； Cornell University（康奈尔大学） ； University of California, San Diego（加州大学圣地亚哥分校） 纠错

AI总结 本文提出时空金字塔流匹配方法，用于高效、准确的多时间尺度气候模拟，并通过ClimateSuite数据集验证其有效性。

STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology

Barathi Subramanian, Rathinaraja Jeyaraj, Mitchell Nevin Peterson, Terry Guo, Nigam Shah, Curtis Langlotz, Andrew Y. Ng, Jeanne Shen

Comments 37 pages, 18 figures, Accepted in NeurIPS 2025

Evaluating and Improving the Effectiveness of Synthetic Chest X-Rays for Medical Image Analysis

Eva Prakash, Jeya Maria Jose Valanarasu, Zhihong Chen, Eduardo Pontes Reis, Andrew Johnston, Anuj Pareek, Christian Bluethgen, Sergios Gatidis, Cameron Olsen, Akshay Chaudhari, Andrew Ng, Curtis Langlotz

机构 * Stanford University（斯坦福大学） 纠错

Journal ref Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, October 2025, pages 4413-4421

UQ: Assessing Language Models on Unsolved Questions

Fan Nie, Ken Ziyu Liu, Zihao Wang, Rui Sun, Wei Liu, Weijia Shi, Huaxiu Yao, Linjun Zhang, Andrew Y. Ng, James Zou, Sanmi Koyejo, Yejin Choi, Percy Liang, Niklas Muennighoff

Comments FN, KZL, and NM are project co-leads and contributed equally. Project website: https://uq.stanford.edu

RELRaE: LLM-Based Relationship Extraction, Labelling, Refinement, and Evaluation

George Hannah, Jacopo de Berardinis, Terry R. Payne, Valentina Tamma, Andrew Mitchell, Ellen Piercy, Ewan Johnson, Andrew Ng, Harry Rostron, Boris Konev

机构 * Department of Computer Science, University of Liverpool（利物浦大学计算机科学系） ； Unilever Plc. Materials Innovation Factory（联合利华材料创新工厂） ； University of Liverpool（利物浦大学） 纠错

Comments 18 Pages, 8 Tables, Under-review at ISWC 2025

Virtual First Betti Number of GGS Groups

Andrew Ng

MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents

Yixing Jiang, Kameron C. Black, Gloria Geng, Danny Park, James Zou, Andrew Y. Ng, Jonathan H. Chen

机构 * Stanford University（斯坦福大学） 纠错

Many-Shot In-Context Learning in Multimodal Foundation Models

Yixing Jiang, Jeremy Irvin, Ji Hun Wang, Muhammad Ahmed Chaudhry, Jonathan H. Chen, Andrew Y. Ng

机构 * Stanford University（斯坦福大学） 纠错

Auto-Generating Weak Labels for Real & Synthetic Data to Improve Label-Scarce Medical Image Segmentation

Tanvi Deshpande, Eva Prakash, Elsie Gyang Ross, Curtis Langlotz, Andrew Ng, Jeya Maria Jose Valanarasu

机构 * Stanford University（斯坦福大学） 纠错

Comments Accepted at MIDL 2024

Unlocking Robust Segmentation Across All Age Groups via Continual Learning

Chih-Ying Liu, Jeya Maria Jose Valanarasu, Camila Gonzalez, Curtis Langlotz, Andrew Ng, Sergios Gatidis

机构 * Stanford University（斯坦福大学） 纠错

CloudTracks: A Dataset for Localizing Ship Tracks in Satellite Images of Clouds

Muhammad Ahmed Chaudhry, Lyna Kim, Jeremy Irvin, Yuzu Ido, Sonia Chu, Jared Thomas Isobe, Andrew Y. Ng, Duncan Watson-Parris

机构 * Stanford University（斯坦福大学） ； UC San Diego, Scripps Institution of Oceanography and Halıcıoğlu Data Science Institute（加州大学圣迭戈分校，斯克里普斯海洋研究所和哈勒西奥卢数据科学研究所） 纠错

Comments 11 pages, 5 figures, submitted to Journal of Machine Learning Research

An Empirical Study of Automated Mislabel Detection in Real World Vision Datasets

Maya Srikanth, Jeremy Irvin, Brian Wesley Hill, Felipe Godoy, Ishan Sabane, Andrew Y. Ng

机构 * Stanford University（斯坦福大学） 纠错

USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery

Jeremy Irvin, Lucas Tao, Joanne Zhou, Yuntao Ma, Langston Nashold, Benjamin Liu, Andrew Y. Ng

机构 * Stanford University（斯坦福大学） 纠错

Weakly-semi-supervised object detection in remotely sensed imagery

Ji Hun Wang, Jeremy Irvin, Beri Kohen Behar, Ha Tran, Raghav Samavedam, Quentin Hsu, Andrew Y. Ng

机构 * Stanford University（斯坦福大学） 纠错

Comments Tackling Climate Change with Machine Learning at NeurIPS 2023

LymphoML: An interpretable artificial intelligence-based method identifies morphologic features that correlate with lymphoma subtype

Vivek Shankar, Xiaoli Yang, Vrishab Krishna, Brent Tan, Oscar Silva, Rebecca Rojansky, Andrew Ng, Fabiola Valvert, Edward Briercheck, David Weinstock, Yasodha Natkunam, Sebastian Fernandez-Pol, Pranav Rajpurkar

机构 * Stanford University（斯坦福大学） ； Stanford University School of Medicine（斯坦福大学医学院） ； Harvard Medical School（哈佛医学院） ； La Liga Nacional Contra el Cáncer de Guatemala (INCAN)（危地马拉国家抗癌联盟（INCAN）） ； Fred Hutchinson Cancer Research Center（弗雷德·哈钦森癌症研究中心） ； Dana-Farber Cancer Institute（达纳-法伯癌症研究所） 纠错

Comments To be published in Proceedings of the 3rd Machine Learning for Health symposium, Proceedings of Machine Learning Research (PMLR)

DataPerf: Benchmarks for Data-Centric AI Development

Mark Mazumder, Colby Banbury, Xiaozhe Yao, Bojan Karlaš, William Gaviria Rojas, Sudnya Diamos, Greg Diamos, Lynn He, Alicia Parrish, Hannah Rose Kirk, Jessica Quaye, Charvi Rastogi, Douwe Kiela, David Jurado, David Kanter, Rafael Mosquera, Juan Ciro, Lora Aroyo, Bilge Acun, Lingjiao Chen, Mehul Smriti Raje, Max Bartolo, Sabri Eyuboglu, Amirata Ghorbani, Emmett Goodman, Oana Inel, Tariq Kane, Christine R. Kirkpatrick, Tzu-Sheng Kuo, Jonas Mueller, Tristan Thrush, Joaquin Vanschoren, Margaret Warren, Adina Williams, Serena Yeung, Newsha Ardalani, Praveen Paritosh, Lilith Bat-Leah, Ce Zhang, James Zou, Carole-Jean Wu, Cody Coleman, Andrew Ng, Peter Mattson, Vijay Janapa Reddi

机构 * Harvard University（哈佛大学） ； ETH Zurich（苏黎世联邦理工学院） ； Landing AI（Landing AI公司） ； Google（谷歌） ； University of Oxford（牛津大学） ； Carnegie Mellon University（卡内基梅隆大学） ； Stanford University（斯坦福大学） ； Contextual AI（Contextual AI公司） ； MLCommons（MLCommons组织） ； Factored（Factored公司） ； Meta ； Cohere（Cohere公司） ； University College London（伦敦大学学院） ； University of Zurich（苏黎世大学） ； San Diego Supercomputer Center, UC San Diego（加州大学圣地亚哥分校圣地亚哥超级计算机中心） ； Cleanlab（Cleanlab公司） ； Eindhoven University of Technology（埃因霍温理工大学） ； Institute for Human and Machine Cognition（人类与机器认知研究所） 纠错

Comments NeurIPS 2023 Datasets and Benchmarks Track

How to Train Your CheXDragon: Training Chest X-Ray Models for Transfer to Novel Tasks and Healthcare Systems

Cara Van Uden, Jeremy Irvin, Mars Huang, Nathan Dean, Jason Carr, Andrew Ng, Curtis Langlotz

机构 * Stanford University（斯坦福大学） ； University of Utah（犹他大学） ； Intermountain Medical Center（山间医疗中心） 纠错

Comments 13 pages, 12 figures

Detecting Neighborhood Gentrification at Scale via Street-level Visual Data

Tianyuan Huang, Timothy Dai, Zhecheng Wang, Hesu Yoon, Hao Sheng, Andrew Y. Ng, Ram Rajagopal, Jackelyn Hwang

Improving debris flow evacuation alerts in Taiwan using machine learning

Yi-Lin Tsai, Jeremy Irvin, Suhas Chundi, Andrew Y. Ng, Christopher B. Field, Peter K. Kitanidis

Comments Supplementary information: https://drive.google.com/file/d/1Y17YxXo5rhIbUuZzwLo99pmttbh28v9X/view?usp=sharing

METER-ML: A Multi-Sensor Earth Observation Benchmark for Automated Methane Source Mapping

Bryan Zhu, Nicholas Lui, Jeremy Irvin, Jimmy Le, Sahil Tadwalkar, Chenghao Wang, Zutao Ouyang, Frankie Y. Liu, Andrew Y. Ng, Robert B. Jackson

Comments Workshop on Complex Data Challenges in Earth Observation at IJCAI-ECAI 2022

Deep Learning-Based Sparse Whole-Slide Image Analysis for the Diagnosis of Gastric Intestinal Metaplasia

Jon Braatz, Pranav Rajpurkar, Stephanie Zhang, Andrew Y. Ng, Jeanne Shen

Effect of Radiology Report Labeler Quality on Deep Learning Models for Chest X-Ray Interpretation

Saahil Jain, Akshay Smit, Andrew Y. Ng, Pranav Rajpurkar

Comments In Neural Information Processing Systems (NeurIPS) Workshop on Data-Centric AI (DCAI)

MedAug: Contrastive learning leveraging patient metadata improves representations for chest X-ray interpretation

Yen Nhi Truong Vu, Richard Wang, Niranjan Balachandar, Can Liu, Andrew Y. Ng, Pranav Rajpurkar