arXivDaily arXiv每日学术速递 周一至周五更新

作者

Andrew Y. Ng

Machine Learning

共收录 88 篇
2608.26070 2026-08-27 cs.CL cs.AI cs.LG 新提交

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)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.19606 2026-06-19 math.GR 新提交

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.05091 2026-06-04 math.GR math.GT

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!

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01876 2026-06-04 math.GR

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.01728 2026-04-03 cs.AI

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)

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)

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.01344 2026-04-03 cs.AI

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)

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。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.05706 2026-01-12 math.GR math.AT math.GT

Cobordism, spin structures, and profinite completions

配边、旋结构与投射有限完备化

Sam Hughes, Andrew Ng

AI总结 针对带Serre意义下好基本群的光滑闭连通非球面流形,证明基本群投射有限完备化同构可推出流形配边、签名模8相等且旋结构性质一致,还讨论了紧流形的类似结论。

Comments 24 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.02268 2025-12-03 cs.CV cs.AI cs.LG eess.IV stat.ML

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)

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。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.00383 2025-11-10 cs.CE

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

STARC-9:用于结直肠癌组织病理学多类别组织分类的大规模数据集

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

AI总结 本文提出STARC-9大规模结直肠癌组织分类数据集及DeepCluster++半自动构建框架,通过聚类与等频采样保证类内多样性,并在多种模型上验证了其优越的泛化性能。

Comments 37 pages, 18 figures, Accepted in NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.18602 2025-11-07 eess.IV cs.CV

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

评估与提升合成胸部X光影像在医学图像分析中的有效性

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)

AI总结 本文系统评估了基于潜在扩散模型生成合成胸部X光影像的最佳实践,发现以单一疾病标签或几何变换分割掩码为条件并结合代理模型微调,可显著提升分类与分割模型性能。

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.17580 2025-08-26 cs.CL cs.AI cs.LG

UQ: Assessing Language Models on Unsolved Questions

UQ:评估语言模型在未解决问题上的表现

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

AI总结 针对当前AI基准存在的困难与现实张力问题,提出UQ测试平台,通过异步评估未解决问题、结合验证器和社区验证,推动模型在真实挑战中的能力提升,顶级模型仅15%通过率。

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.03829 2025-07-08 cs.AI

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

RELRaE:基于大语言模型的关系抽取、标注、精化与评估

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)

AI总结 本文提出RELRaE框架,利用大语言模型从实验室XML模式中抽取并标注隐含关系,以支持知识图谱和本体构建,并验证了LLM在半自动本体生成中的有效性。

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23269 2025-05-30 math.GR

Virtual First Betti Number of GGS Groups

GGS群的虚拟第一贝蒂数

Andrew Ng

AI总结 本文提出群具有消失的虚拟第一贝蒂数的准则,并据此构造出无限多个非虚拟扩散的无挠、有限生成、剩余有限群实例,回答了Kionke和Raimbault提出的问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.14654 2025-02-13 cs.LG cs.AI cs.MA

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

MedAgentBench:用于基准测试医疗LLM智能体的真实虚拟电子健康记录环境

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)

AI总结 针对医疗领域缺乏LLM智能体能力基准测试数据集的问题,本文提出MedAgentBench评估套件,含300项临床任务、100份患者档案等,可评估医疗记录语境下LLM智能体能力,为模型优化提供方向。

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.09798 2024-10-08 cs.LG cs.AI cs.CL cs.CV

Many-Shot In-Context Learning in Multimodal Foundation Models

多模态基础模型中的多示例上下文学习

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)

AI总结 本研究评估多模态基础模型从少样本到多样本上下文学习的性能,发现闭源模型随示例增多性能持续提升,开源模型无获益有限,批量查询可降本提效,为多模态模型适配新场景提供了思路。

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.17033 2024-04-29 cs.CV

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)

Comments Accepted at MIDL 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.13185 2024-04-23 eess.IV cs.CV

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)

详情

展开后加载摘要…

URL PDF HTML 收藏
2401.14486 2024-01-29 cs.CV cs.LG

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)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.02200 2023-12-06 cs.CV cs.AI stat.AP

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)

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.02199 2023-12-06 cs.CV cs.AI cs.LG eess.IV stat.AP

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)

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.17449 2023-11-30 cs.CV

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)

Comments Tackling Climate Change with Machine Learning at NeurIPS 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.09574 2023-11-21 cs.LG cs.AI cs.CV

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)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2207.10062 2023-10-16 cs.LG

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)

Comments NeurIPS 2023 Datasets and Benchmarks Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2305.08017 2023-05-16 cs.CV

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)

Comments 13 pages, 12 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2301.01842 2023-01-06 cs.CV cs.CY

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

机构 * Stanford University(斯坦福大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2208.13027 2022-09-05 cs.LG cs.AI

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

机构 * Stanford University(斯坦福大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2207.11166 2022-08-16 cs.CV

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

机构 * Stanford University(斯坦福大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2201.01449 2022-01-06 eess.IV cs.CV cs.LG

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

机构 * Stanford University(斯坦福大学) ; Harvard University(哈佛大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2104.00793 2021-11-30 eess.IV cs.CV cs.LG

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

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

机构 * Stanford University(斯坦福大学) ; Harvard University(哈佛大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2102.10663 2021-10-19 eess.IV cs.CV cs.LG

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

机构 * Stanford University(斯坦福大学) ; School of Medicine, Stanford University(斯坦福大学医学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
↑