arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Massachusetts Institute of Technology(麻省理工学院)

2026-04-15 至 2026-04-15 共收录 10
2604.11584 2026-04-15 math.OC cs.LG math.ST stat.TH

Computation of Least Trimmed Squares: A Branch-and-Bound framework with Hyperplane Arrangement Enhancements

最小子集平方求解:一种结合超平面排列改进的分支限界框架

Xiang Meng, Andrés Gómez, Rahul Mazumder

机构 * MIT Operations Research Center(麻省理工学院运营研究中心) USC Daniel J. Epstein Department of Industrial and Systems Engineering(南加州大学Daniel J. Epstein工业与系统工程系) MIT Sloan School of Management, Operations Research Center(麻省理工学院斯隆管理学院,运营研究中心)

AI总结 本文提出一种改进的分支限界框架,用于高效求解稳健统计中的加权最小子集平方回归问题,通过超平面排列逻辑提升计算效率,实验证明在低维数据中能显著提升求解速度和精度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.09784 2026-04-15 stat.ML cs.LG

Discrete Flow Maps

离散流映射

Peter Potaptchik, Jason Yim, Adhi Saravanan, Peter Holderrieth, Eric Vanden-Eijnden, Michael S. Albergo

机构 * Harvard University(哈佛大学) University of Oxford(牛津大学) MIT(麻省理工学院) Kempner Institute(凯普纳研究所)

AI总结 本文提出离散流映射,通过在概率单纯形几何上实现轨迹压缩,解决离散数据生成中的几何不匹配问题,提升离散流模型性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.13961 2026-04-15 cs.CL cs.LG

Olmo 3

Olmo 3:先进全开源语言模型家族

Team Olmo, :, Allyson Ettinger, Amanda Bertsch, Bailey Kuehl, David Graham, David Heineman, Dirk Groeneveld, Faeze Brahman, Finbarr Timbers, Hamish Ivison, Jacob Morrison, Jake Poznanski, Kyle Lo, Luca Soldaini, Matt Jordan, Mayee Chen, Michael Noukhovitch, Nathan Lambert, Pete Walsh, Pradeep Dasigi, Robert Berry, Saumya Malik, Saurabh Shah, Scott Geng, Shane Arora, Shashank Gupta, Taira Anderson, Teng Xiao, Tyler Murray, Tyler Romero, Victoria Graf, Akari Asai, Akshita Bhagia, Alexander Wettig, Alisa Liu, Aman Rangapur, Chloe Anastasiades, Costa Huang, Dustin Schwenk, Harsh Trivedi, Ian Magnusson, Jaron Lochner, Jiacheng Liu, Lester James V. Miranda, Maarten Sap, Malia Morgan, Michael Schmitz, Michal Guerquin, Michael Wilson, Regan Huff, Ronan Le Bras, Rui Xin, Rulin Shao, Sam Skjonsberg, Shannon Zejiang Shen, Shuyue Stella Li, Tucker Wilde, Valentina Pyatkin, Will Merrill, Yapei Chang, Yuling Gu, Zhiyuan Zeng, Ashish Sabharwal, Luke Zettlemoyer, Pang Wei Koh, Ali Farhadi, Noah A. Smith, Hannaneh Hajishirzi

机构 * Allen Institute for AI(Allen人工智能研究所) University of Washington(华盛顿大学) Carnegie Mellon University(卡内基梅隆大学) Stanford University(斯坦福大学) Princeton University(普林斯顿大学) Massachusetts Institute of Technology(麻省理工学院) University of Maryland(马里兰大学)

AI总结 Olmo 3是一款7B和32B参数规模的先进语言模型,专注于长上下文推理、函数调用、编程、指令遵循、通用聊天和知识回忆。

Comments minor edit updates

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03497 2026-04-15 cs.LG

Invariant Features for Global Crop Type Classification

全局作物类型分类的不变特征

Xin-Yi Tong, Sherrie Wang

机构 * Laboratory for Information and Decision Systems, MIT(信息与决策系统实验室,麻省理工学院) Department of Mechanical Engineering, MIT(机械工程系,麻省理工学院) Institute for Data, Systems, and Society, MIT(数据、系统与社会研究所,麻省理工学院)

AI总结 本文提出CropNet,通过联合学习光谱和时间维度的不变特征,提升跨地理区域的作物分类性能,优于传统方法和基础模型。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.12202 2026-04-15 cs.AI cs.SI

Latent patterns of urban mixing in mobility analysis across five global cities

城市混合的潜在模式:在五个全球城市中的移动分析

Z. Fan, B. P. Y. Loo, F. Duarte, C. Ratti, E. Moro

机构 * Department of Geography, The University of Hong Kong(香港大学地理系) Institute of Marine Sustainable Development, Liaoning Normal University(辽宁师范大学海洋可持续发展研究院) Senseable City Lab, Massachusetts Institute of Technology(麻省理工学院感知城市实验室) ABC Department, Politecnico di Milano(米兰理工大学ABC部门) Network Science Institute and Department of Physics, Northeastern University(东北大学网络科学研究院和物理系) Media Lab, Massachusetts Institute of Technology(麻省理工学院媒体实验室)

AI总结 研究通过大规模出行调查揭示五个全球城市中社会混合模式,发现 socioeconomic 状态和年龄对混合影响不同,构建了空间时间场所网络。

Comments Fan, Z., Loo, B.P.Y., Duarte, F., Ratti, C., & Moro, E. (2026). Latent patterns of urban mixing in mobility analysis across five global cities. Nature Cities, accepted

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.12152 2026-04-15 cs.CV cs.AI

Domain-Specific Latent Representations Improve the Fidelity of Diffusion-Based Medical Image Super-Resolution

领域特定潜在表示提高基于扩散的医学图像超分辨率的保真度

Sebastian Cajas, Ashaba Judith, Rahul Gorijavolu, Sahil Kapadia, Hillary Clinton Kasimbazi, Leo Kinyera, Emmanuel Paul Kwesiga, Sri Sri Jaithra Varma Manthena, Luis Filipe Nakayama, Ninsiima Doreen, Leo Anthony Celi

机构 * Massachusetts Institute of Technology(麻省理工学院) Department of Biomedical Engineering, Mbarara University of Science and Technology(姆巴拉大学科学与技术学院生物医学工程系) Johns Hopkins University(约翰霍普金斯大学) University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校) Makerere University(Makerere大学) Federal University of São Paulo(圣保罗联邦大学) Technical University of Applied Sciences Lübeck (TH Lübeck)(吕贝克应用技术大学) Harvard T.H. Chan School of Public Health(哈佛大学T.H. Chan公共卫生学院)

AI总结 本文通过替换通用稳定扩散VAE为领域特定的MedVAE,显著提升了医学图像超分辨率的PSNR,验证了领域特定自动编码器对重建质量的关键影响。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.12137 2026-04-15 stat.AP cs.AI stat.ME

Observing the unobserved confounding through its effects: toward randomized trial-like estimates from real-world survival data

通过其影响观测未观测的混淆:从真实世界生存数据中获得随机对照试验样的估计

Vasiliki Stoumpou, Dimitris Bertsimas, Samuel Singer, Georgios Antonios Margonis

机构 * Operations Research Center, Massachusetts Institute of Technology(麻省理工学院运营研究中心) Sloan School of Management, Massachusetts Institute of Technology(麻省理工学院斯隆管理学院) Department of Surgery, Memorial Sloan Kettering Cancer Center(纪念斯隆凯特琳癌症中心外科部) Charité-Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin(柏林夏里特医学院,柏林自由大学和洪堡大学联合成员)

AI总结 本文提出一种三步框架,通过推断和平衡潜在的预后因素来减少真实世界生存数据中的未观测混淆,提升治疗效应估计。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.11992 2026-04-15 cs.RO cs.CV

ReefMapGS: Enabling Large-Scale Underwater Reconstruction by Closing the Loop Between Multimodal SLAM and Gaussian Splatting

ReefMapGS:通过多模态SLAM与高斯点云之间的闭环实现大规模水下重建

Daniel Yang, Jungseok Hong, John J. Leonard, Yogesh Girdhar

机构 * Massachusetts Institute of Technology(麻省理工学院) Woods Hole Oceanographic Institution(伍兹霍尔海洋研究所)

AI总结 本文提出ReefMapGS框架,通过多模态传感器数据与高斯点云结合,实现水下复杂场景的增量重建与全局轨迹优化,展示无COLMAP的3D重建与高精度AUV轨迹估计。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.18187 2026-04-15 cs.CV cs.AI

BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding

BRAIN: 一种用于视觉-脑理解的偏见缓解持续学习方法

Xuan-Bac Nguyen, Thanh-Dat Truong, Pawan Sinha, Khoa Luu

机构 * organization= Department of Physics, J.K. Institute of Science , addressline= Jawahar Nagar , city= Trivandrum , postcode= 695013 , state= Kerala , country= India organization= World Scientific University , addressline= Street 29 , postcode= 1011 NX , postcodesep= , city= Amsterdam , country= The Netherlands organization= University of Intelligent Studies , addressline= Street 15 , city= Jabaldesh , postcode= 825001 , state= Orissa , country= India organization= Electrical Engineering \& Computer Science Department, University of Arkansas , addressline= 1 University of Arkansas , postcode= 72703 AR , postcodesep= , city= Fayetteville , country= USA organization= Department of Brain Cognitive Sciences, Massachusetts Institute of Technology , addressline= 77 Massachusetts Ave , postcode= 02139 MA , postcodesep= , city= Cambridge , country= USA

AI总结 本文提出BRAIN方法,通过持续学习缓解脑信号偏见问题,引入去偏对比学习损失和角度基遗忘缓解方法,提升模型性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00239 2026-04-15 cs.AI

SmellNet: A Large-scale Dataset for Real-world Smell Recognition

SmellNet:一个大规模数据集用于现实世界中的气味识别

Dewei Feng, Wei Dai, Carol Li, Alistair Pernigo, Yunge Wen, Paul Pu Liang

机构 * MIT Media Lab(麻省理工学院媒体实验室) MIT EECS(麻省理工学院电子工程与计算机科学系)

AI总结 本文提出SmellNet数据集,通过小气体和化学传感器收集82.8万条时间序列数据,用于训练ScentFormer模型,实现对多种物质和混合物的气味识别与分类,展示了基于传感器的嗅觉AI的应用潜力。

Comments Accepted to ICLR 2026; published as a conference paper at ICLR 2026. 32 pages; 21 figures

详情

展开后加载摘要…

URL PDF HTML 收藏