LatentDiff: Scaling Semantic Dataset Comparison to Millions of Images
School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, Oregon, USA(俄勒冈州立大学电气工程与计算机科学学院);Lawrence Livermore National Laboratory, Livermore, California, USA(劳伦斯利弗莫尔国家实验室);University of California San Diego, California, USA(加州大学圣地亚哥分校)
James Flora, Kowshik Thopalli, Akshay R. Kulkarni, Weng-Keen Wong, Shusen Liu
We present LatentDiff, a scalable framework for semantic dataset comparison that operates directly in the latent space of pretrained vision encoders. By combining sparse autoencoder-based divergence testing with density ratio estimation, LatentDiff identifies interpretable semantic differences between datasets at a fraction of the computational cost of caption-based alternatives. We also introduce Noisy-Diff, a benchmark capturing realistic sparse distribution shifts that cause existing methods to struggle. Experiments demonstrate that LatentDiff achieves superior accuracy while remaining robust to settings where an extremely small fraction of images (from 5% to <1% ) differ semantically.
OpenECG: Benchmarking ECG Foundation Models with Public 1.2 Million Records
The First Affiliated Hospital, Jiangxi Medical College, Nanchang University(南昌大学江西医学院第一附属医院);Nanchang University(南昌大学);Georgia Institution of Technology(佐治亚理工学院)
AstroPT: Scaling Large Observation Models for Astronomy
Aspia Space(阿斯皮亚空间);Instituto de Astrofísica de Canarias (IAC)(加那利群岛天体物理学研究所);UniverseTBD;Astrophysics Research Institute, Liverpool John Moores University(利物浦约翰摩尔大学天体物理学研究所);Universidad de la Laguna(拉古纳大学);Observatoire de Paris(巴黎天文台);PSL University(巴黎文理研究大学);Université Paris-Cité(巴黎城市大学)
BioVFM-21M: Benchmarking and Scaling Self-Supervised Vision Foundation Models for Biomedical Image Analysis
Paul C. Lauterbur Research Center for Biomedical Imaging(生物医学成像保罗·劳特伯研究中心);Shenzhen Institutes of Advanced Technology(深圳先进技术研究院);Chinese Academy of Sciences(中国科学院);Pengcheng Laboratory(鹏城实验室);University of Chinese Academy of Sciences(中国科学院大学);Faculty of Applied Sciences(应用科学学院)
P3P: Pseudo-3D Pre-training for Scaling 3D Voxel-based Masked Autoencoders
SIGS, Tsinghua University(清华大学信号与信息处理系);Youtu Lab, Tencent(腾讯优图实验室);The University of Texas at Austin(德克萨斯大学奥斯汀分校);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Shanghai AI Laboratory(上海人工智能实验室);The Hong Kong Polytechnic University(香港理工大学);ARC Lab, Tencent PCG(腾讯平台与内容事业群ARC实验室);The Chinese University of Hong Kong(香港中文大学)
Virchow: A Million-Slide Digital Pathology Foundation Model
Paige;Microsoft Research(微软研究院);NSW Health Pathology(新南威尔士州卫生病理学);St George Hospital(圣乔治医院);Memorial Sloan Kettering Cancer Center(纪念斯隆凯特琳癌症中心);University of Rochester(罗切斯特大学)
Scaling up self-supervised learning for improved surgical foundation models
Department of Electrical Engineering, Video Coding \& Architectures, Eindhoven University of Technology, Eindhoven, The Netherlands;Department of Biomedical Engineering, Medical Image Analysis, Eindhoven University of Technology, Eindhoven, The Netherlands;Department of Surgery, University Medical Center Utrecht, Utrecht, The Netherlands;Department of Oncological Urology, University Medical Center Utrecht, Utrecht, The Netherlands;Department of Urology, Catharina Hospital, Eindhoven, The Netherlands