← 研踪 PaperTrailCVF · CVPR 2026:cvf:00d6cf3a4b86c8374238d23b415b6fe3 · 记录 #1
OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation
Herzog, HenryBastani, FavyenZhang, YawenTseng, GabrielRedmon, JosephSablon, HadrienPark, RyanMorrison, JacobBuraczynski, AlexandraFarley, KarenHansen, JoshHowe, AndrewJohnson, Patrick AlanOtterlee, MarkSchmitt, TedPitelka, HunterDaspit, StephenRatner, RachelWilhelm, ChristopherWood, SebastianJacobi, MikeKerner, HannahShelhamer, EvanFarhadi, AliKrishna, RanjayBeukema, Patrick 来源日期（仅到年份） 2026
来源记录日期 2026
雷达观测 2026-11-02 00:09
摘要
Earth observation data presents a unique challenge: it is spatial like images, sequential like video or text, and highly multimodal. We present Helios: a multimodal, spatio-temporal foundation model that employs a novel self-supervised learning formulation, masking strategy, and loss all designed for the Earth observation domain. Helios achieves state-of-the-art performance compared to 12 other foundation models across a variety of research benchmarks and real-world tasks from external partners. When evaluating embeddings Helios achieves the best performance on 15 out of 24 tasks, and with full fine-tuning it is the best on 19 of 29 tasks. We deploy Helios as the backbone of an end-to-end platform for data collection, labeling, training, and inference of Earth observation models. The Helios platform puts frontier foundation models and powerful data management tools into the hands of non-profits and NGOs working to solve the world's biggest problems. Helios source code, training data, and pre-trained weights are available at REDACTED.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation
Earth observation data presents a unique challenge: it is spatial like images, sequential like video or text, and highly multimodal. We present Helios: a multimodal, spatio-temporal foundation model that employs a novel self-supervised learning formulation, masking strategy, and loss all designed for the Earth observation domain. Helios achieves state-of-the-art performance compared to 12 other foundation models across a variety of research benchmarks and real-world tasks from external partners. When evaluating embeddings Helios achieves the best performance on 15 out of 24 tasks, and with full fine-tuning it is the best on 19 of 29 tasks. We deploy Helios as the backbone of an end-to-end platform for data collection, labeling, training, and inference of Earth observation models. The Helios platform puts frontier foundation models and powerful data management tools into the hands of non-profits and NGOs working to solve the world's biggest problems. Helios source code, training data, and pre-trained weights are available at REDACTED.
查看此版本解读 →查看此版本原文 ↗