26 citations · 123 across the 25 of their papers we have counts for
18 papers · 1 filter
OlmoEarth v1.2: A more efficient family of OlmoEarth models
Gabriel Tseng, Yawen Zhang, Favyen Bastani +8
We present a set of improvements to the OlmoEarth family. These improvements allow us to cut compute costs during training ( reduction in GPU hours required to train ou…
OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation
Henry Herzog, Favyen Bastani, Yawen Zhang +23
Earth observation data presents a unique challenge: it is spatial like images, sequential like video or text, and highly multimodal. We present OlmoEarth: a multimodal, spatio-temp…
OPTIMUS: Observing Persistent Transformations in Multi-temporal Unlabeled Satellite-data
Raymond Yu, Paul Han, Josh Myers-Dean +2
In the face of pressing environmental issues in the 21st century, monitoring surface changes on Earth is more important than ever. Large-scale remote sensing, such as satellite ima…
Galileo: Learning Global & Local Features of Many Remote Sensing Modalities
Gabriel Tseng, Anthony Fuller, Marlena Reil +7
We introduce a highly multimodal transformer to represent many remote sensing modalities - multispectral optical, synthetic aperture radar, elevation, weather, pseudo-labels, and m…
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
Matt Deitke, Christopher Clark, Sangho Lee +47
Today's most advanced vision-language models (VLMs) remain proprietary. The strongest open-weight models rely heavily on synthetic data from proprietary VLMs to achieve good perfor…
On the Generalizability of Foundation Models for Crop Type Mapping
Yi-Chia Chang, Adam J. Stewart, Favyen Bastani +5
Foundation models pre-trained using self-supervised learning have shown powerful transfer learning capabilities on various downstream tasks, including language understanding, text…