OlmoEarth v1.2: A more efficient family of OlmoEarth models
Not on the map. Why?
Abstract (arXiv)
We present a set of improvements to the OlmoEarth family. These improvements allow us to cut compute costs during training (3.0 × reduction in GPU hours required to train our Base models) and inference (2.9× reductions in MACs on Sentinel-2 tasks), while maintaining the models' overall performance. All training code is available at github.com/allenai/olmoearthpretrain.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 13 of its 19 references that are in the map. First posted on arXiv 20 May 2026.
Builds on
13 of 19 references.
References · 13
- 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
- 2022SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagerycited by 402
- 2021Early Convolutions Help Transformers See Bettercited by 395
- 2024Rotary Position Embedding for Vision Transformercited by 226
- 2022FlexiViT: One Model for All Patch Sizescited by 151
- 2024Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applicationscited by 139
- 2020Boosting Contrastive Self-Supervised Learning with False Negative Cancellationcited by 119
- 2023Lightweight, Pre-trained Transformers for Remote Sensing Timeseriescited by 102
- 2023Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidarcited by 60
- 2025Galileo: Learning Global & Local Features of Many Remote Sensing Modalitiescited by 41
- 2023Understanding Contrastive Learning via Distributionally Robust Optimizationcited by 21
- 2024Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learningcited by 20
1 more
Built on by
Citing papers per year: 2026: 1.
1 paper.