CVLGMay 20

OlmoEarth v1.1: A more efficient family of OlmoEarth models

arXiv:2605.2080449.5Has Code
AI Analysis

Incremental efficiency improvements for users of the OlmoEarth model family.

OlmoEarth v1.1 reduces training GPU hours by 1.7× and inference MACs by 2.9× on Sentinel-2 tasks while maintaining performance.

We present a set of improvements to the OlmoEarth family. These improvements allow us to cut compute costs during training ($1.7 \times$ reduction in GPU hours required to train our Base models) and inference ($2.9\times$ reductions in MACs on Sentinel-2 tasks), while maintaining the models' overall performance. All training code is available at github.com/allenai/olmoearth_pretrain.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes