OlmoEarth v1.1: A more efficient family of models
Allen AI has released OlmoEarth v1.1, an updated family of models designed for processing satellite imagery more efficiently. These new models reduce compute costs by up to 3x for inference and require 1.7x fewer GPU hours for training, while maintaining performance on remote sensing tasks. The efficiency gains are achieved by optimizing the tokenization process for transformer-based architectures, specifically by merging resolution-based tokens without significant performance degradation. AI
IMPACT Offers significant cost reductions for satellite imagery analysis, potentially enabling wider adoption of AI for environmental monitoring and mapping.