NASA-IBM lunar foundation model hits Hugging Face: 11 data modalities, 2M observation bundles
victormustar · x · 2026-09-19
The NASA-IBM Lunar Foundation Model, supported by USRA's planetary science expertise, is now available on Hugging Face. It was pre-trained on roughly 2 million bundles of lunar data combining high-resolution imagery, terrain/topography, illumination, gravity, and other measurements — 11 data modalities in total, with resolutions ranging from 1 meter to 100 meters per pixel.
Related event: NASA and IBM Open-Source Lunar Foundation Model(3 posts)→
More from Research
- Tiny tuned classifier beats Jev: GLiNER 2.5 hits 99.7% vs 83.6%, 8.8x faster locally — rickasaurus · 2026-09-19
- Researcher proposes open eval cards and public benchmark repository to fix AI evaluation trust — evijit · 2026-09-19
- DLinear vs PatchTST: an AI research tool unpacks why two 'contradictory' forecasting papers weren't — nagkakaIat · 2026-09-19
- How to Benchmark Enterprise AI Memory Beyond LoCoMo — blaizedsouza · 2026-09-19
- MIT's injectable magnetic nanoantennas kill 52% of drug-resistant brain cancer cells — RosalindPicard · 2026-09-19
- HarvestBench: LLM agents run over animals to save fuel, kill rates hit 98.8% — rickasaurus · 2026-09-19