LFM3-1.7B
Liquid AIthe whole network is fine-tuned end to end.
specific method · filed under post-training
Fine-tunes the entire VLA or vision-language-action network end to end rather than relying on a separate low-level controller.
The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See supervised fine-tuning for the methods filed beside it.
Also called fine-tune the base VLA end-to-end, the whole network is fine-tuned end to end.
2 quotes from 2 sources, one card per model, each opening with its strongest.
the whole network is fine-tuned end to end.
we fine-tune the base VLA end-to-end with techniques that enable high efficiency without needing a separate controller