A Primer on Latent Action Models From the #ssad2026 Talks

abursuc · x · 2026-09-17

Following a showcase of FIVE-VLA's efficiency (640M total parameters, 7.5x more efficient than SimLingo on driving), the author shifted to fundamentals with a primer on Latent Action Models — the technique for learning latent action representations from unlabeled video, a key building block of modern VLA and robot training.

Original post →

More from Embodied

Embodied channel →