GEN architecture challenges VLA status quo with synchronous streams

12exyz · x · 2026-08-21

Notes that @GeneralistAI's GEN architecture diverges from the standard VLA + action chunking approach, resembling @thinkymachines' interaction model with simultaneous I/O streams. GEN-0 is a 10B+ foundation model trained on 270k hours of dexterous data using Harmonic Reasoning. The author questions the 99% from-scratch training and congratulates them on GEN-1.5.

Original post →

More from Embodied

Embodied channel →