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.
More from Embodied
- Lightwheel open-sources EgoSuite-Open100K: 100K hours of egocentric video for robot hands — lukas_m_ziegler · 2026-08-21
- Open-source WBC-Mjlab lands on mjswan Cloud: one policy drives G1's whole-body skills in your browser — kevin_zakka · 2026-08-21
- Humanoid robotics VC funding hits $8.7B in 2026, nearly 2x 2025's record — rohanpaul_ai · 2026-08-21
- Humanoid Robot Finger Dexterity: Bag Drops in One Second — rohanpaul_ai · 2026-08-21
- Proposal: use video generation as the high-level policy in a pi-0.7-style dual-system robot architecture — 12exyz · 2026-08-21
- Mars is the experiment robot learning can't run on Earth — Dr_Singularity · 2026-08-21