QF3 arrives: fast flow RL trains humanoids from scratch and fine-tunes VLAs
ChongZzZhang · x · 2026-10-07
Chung Min Kim introduces QF3 (Fast Flow RL with Filtered Q-Gradients), a simple off-policy update that can train humanoids from scratch, fine-tune VLAs, and even fine-tune image models — one method covering multiple tasks. A robotics training research advance worth watching for paper details and reproductions.
More from Embodied
- Workhorse: whole-body loco-manipulation from human demos, no teleop, one take fully autonomous — ChongZzZhang · 2026-10-07
- Tesla Powershare Home Backup goes live: 30-minute Supercharge adds ~2 days of whole-home power — kleffew94 · 2026-10-07
- Chinese team creates light-activated hydrogel that evolves with living tissue — yogthos · 2026-10-07
- Scoble visits a quick-turn Berkeley machine shop that robot prototype builders rely on — Scobleizer · 2026-10-07
- GroundedSLAM debuts, decisively beating all methods on Meta's egocentric SLAM benchmark — Scobleizer · 2026-10-07
- The ceiling for ambient, audio-only compute is extremely high: collapsing a whole workday into one thread — curious_vii · 2026-10-07