NVIDIA's Jim Fan unveils VFlash: a System 1 vision model for Physical AI
andrew_n_carr · x · 2026-11-06
Jim Fan of NVIDIA introduces VFlash, billed as the arrival of "System One Vision Models" that parse the visual world in parallel at unmatched speeds for Physical AI.
Key insight: most embodied prediction tasks—object localization, robot trajectory planning, dense 3D motion—produce fixed-length float vectors (a bounding box is always 6 tokens, a 10-waypoint robot arm trajectory 54). VFlash exploits these known output shapes to parallelize prediction for major speed gains.
More from Embodied
- GPT-6 Astra tops a 16-benchmark robot index, yet went 0/11 on real plug insertions — AIFlow_ML · 2026-11-06
- Giving Claude a cutting-edge robot body just so it can spoon-feed me — repligate · 2026-11-06
- moonlake previews research on scaling robot learning with simulation in the RL era — du_yilun · 2026-11-06
- Nearly 100 testers praise Sphenomenon MR demo that turns a whole house into voxels — Scobleizer · 2026-11-06
- Spectral Skills lands on real robots: composing motion skills via energy functions — daibond_alpha · 2026-11-06
- Developer gives Claude Desktop a body and sensors via MCP and Raspberry Pi — jfrankie · 2026-11-06