InternW0-Δ open-sources code, weights and 20K+ hours of robot data
arankomatsuzaki · x · 2026-09-28
Ara Komatsuzaki introduces InternW0-Δ, which jointly learns visual dynamics and robot actions, outperforming prior methods. The project is 100% open-sourced including code, weights and data — the dataset mixes robot, UMI and egocentric data totaling 20K+ hours, the largest of its kind.
More from Embodied
- AnyMo, a Setup-Agnostic IMU Human Motion Model, Accepted at NeurIPS 2026 — flosalim · 2026-09-28
- Leslie Kaelbling on Why Astra Excels at Robotics—and Why It Isn't Solved Yet — shaohua0116 · 2026-09-28
- Meta's official XR FOV Simulator used for accurate Quest 3 vs VR glasses FOV comparison — ZeroStateReflex · 2026-09-28
- Robotics researcher argues proprioception, not vision, is the real bottleneck for grasping — arankomatsuzaki · 2026-09-28
- Dev builds own Playdate visual simulator with Figma-to-dither workflow — eschadiol · 2026-09-28
- IMLE-VLA replaces flow matching with single-step cIMLE, 3.67x faster robot actions at 55Hz — petitegeek · 2026-09-28