VLA Insiders: Fast Policies Are 90% About Skipping Teleop Data — Kinematics Helps Too
andrew_n_carr · x · 2026-10-28
VLA researcher hanazhang argues the 'trick' to fast vision-language-action policies is 90% just not using teleop data; Andrew Carr adds that kinematics solves this too — implying efficient robot policies don't hinge on massive human teleoperation datasets. A terse but substantive exchange from robotics practitioners on training fast manipulation policies.
More from Embodied
- Foundry Robotics raises $100M Series A to build 130,000 sq ft factory in Emeryville, California — ishabytes · 2026-10-29
- Sony launches ELF-MN1, a 6-inch glasses-free spatial display that puts VRChat avatars on your desk — TinfoilTricorn · 2026-10-29
- NVIDIA's Metatron lets coding agents drive humanoid whole-body motion via a goal interface — carlosdponx · 2026-10-29
- StackChan Desk Robot Runs Grok + Hermes Agent, Lights Sync With Mood — alexcovo_eth · 2026-10-29
- Purdue's GPS-free drone tracks runners through forests; Rachel Thomas asks if it should exist — mmitchell_ai · 2026-10-29
- Insta360 X6 Spatial Capture Turns a 360° Walk Into an Explorable Gaussian Splat Scene — Aiden_Tech_Ai · 2026-10-28