Jitendra Malik pushes back on Isola: LLMs can't handle high-frequency robot control

sainingxie · x · 2026-09-08

Jitendra Malik disagrees with Phillip Isola on LLMs for robot control: locomotion needs high-frequency policies dealing with forces and contacts. He challenges Isola to implement quadruped locomotion policies (RSS 2021/CoRL 2022) in an LLM, arguing quasi-static manipulation ≠ dexterity; LLMs can do high-level planning but that's not the hard part. The linked CoRL 2022 Best Systems Paper is an end-to-end egocentric-vision quadruped locomotion policy (single front depth camera, sim-trained, zero fine-tuning transfer) crossing stairs, gaps and stepping stones.

Related event: Robotics Legend Malik Pushes Back on LLM-Driven Robot Control(2 posts)→

Original post →

More from Embodied

Embodied channel →