Hongyu Li(@Hongyu_Lii):What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7

Hongyu Li

@Hongyu_Lii

Robotics researcher at @NVIDIA. Ph.D. @BrownCSDept 🐻. Prev: @ColumbiaCompSci, @rai_inst, @AmazonScience, @Honda

Joined December 2018

1.1K Following 1.8K Followers

Hongyu Li@Hongyu_Lii

2026.08.20 21:52

What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7