Zhenyang Chen

@DanielZhenyang

Robotics Ph.D@GT, Research@NV GEAR

Joined December 2021

480

Following

315

Followers

Replies Reposts Media

Zhenyang Chen
@DanielZhenyang
Sep 6
WARP is accepted to #CoRL2026 ! See you guys in Austin this November!
Zhenyang Chen
@DanielZhenyang
Aug 19
Human data is the cheapest source of whole-body mobile manipulation demos. Turning it into robot data is the hard part.🤖 WARP retargets OFFLINE human motion into replayable robot actions in closed form — precise, consistent, faithful to whole-body intent. 🌍
00:00
2
Zhenyang Chen
@DanielZhenyang
Aug 20
Thanks Guangqi!
Guangqi Jiang
@LuccaChiang
Aug 20
Can’t agree more! If you think human-to-robot gap is too large, then use human data to get robot data. Awesome @DanielZhenyang
Zhenyang Chen
@DanielZhenyang
Aug 20
Flow is a good representation to support embodiment transfer and will be useful for ICL prompting
Hongyu Li
@Hongyu_Lii
Aug 20
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
00:00
1
Zhenyang Chen
@DanielZhenyang
Aug 19
Human data is the cheapest source of whole-body mobile manipulation demos. Turning it into robot data is the hard part.🤖 WARP retargets OFFLINE human motion into replayable robot actions in closed form — precise, consistent, faithful to whole-body intent. 🌍
00:00
9
Zhenyang Chen
@DanielZhenyang
Aug 10
Great work by @DynaRobotics! Human video/data is the future, but actually getting 1M *USABLE* data is not trivial.
Dyna Robotics
@DynaRobotics
Aug 10
Today we are introducing Dyna-2, a world-action model pre-trained on one million hours of human video. At this scale, for the first time, we discovered several new scaling laws: • world-action models exhibit scaling law on human data across four orders of magnitude, from 1000
00:00
1