Juncheng Mu

I am a first-year Ph.D. student co-advised by Prof. Jiangmiao Pang at Shanghai AI Laboratory and Prof. Huazhe Xu at Tsinghua University.

[Juncheng Mu @Juncheng_Mu]

Can robots learn a bimanual dexterous skill from just one video?
DexImit makes it possible 🏄‍♂️ — automatically converting human videos into physically plausible training data for bimanual manipulation, either from text2video models or real-world recordings.

[Lucy Shi @lucy_x_shi]

1/ We just released π0.7 — a steerable generalist robot model with emergent capabilities.
I want to share a bit of the backstory, because π0.7 taught me something surprising about where robot learning is heading. A thread on bittersweet lessons 🧵

[Generalist @GeneralistAI]

Introducing GEN-1.

Our latest milestone in scaling robot learning.

We believe it to be the first general-purpose AI model to master simple physical tasks.

99% success rates, 3x faster speeds, adapts in real time to unexpected scenarios, w/ only 1 hour of robot data.

More🧵👇

[Juncheng Mu @Juncheng_Mu]

@ju_yuanchen Thanks Yuanchen — really appreciate it! Glad you found it interesting 🥳

[Juncheng Mu @Juncheng_Mu]

@andrew_n_carr Thanks — really appreciate it !!!

[Juncheng Mu @Juncheng_Mu]

Can robots learn a bimanual dexterous skill from just one video?
DexImit makes it possible 🏄‍♂️ — automatically converting human videos into physically plausible training data for bimanual manipulation, either from text2video models or real-world recordings.

[Juncheng Mu @Juncheng_Mu]

Huge thanks to my amazing collaborators! 🔥
@SizheYang111 @still_wtm @EvenEveno

Big shoutout to our best advisors: @Boyiliee @HarryXu12 @pangjiangmiao 🙌

[Juncheng Mu @Juncheng_Mu]

Learn more and explore our project 👇
📜 Paper: https://t.co/93RDMqZEFZ
🌐 Project Page: https://t.co/MXTpLOkKfy

[Juncheng Mu @Juncheng_Mu]

📊 Result
We evaluate DexImit along two dimensions:
input video quality and task difficulty.
DexImit can generate diverse short-horizon data using only a text2video model. For long-horizon tasks such as beverage making and apple cutting, higher-quality videos are necessary.