Cheng Chi (@chichengcc) / X

Cheng Chi

472 posts

Cheng Chi

@chichengcc

Co-founder & CTO @sundayrobotics Prev 🤖 PhD @Stanford and @Columbia

Stanford, CA

Joined January 2016

Pinned
Cheng Chi
@chichengcc
Nov 19, 2025
From glove data to long-horizon, dexterous, precise and whole-body manipulation ⚙️ Details in this thread!
Tony Zhao
@tonyzzhao
Nov 19, 2025
Today, we present a step-change in robotic AI @sundayrobotics. Introducing ACT-1: A frontier robot foundation model trained on zero robot data. - Ultra long-horizon tasks - Zero-shot generalization - Advanced dexterity 🧵->
00:00
28K
Cheng Chi
@chichengcc
Feb 16, 2024
Can we collect robot data without any robots? Introducing Universal Manipulation Interface (UMI) An open-source $400 system from @Stanford designed to democratize robot data collection 0 teleop -> autonomously wash dishes (precise), toss (dynamic), and fold clothes (bimanual)
00:00
439K
Cheng Chi
@chichengcc
Mar 8, 2023
What if the form of visuomotor policy has been the bottleneck for robotic manipulation all along? Diffusion Policy achieves 46.9% improvement vs prior StoA on 11 tasks from 4 benchmarks + 4 real world tasks! (1/7) website : diffusion-policy.cs.columbia.edu paper: arxiv.org/abs/2303.04137
00:00
130K
Cheng Chi
@chichengcc
Feb 23, 2024
We made a step-by-step video tutorial for building the UMI gripper! Please leave comments on @YouTube if you have any question youtu.be/x3ko0v_xwpg
34K
Cheng Chi
@chichengcc
Mar 21, 2024
Weights drop ⚠️ We released our pre-trained model for the cup arrangement task trained on 1400 demos! We aim to enable anyone to deploy UMI on their robot to arrange any "espresso cup with saucer" they buy on Amazon. github.com/real-stanford/…
00:00
25K
Cheng Chi
@chichengcc
Nov 8, 2025
UMI-style data collection has a lot more potential for scaling compared to teleoperation. But getting it to work well involves so much effort. It is amazing to see how much thought Generalist has put into perfecting it - the robot moves so smoothly! I am curious to see if they
Generalist
@GeneralistAI
Nov 4, 2025
Introducing GEN-0, our latest 10B+ foundation model for robots ⏱️ built on Harmonic Reasoning, new architecture that can think & act seamlessly 📈 strong scaling laws: more pretraining & model size = better 🌍 unprecedented corpus of 270,000+ hrs of dexterous data Read more 👇
00:00
19K
Cheng Chi
@chichengcc
Nov 6, 2025
20 months since... Can we come up with a new handshake? @tonyzzhao
Cheng Chi
@chichengcc
Feb 16, 2024
Replying to @chichengcc
It was a blast working with @tonyzzhao and @zipengfu in the Stanford Robotic Center! 8/9
00:00
33K
Cheng Chi
@chichengcc
Mar 21, 2024
UMI x ARX @YihuaiGao just got our in-the-wild cup policy working with ARX5 @ARX_Zhang ! We are still tuning the controller and latency matching for smoother tracking. Lot’s of potential in these low-cost lightweight arms!
00:00
12K
Cheng Chi
@chichengcc
Feb 16, 2024
Replying to @chichengcc
With UMI, you can go to any home, any restaurant and start data collection within 2 minutes. With a diverse in-the-wild cup manipulation dataset, we can train a diffusion policy that generalizes to the top of a water fountain – clearly unseen environments and objects. 2/9
00:00
12K
Cheng Chi
@chichengcc
Nov 5, 2025
Excited for the road ahead ❤️
Tony Zhao
@tonyzzhao
Nov 5, 2025
Looking back, it’s wild to see how much has changed. The work, the thinking, the pace. Grateful to work alongside you @chichengcc
21K
Cheng Chi
@chichengcc
Oct 15, 2025
It was incredible to witness Ruoshi went from 0 robotics experience to a paper plane folding robot in a month, building every bit of infra himself! If you want become the first-batch PhD student of a rising star AP with strong vision intuition, please reach out to Ruoshi!
Ruoshi Liu
@ruoshi_liu
Oct 15, 2025
Everyone says they want general-purpose robots. We actually mean it — and we’ll make it weird, creative, and fun along the way 😎 Recruiting PhD students to work on Computer Vision and Robotics @umdcs for Fall 2026 in the beautiful city of Washington DC!
15K
Cheng Chi
@chichengcc
Jan 23, 2025
The mirror 🤯🤯🤯🤯
Kevin Zakka
@kevin_zakka
Jan 23, 2025
The UMI gripper is now officially in MuJoCo Menagerie, thanks to the amazing contribution of @omarrayyann!
00:00
5.5K
Cheng Chi
@chichengcc
Feb 16, 2024
Replying to @chichengcc
It was a blast working with @tonyzzhao and @zipengfu in the Stanford Robotic Center! 8/9
00:00
30K
Cheng Chi
@chichengcc
Jun 28, 2020
Replying to @mranti
因为这样观众就可以同时看到演员的脸和屏幕上显示的东西了。因此没隐私是feature不是bug