@DoubleHan07i
iAccount based inHong Kong!
About this account
- Account based in
- Hong Kong
- Connected via
- China App Store
! X says this location may be affected by a proxy or VPN.
Account-level information from X, not a live location or the device used for a specific post.
PhD student in robotics @Stanford | Ham radio (BI1NWO; AI6OT) | Prev @Tsinghua_Uni
Palo Alto, CA
Joined October 2013
- Tweets131
- Following243
- Followers439
- Likes747
Pinned Tweet
Collecting manipulation data with DexUMI. Let’s scale up together! 📈
Big shoutout to my amazing project co-lead Mengda @mengdaxu__ , who brought full stack experience, strong system design skills, and unique insight to make this possible! 🙌
Can we collect robot dexterous hand data directly with human hand?
Introducing DexUMI:
0 teleoperation and 0 re-targeting dexterous hand data collection system → autonomously complete precise, long-horizon and contact-rich tasks
Project Page: dex-umi.github.io
Transformer Transformer will be presented at #CoRL2026 🚀 See y'all in Austin!
Website: transformer-transformer.gith…
Video: youtube.com/watch?v=TTyjvPVF…
Paper: transformer-transformer.gith…
Han Zhang retweeted
When a robot learns a new behavior, what keeps it from forgetting the ones it already knows?
Prior work, especially on VLAs, shows that rehearsing past experiences can enable strong continual learning. But why does rehearsal work so well, and when does it fail?
We find that a small but ✨special subset✨ of rehearsed data largely determines whether old behaviors are retained or forgotten. We call these examples Memory Anchors. ⚓
Withholding just the top 10% of Memory Anchors from rehearsal increases forgetting by up to 4.5x. Increasing their presence, meanwhile, reduces task forgetting and enables a real robot to learn challenging task sequences.
Website: robot-adaptation.github.io/M…
Paper: arxiv.org/abs/2608.26545
Curious? Read on! 🧵👇 (1/9)
Han Zhang retweeted
Introducing ACT-2 Preview
The first robotics model to unify broad generalization with high reliability. A single fine-tuning example can teach Memo a new behavior that generalizes.
Zero shot, real unseen homes, 99% success rate.
Han Zhang retweeted
Long horizon bimanual mobile manipulation requires reasoning in many coordinate frames: base, L/R hands, etc. In which frame would policy work best?
It really depends, so don’t pick. Mixture of Frames Policy: denoise in multiple frame in parallel.
🌐mofpo.github.io (1/9)
Han Zhang retweeted
LLMs learn new tasks in-context. It’s time robots do the same 🤖
Introducing Behavior Prompting: human shows one demo, and the robot adapts immediately. Turns out robot demos are great in-context prompts!
And the magic: no paired human2robot data needed
behavior-prompting.github.io (1/8)
Han Zhang retweeted
Manipulation happens through surfaces. To understand contact-rich dexterous interaction, motion alone is not enough. We also need to know surface properties and contact state.
Excited to share ART-Glove, an articulated tactile glove that captures contact-grounded information while preserving human dexterity. It provides:
- Known Geometry: 16 rigid functional surfaces
- Surface Motion: 22 anatomically aligned joints
- Tactile Contact: 2048 piezoresistive taxels
Huge thanks to my advisor Ding @zhao__ding, and to Yuxiang @yxyang1995, Maria @bauzavillalonga, Marissa, and Peide @peide_huang for the valuable advice and discussions.
Paper: arxiv.org/abs/2606.16370
Han Zhang retweeted
🤖Low-data post-training can teach a VLA policy a new robot skill. But it also makes it too attached to the training demos.
We call this lock-in🔒: the policy can execute the post-training task, yet fails to respond to seemingly obvious prompt changes.
DeLock preserves steerability using only the policy’s own pretrained knowledge. No extra supervision needed!🚀🚀🚀
#Robotics #AI #EmbodiedAI #VLA
Han Zhang retweeted
Can we learn whole-body mobile manipulation directly from human demonstrations?
Introducing Whole-Body Mobile Manipulation Interface (HoMMI)
Egocentric + UMI, 0 teleop -> bimanual & whole-body manipulation, long-horizon navigation, active perception
hommi-robot.github.io
Han Zhang retweeted
Introducing ACT-1: The frontier robot AI behind Memo.
ACT-1 enables Memo to perform: 🎭
⏰ Lengthy tasks like cleaning up after your dinner
🦾 Dexterous tasks such as folding socks
☕ Daily delights like making an espresso
How does it work? 🧵
Han Zhang retweeted
mm level precision beyond actuator limits, so much torque that you need to manage thermals. Owning the whole stack from HW to AI is the only way 🦾
Han Zhang retweeted
Toddy enjoyed his time in Seoul — his first big trip away from home!😆 He rolled around on wheels, showed off his pull-up skills (Cr: @li_yitang), spoke in the spotlight as a 1.5-year-old, and presented at the poster session.
ToddlerBot is accepted to CoRL, and we will bring Toddy (2.0 version) to Seoul for a trip. Come and say hi to Toddy if you're around😁! Our arxiv paper is also updated with more technical details in the appendix: arxiv.org/abs/2502.00893
Han Zhang retweeted
How do we unlock the full dexterity of robot hands with data, even beyond what teleoperation can achieve?
DEXOP captures natural human manipulation with full-hand tactile & proprio sensing, plus direct force feedback to users, without needing a robot👉dex-op.github.io/
Han Zhang retweeted
Collecting dexterous humanoid robot data is difficult to scale. That's why @mengdaxu__ and @DoubleHan07 built DexUMI: a tool for demonstrating how to control a dexterous robot hand, which allows you to quickly collect task data.
Co-hosted by @micoolcho and @chris_j_paxton
This video is larger than Cloudflare's 512 MB cache, so it can't be played through. More donations are needed to cover a larger cache. Donate
Han Zhang retweeted
Human hands are incredibly capable manipulators, but it's hard to get high-quality robot data for learning policies. DexUMI provides a solution: a tool by which you can naturally "puppet" a dexterous hand with your own, in order to learn skills that directly transfer to a robot. Learn more ->
Collecting dexterous humanoid robot data is difficult to scale. That's why @mengdaxu__ and @DoubleHan07 built DexUMI: a tool for demonstrating how to control a dexterous robot hand, which allows you to quickly collect task data.
Co-hosted by @micoolcho and @chris_j_paxton
This video is larger than Cloudflare's 512 MB cache, so it can't be played through. More donations are needed to cover a larger cache. Donate
Han Zhang retweeted
Full episode dropping soon!
Geeking out with @mengdaxu__ @DoubleHan07 on DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation dex-umi.github.io
Co-hosted by @micoolcho @chris_j_paxton
Excited to present DOGlove at #RSS2025 today!
We’ve brought the glove with us, come by and try it out!
📌 Poster: All day at #54 (Associates Park)
🎤 Spotlight talk: 2:00–3:00pm (Bovard Auditorium)
Han Zhang retweeted
Our lab at Stanford usually do research in AI & robotics, but very occasionally we indulge in being functional alcoholics -- Recently we hosted a lab cocktail night, and created drinks with research-related puns like 'reviewer#2' and 'make 6 figures', sharing the full recipes here in case you are looking for a fun summer drink:
HADES-ICM (SO-125) 🛰️FM repeater is now on!
First QSO with JK2XXK @kikori1906 ! Nice QSO!
#HamRadio #amsat
@AmsatSpain