
Ph.D. @CarnegieMellon @CMU_ECE @CMU_Robotics @LeCARLab | Intern @AIatMeta @Meta | @Tsinghua_Uni alum | Exploring the intersections of Learning & Control
Pittsburgh, PA
Joined July 2022
- Tweets132
- Following362
- Followers1.1K
- Likes390
Pinned Tweet
Generative models (diffusion/flow) are taking over robotics 🤖. But do we really need to model the full action distribution to control a robot?
We suspected the success of Generative Control Policies (GCPs) might be "Much Ado About Noising."
We rigorously tested the myths. 🧵👇
Common belief: Robot policies need continuous action heads; discrete actions are 𝐥𝐞𝐬𝐬 𝐧𝐚𝐭𝐢𝐯𝐞 𝐚𝐧𝐝 𝐥𝐞𝐬𝐬 𝐩𝐫𝐞𝐜𝐢𝐬𝐞.
❗We find policies w/ the simplest discrete representations 𝐦𝐚𝐭𝐜𝐡 𝐨𝐫 𝐛𝐞𝐚𝐭 continuous ones—in sim & real, in single-step & diffusion/flow settings.
Here's why 🧵
Chaoyi Pan 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
Moving from scaling to research: How do we train VLAs efficiently with limited data?
Haoyang’s new project shows why object-centric co-training is key. Plus, their repo is highly optimized for multi-GPU training. Great resource!
🕸️ SPIDER is now OPEN SOURCE! 🕸️
The first framework for both humanoids and dexterous hands retargeting.
✅ Physics-Based: No artifacts or ghosting.
✅ General: Supports 9+ robots (G1, H1, Allegro, etc.)
📦 Repo: github.com/facebookresearch/… 📓 Tutorial: github.com/facebookresearch/…
Action Chunking is standard in robot learning, but we finally have a formal "why."
🔑 Key Insight: AC leverages the open-loop stability of the system. In stable dynamics (e.g., end-effector control), AC yields horizon-free imitation guarantees.
Great work by @ThomasTCKZhang
🤖🤖Very excited to finally share our new work “Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control”
Everyone in robotics does action-chunking, but why does it actually work?🤔🤔And, what can theory tell us about the properties of data we should be collecting for robotic behavior cloning? 🧵1/N
Chaoyi Pan retweeted
🤖🤖Very excited to finally share our new work “Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control”
Everyone in robotics does action-chunking, but why does it actually work?🤔🤔And, what can theory tell us about the properties of data we should be collecting for robotic behavior cloning? 🧵1/N
Start treating your policy architecture as an iterative solver, not just a distribution fitter ;)
📄 Paper: arxiv.org/abs/2512.01809
💻 Code: github.com/simchowitzlabpubl…
🌐 Website: simchowitzlabpublic.github.i…
If you see @max_simchowitz @GuanyaShi @nmboffi @guannanqu at NeurIPS, feel free to chat with them about our work!
Work led by me w/ Giri Anantharaman, Nai-Chieh Huang, Claire Jin, Daniel Pfrommer, Chenyang Yuan, Frank Permenter, @guannanqu , @nmboffi, @GuanyaShi, @max_simchowitz
1
21
2,696
Chaoyi Pan retweeted
🧐🧐 Why do we pretrain LLMs with log likelihood? Why does action chunking work so well in robotics? Why is EMA so ubiquitous? And could their be a mathematical basis for Moravec’s paradox? 🤖🤖
Come check out our NeurIPS 2025 Tutorial “Foundations of Imitation Learning” with @canondetortugas and Adam Block, Tuesday 130-4pm, to find out! (🧵for details)
Another big leap for learning from humans! Amazing to see human→robot learning done with just Aria 2 glasses from @irmakkguzey. 2026 is going the year of 3D hardware + foundation models + policy learning coming together. 🤖🪞
A great, down-to-earth work on tackling a locomanipulation sim2real problem. (Note to self: find 64 spare GPUs 😂) Amazing results!
Zero teleoperation. Zero real-world data. ➔
Autonomous humanoid loco-manipulation in reality.
Introducing VIRAL: Visual Sim-to-Real at Scale.
We achieved 54 autonomous cycles (walk, stand, place, pick, turn) using a simple recipe:
1. RL
2. Simulation
3. GPUs
Website: viral-humanoid.github.io/
Arxiv: arxiv.org/abs/2511.15200
Deep dive with me: 🧵
🕸️ Introducing SPIDER — Scalable Physics-Informed Dexterous Retargeting!
A dynamically feasible, cross-embodiment retargeting framework for BOTH humanoids 🤖 and dexterous hands ✋.
From human motion → sim → real robots, at scale.
🔗 Website: jc-bao.github.io/spider-proj…
🧵 1/n
🧵 5/n
SPIDER is also a data engine:
We vary object size, states, and scenes to produce massive, physics-valid training data.
🧵 6/n
For more details, please refer to:
🔗 Website: jc-bao.github.io/spider-proj…
📄 Paper: arxiv.org/abs/2511.09484
Huge thanks to the team at FAIR + CMU!
We hope SPIDER pushes scalable, physics-grounded retargeting forward 🕷️🤖










