M.S. at Cornell University researching in AI and robotics
Joined February 2026
- Tweets15
- Following45
- Followers36
- Likes13
Maximus Pace retweeted
Setting up new tasks with Play2Perfect is super easy!
Here are 2 additional envs + assets that Opus 5 generated from SCRATCH. The same RL training code works without any modifications. Go play with the awesome demo @tylerlum23 created :)
play2perfect.github.io/
Excited to share that Play2Perfect was accepted to #CoRL2026!
We also added an interactive demo to our project website 🖥️
Watch Play2Perfect perform precise, contact-rich assembly in MuJoCo, right in your browser!
Zero-shot sim-to-sim transfer from Isaac Sim to MuJoCo.
Teaching a robot shouldn't require humans to act like robots.
Human demonstrations contain valuable signal for robot manipulation, but they aren’t directly transferable to robots.
X-Diffusion learns from noisy human demonstrations while staying within the robot’s capabilities.
Ambient Diffusion is useful for learning from not just human videos but also suboptimal data. Check out this closely related robotics work from the authors of Ambient Diffusion! 👇
nitter.cf/adamwei_/status/206767…
🤖 We introduce Ambient Diffusion Policy, a simple and principled method for training policies with suboptimal data in robotics.
Suboptimal data is everywhere in robotics…
❌ Data filtering is wasteful
❌ Co-training learns both good and bad features
✅ Ambient Diffusion Policy selectively learns useful features via noise-dependent data usage
👇🧵(1/5)
Huge thanks to my collaborators @prithwish_dan (co-lead), @TritiumAc, Atiksh Bhardwaj, Audrey Du, and Edward Duan, and to @weichiuma and @kushalk_ for their guidance and support.
We recently presented at ICRA 2026!
Check out our project website + code: portal-cornell.github.io/X-D…
Human videos 👩 are noisy and break standard imitation learning.
X-Diffusion selectively trains on noisy human data to learn skills while maintaining robot feasibility 🦾
Come check out our poster at #ICRA26
Interactive Session 6 − ThI2I Hall C - 3-4:30 p.m.
With X-Diffusion, humans don't have to act like robots to provide training data.
portal-cornell.github.io/X-D…