I decided to review and explicitly post about the limitations of all my previous papers because I believe this is the fundamental driving force behind research, especially in this era of PRs and bubbles.
🎯Demo is on the shelf!
wuyan01.github.io/ADAPT-project/…
Try out the language-conditioned end-to-end humanoid control in your browser!
And our paper:
📄 ADAPT: Agile Diffusion Action Priors for Robust and Steerable Online Text-Driven Humanoid Control
arxiv.org/abs/2609.00677
Dominant text-to-motion pipelines generate kinematic motions for a separate tracker.
Instead, in our @corl_conf work ADAPT, we solve humanoid language control end-to-end closed-loop, where the robot must continuously respond to changing commands.
🌐Page: wuyan01.github.io/ADAPT-project/
Dominant text-to-motion pipelines generate kinematic motions for a separate tracker.
Instead, in our @corl_conf work ADAPT, we solve humanoid language control end-to-end closed-loop, where the robot must continuously respond to changing commands.
🌐Page: wuyan01.github.io/ADAPT-project/
Last month, I wrapped up my internship with the Gemini Robotics team @GoogleDeepMind.
Being part of it was a dream come true, and I’m grateful to contribute alongside such amazing people.
I’m proud of what we’ve accomplished together and can’t wait to share more about it soon!
Great to see people are already getting impressive results from our terrain-aware human reference motions!
We are also bringing EgoHTR to @corl_conf! Can’t wait to see more being unlocked!
🌐 Project Page: egohtr.github.io
orcs v0.1.1 is out 🚀 github.com/lok-i/orcs
🧗 perceptive whole-body locomotion task on EgoHTR: one adapted policy for rocky climbs and window crossing
🛠️ agentic UMR retargeting skill: leave frame-wise notes; your agent revises the reference
