Guangqi Jiang
287
posts
@LuccaChiang
San Diego, CA
Joined September 2023
Pinned
Ever want to have a single policy to control diverse robots as well as different dexterous hands, or to observe the emergent behavior under cross embodiment training? Introducing our #CVPR2026 paper XL-VLA, Cross-Hand Latent Representation for Vision-Language-Action Models.
00:00
Can’t agree more! If you think human-to-robot gap is too large, then use human data to get robot data. Awesome
@DanielZhenyang
Human data is the cheapest source of whole-body mobile manipulation demos. Turning it into robot data is the hard part.🤖 WARP retargets OFFLINE human motion into replayable robot actions in closed form — precise, consistent, faithful to whole-body intent. 🌍
00:00
I'm recently aware that one reason my hands are so powerful is that they have many highly sensitive contact/tactile sensors. And why VR-based teleoperation is so frustrating is that it does not provide me with feedback. Force is one of the point we human beat robots.
00:00
I did a lot data collection for imitation learning. Ususally we abandon failed trajectories since adding "low-quality" data to naive imitation could damage the model's final performance. However, I'm faithful that these kinds of data are still valuable. Thank you
@QuanquanPeng03
Children learn to walk by falling. Robots fail too—but we usually throw those failures away. Yet failed rollouts tell us something successful demonstrations cannot: what bad actions actually lead to. So, can robots learn from their failures too? Introducing FACT: Failure-Aware
00:00
This is super cheap. Code already open and give it a try.
🔥We’re open-sourcing Multi-Agent CAD, a text-to-CAD pipeline that generates 3D assets for about $0.15 each—at roughly 1/13 the cost of CAD Skills, with faster inference and higher accuracy 🚀 This project began when our lab recruited Guanxing for his CAD expertise 🛠️ to build
00:00