Lai Wei
28
posts
@laiiwei
La Jolla, CA
Joined February 2025
Pinned
We just open-sourced the fingertip design files for our latest DexHand project: 👉x.com/jianglong_ye/s…! 🎉 Check out our new video to see the robot hand pick up a coin🪙, battery🔋, and nut🔩 with a simple, near-zero-cost 3D printing fingertip. You can have your own one
00:00
00:37
How do we make dexterous hands handle both power and precision tasks with ease? 🫳👌🫰 We introduce Power to Precision (💪➡️🎯), our new paper that optimizes both control and fingertip geometry to unlock robust manipulation from power grasp to fine-grained manipulations. With
This is a really cool paper. A shared latent action space across multiple dexterous hands, plus better transfer to unseen hand-task combinations, is exactly the kind of abstraction we need for scalable robot learning. Congrats to
@LuccaChiang!
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
Very exciting work!🤩🤩🤩
Can we bridge the Sim-to-Real gap in complex manipulation without explicit system ID? 🤖 Presenting Contact-Aware Neural Dynamics — a diffusion-based framework that grounds simulation with real-world touch. Implicit Alignment: No tedious parameter tuning. Tactile-Driven:
00:00
Checkout our new fancy demo about In-N-On 🙌👇
How do you teach a robot to do something it has never seen before? 🤖 With human data. Our new Human0 model is co-trained on human and humanoid data. It allows the robot to understand a novel language command and execute it perfectly in the wild without prior practice.
00:00
Proud to share our latest work In-N-On, with my amazing labmates! Check out the first-author thread below 👇
A large human behavior model. Introducing In-N-On, our latest findings in scaling egocentric data for humanoids. 1. Pre-training and post-training with human data 2. 1,000+ hours of in-the-wild data and 20+ hours of on-task data with accurate action labels Website:
00:00