New Video from Generalist showcasing the same model working with many different kinds of "hands"
Summary
A new video from Generalist demonstrates their AI model working with various types of hands, highlighting its versatility.
Similar Articles
@micoolcho: New dexterous hands from Xynova #icra2026
Xynova announces new dexterous hands, showcased at ICRA 2026.
@LinusEkenstam: Humanoids are moving beyond basic grasping into dexterous manipulation. These WUJI demos are seriously impressive. Move…
WUJI showcases its Hand 2 humanoid dexterous hand, which mirrors human hand movements via camera tracking or a glove and learns skills like pen spinning through reinforcement learning in mjlab simulation before transferring them to the real world. The wuji-mjlab code is released as open source for developers and researchers.
@RemiCadene: Super cool work congrats!
Researchers introduce the Unified Hand Action Space (UHAS), a representation enabling a single policy to control robotic hands with different kinematic structures and numbers of fingers, advancing cross-embodiment dexterous manipulation.
I Saw the Future of AI in a Robot That Can Learn on the Spot
A startup called Generalist AI demonstrates robots that can quickly learn tasks from instructional videos and improvise solutions, drawing parallels to GPT-3's adaptability and advancing physical AI capabilities.
@Knesix: Whoa. This looks amazing!
WUJI demonstrated its 20-joint WUJI Hand 2 robotic hand spinning a pen, trained in a physics simulator and deployed sim-to-real, showcased around IROS 2026.