Being-M0.7: A Latent World-Action Model for Humanoid Robots
Humanoid loco-manipulation requires coordinated locomotion and manipulation informed by future scene evolution and whole-body motion, yet learning these capabilities is constrained by scarce robot demonstrations. Human video and motion datasets offer scalable supervision, but many contain only video or motion rather th...
Jun-Peng Yue, Bo-Yuan Li, Yuxuan Wang et al.
· 0 citations