Search papers, labs, and topics across Lattice.
Shanghai AI Lab, Fudan University
3
0
4
3
Forget painstakingly collecting real-world data for deformable object manipulation: SIM1 achieves equivalent policy performance with 15x less data by grounding simulations in the physical world.
Humanoid robots can now perform complex loco-manipulation tasks with more natural and stable movements by decomposing control into VLM-orchestrated expert policies trained with human motion priors.
By combining video generation and vision-language models, EmboAlign achieves a 43% boost in real-world robot manipulation success without any task-specific training.
