Search papers, labs, and topics across Lattice.
3
0
3
A massive 2.6M-scene benchmark and a novel generative model finally unlock robust dexterous grasping in cluttered environments, outperforming prior methods without post-optimization.
A novel tri-stream transformer architecture unlocks synergistic control by enabling a dedicated action expert to selectively fuse semantic and dynamics information from independent VLM and World Model streams.
ACE-Data-0 reveals that existing models struggle significantly with complex interactions, exposing critical gaps in embodied AI performance.
