Search papers, labs, and topics across Lattice.
The University of Hong Kong
3
0
5
FlowR2A unifies dense reward supervision and dynamic proposal generation, achieving state-of-the-art multimodal driving planning performance.
A well-designed harness can unlock powerful embodied manipulation capabilities in compact models, achieving frontier performance with just 2K simulation trajectories.
Forget hand-crafted environments: ClawEnvKit lets you automatically generate diverse, verified environments for claw-like agents from natural language, slashing costs by 13,800x.
