Search papers, labs, and topics across Lattice.
3
0
5
6
GS-Agent transforms natural language into intricate 4D worlds, showcasing a new era of automated creative content generation that rivals traditional manual methods.
Ditch the action tokens: representing robot actions as interpretable, pixel-grounded "action images" lets your video backbone act as a zero-shot policy.
LLMs can now generate complex, physically plausible 3D scenes for robotics simulation by iteratively proposing assets and refining arrangements based on physics engine feedback.
