Search papers, labs, and topics across Lattice.
2
0
5
Jointly modeling 3D geometry and relighting in a diffusion framework unlocks physically plausible single-image relighting that surpasses previous pipeline-based or geometry-agnostic approaches.
By explicitly modeling spatial interaction and manipulation intent, AIM achieves a 94% success rate on RoboTwin 2.0, suggesting that robot control can be drastically improved by explicitly reasoning about *where* to interact, not just *how* scenes evolve.
