Search papers, labs, and topics across Lattice.
2
0
6
R2RDreamer achieves superior spatial generalization for 2D manipulation policies by transforming 3D action-observation pairs into coherent 2D video data, all while minimizing the sim-to-real gap.
LLMs can beat state-of-the-art tensor compilers on individual subgraphs, but struggle with consistency, revealing a path to unlock their full potential through targeted training.
