Search papers, labs, and topics across Lattice.
3
0
4
Cloning synthetic demonstrations alone caps performance, but combining it with reinforcement learning unlocks superior real-world manipulation capabilities.
Achieving state-of-the-art performance in 3D motion forecasting, MolmoMotion reveals that language instructions can significantly enhance trajectory predictions across various object categories and motion types.
Forget expensive real-world data collection: a massive, diverse synthetic dataset enables surprisingly effective zero-shot transfer for robotic manipulation.
