Search papers, labs, and topics across Lattice.
3
0
5
8
Forget static imitation learning: LaST-R1 unlocks near-perfect robotic manipulation (99.8% success) by adaptively reasoning about physical dynamics *before* acting, then refining with RL.
Achieve 9x lower trajectory error and 3x better FID in motion generation by using a diffusion-based discrete motion tokenizer that elegantly handles both semantic and kinematic constraints.
Visual grounding in VLAs weakens in deeper layers, but injecting multi-level visual features and pruning irrelevant tokens can boost performance by 9% in simulation and 7.5% in the real world.
