Search papers, labs, and topics across Lattice.
5
4
6
14
Current action-conditioned world models fail to reliably follow diverse off-expert actions, risking the effectiveness of policy learning in real-world applications.
Future scene geometry, not pixel data, is the key to unlocking superior driving policies in autonomous systems.
The data pyramid framework reveals how the interplay of diverse data sources can unlock new capabilities in embodied agents, highlighting critical gaps in current methodologies.
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.
Diffusion models can now achieve state-of-the-art performance in vision-language-action robotics tasks, rivaling and surpassing discrete and continuous action policies.
