Search papers, labs, and topics across Lattice.
4
0
9
11
Achieve SOTA 3D scene reconstruction from collaborative driving views without calibration by treating multiple vehicles as a single, unstructured multi-camera system.
Finally, a way to train LLM agents to reason step-by-step without needing humans to check every intermediate thought.
Visual RL agents can recover near-perfect performance even under severe, dynamically changing visual corruptions by learning to disentangle task-relevant foreground from perturbation artifacts.
On-device LLM inference gets a massive speed and energy boost by adaptively streaming only the most expensive parts of the KV cache from the cloud.
