Search papers, labs, and topics across Lattice.
3
0
6
4
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.
Current MLLMs can't find the lies hidden in their long image captions, struggling to pinpoint specific hallucinated words within detailed narratives.
You can now get state-of-the-art hepatocellular carcinoma diagnosis and captioning from whole slide images using a new MLLM with a topology-aware attention mechanism.
