Search papers, labs, and topics across Lattice.
3
0
5
0
Cosmos 3 sets a new benchmark for omnimodal models, outperforming existing state-of-the-art in both Text-to-Image and Image-to-Video tasks.
Skill-based agents, designed for modularity and scalability, are shockingly vulnerable: a single compromised skill can turn the entire system into a weapon.
Precisely manipulate fragile objects in-hand without tactile feedback using a rigidity-based force planning approach that converts force trajectories into joint movements.
