Search papers, labs, and topics across Lattice.
3
0
5
Training with local visual cues can dramatically enhance MLLMs' ability to extract fine-grained visual details without altering their inference interface.
Time-to-collision metrics miss critical collision risk information, but a new 2D acceleration-based metric anticipates collisions far better.
LLMs can now handle autonomous driving tasks with greater precision and efficiency thanks to DriveCode, which replaces discrete number tokens with continuous embeddings.
