Search papers, labs, and topics across Lattice.
3
0
8
LUNA-AD achieves state-of-the-art performance in autonomous driving while cutting inference latency, revolutionizing how AI can operate in safety-critical environments.
You can get SOTA autonomous driving performance with a distilled, lightweight language model that also tells you how confident it is.
Online reinforcement fine-tuning can measurably improve the safety and efficiency of diffusion-based multi-agent driving planners, even when starting from strong pre-trained models.
