Search papers, labs, and topics across Lattice.
5
0
8
3
DRIFT achieves near real-time trajectory planning with 89.6 PDMS and 90.4 EPDMS by efficiently aggregating multiple driving behavior proposals without requiring extensive quality labels.
LLM-generated bug reports often hinge on implicit assumptions, and this framework reveals how to validate their correctness through a novel witness-generation approach.
Autonomous vehicles can now plan trajectories 10x faster without sacrificing performance, thanks to a novel architecture that learns complex driving behaviors in latent space during training.
LLMs can now predict where drivers look with uncanny human-like accuracy, thanks to a new dataset and architecture that grounds attention in objects, not just scenes.
Time-to-collision metrics miss critical collision risk information, but a new 2D acceleration-based metric anticipates collisions far better.
