Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
0
Current vision-language models can identify context in driving videos but fail to accurately assign fault in accidents, revealing a critical gap in autonomous driving AI capabilities.
STRIVE-D achieves up to 84% relative improvement in video retrieval accuracy by intelligently adapting query rules to real-world driving data.
SliceScorer reveals critical coverage gaps in driving VLMs that traditional methods overlook, enhancing safety validation in real-world applications.
