Bench2ADVLM is a closed-loop evaluation framework that tests vision-language models for autonomous driving in simulation and on real vehicles, and reports that current models perform poorly under interactive conditions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bench2ADVLM: A Closed-Loop Benchmark for Vision-language Models in Autonomous Driving
Bench2ADVLM is a closed-loop evaluation framework that tests vision-language models for autonomous driving in simulation and on real vehicles, and reports that current models perform poorly under interactive conditions.