DriveSpatial benchmark shows the best of 15 VLMs trails humans by 28.4 points on spatiotemporal driving tasks, with cognitive scene construction as the main failure mode.
Talk2car: Taking control of your self-driving car
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A graph-grounded Combined Road Substrate framework generates traceable QA pairs from road maps to improve small VLMs on compositional road reasoning tasks.
citing papers explorer
-
DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
DriveSpatial benchmark shows the best of 15 VLMs trails humans by 28.4 points on spatiotemporal driving tasks, with cognitive scene construction as the main failure mode.
-
Bridging Structure and Language: Graph-Based Visual Reasoning for Autonomous Road Understanding
A graph-grounded Combined Road Substrate framework generates traceable QA pairs from road maps to improve small VLMs on compositional road reasoning tasks.