One 8B multimodal model trained jointly on six driving datasets outperforms individual specialists on average and transfers zero-shot to three unseen driving benchmarks.
Maplm: A real-world large-scale vision-language benchmark for map and traffic scene under- standing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
RoboTron-Drive: All-in-One Large Multimodal Model for Autonomous Driving
One 8B multimodal model trained jointly on six driving datasets outperforms individual specialists on average and transfers zero-shot to three unseen driving benchmarks.