SEAL extends a V2X vision-language driving model with GPT-4o-generated snow/fog data, gated scenario attention, and contrastive learning, reporting improved planning accuracy on synthetic long-tail tests.
Spatialvlm:Endowingvision-languagemodelswithspatialreasoning capabilities, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
SEAL: Vision-Language Model-Based Safe End-to-End Cooperative Autonomous Driving with Adaptive Long-Tail Modeling
SEAL extends a V2X vision-language driving model with GPT-4o-generated snow/fog data, gated scenario attention, and contrastive learning, reporting improved planning accuracy on synthetic long-tail tests.