2 papers
cs.CV2026
MVPruner: Dynamic Token Pruning for Accelerating Multi-view Vision-Language Models in Autonomous Driving
Nan Yang, Zhanwen Liu, Linfeng Zhang +4
Vision-Language Models (VLMs) improve generalization and interpretability in autonomous driving but suffer from efficiency issues due to long visual token sequences, particularly i…
cs.CV2026
4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking
Chaoyue Li, Boxue Yang, Shengyao Zhou +3
4D dynamic scene understanding requires grounding language to a persistent worldline that binds identity, metric 3D motion, and synchronized multi-view 2D projections. Existing par…