NudgeVAD shows language nudges improve VAD trajectories mainly when categorical commands are random, recovering 0.36 m ADE6s over detached-text baseline and outperforming a compute-matched unconditional fine-tune by 0.312 m.
doScenes: An Autonomous Driving Dataset with Natural Language Instruction for Human Interaction and Vision–Language Navigation
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
L-LIO integrates audio with visual data to enhance driver safety assessment and intelligent vehicle decision-making via multimodal sensor fusion.
citing papers explorer
-
NudgeVAD: Language-Nudged End-to-End Driving via FiLM Residuals
NudgeVAD shows language nudges improve VAD trajectories mainly when categorical commands are random, recovering 0.36 m ADE6s over detached-text baseline and outperforming a compute-matched unconditional fine-tune by 0.312 m.
-
Looking and Listening Inside and Outside: Multimodal Artificial Intelligence Systems for Driver Safety Assessment and Intelligent Vehicle Decision-Making
L-LIO integrates audio with visual data to enhance driver safety assessment and intelligent vehicle decision-making via multimodal sensor fusion.