arXiv Computer Vision
RSKD: Grounding Semantic Consistency in Driving VLMs via Distillation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Oct 26
RSKD: Grounding Semantic Consistency in Driving VLMs via Distillation
Knowledge distillation can transfer large multimodal models to compact models for autonomous driving, but uniform token-level matching can dilute planning-relevant semantics and amplify teacher errors...
arXiv AI
Jun 6
Drive-KD: Multi-Teacher Distillation for VLMs in Autonomous Driving
arXiv:2601. 21288v2 Announce Type: replace Abstract: Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and planning in this domain.
arXiv Machine Learning
Jun 15
RT-VLA: Real-Time Vision-Language-Action Models via Knowledge Distillation
arXiv:2606. 14010v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong potential for end-to-end autonomous driving by jointly modeling visual perception, language reasoning, explainability and action prediction.
arXiv AI
Jul 7
CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillation for Autonomous Driving
arXiv:2607. 04179v1 Announce Type: cross Abstract: End-to-end Vision-Language Models (VLMs) show immense potential in autonomous driving.
arXiv AI
Oct 15
Cross-Stage Coherence in Hierarchical Driving VQA: A Consistency Protocol and Parameter-Efficient Gated Context Routing
The paper studies cross‑stage context passing in Graph Visual Question Answering for autonomous driving, focusing on the Perception, Prediction, and Planning stages. Two complementary approaches are evaluated on DriveLM‑nuScenes: an explicit prompt‑based conditioning strategy using a domain‑adapted 4B VLM that reduces NLI contradiction by up to 42.6%, and an implicit gated context projector that, with only ~0.5% of parameters updated, cuts planning‑stage NLI contradiction by 34% and boosts cross‑stage entailment by 50%. The explicit method offers a strong zero‑training baseline for surface consistency, while the implicit method delivers significant semantic gains, highlighting the potential of domain adaptation for further improvement.
arXiv AI
Jun 17
DriveJudge: Rethinking Autonomous Driving Evaluation with Vision-Language Models
arXiv:2606. 17362v1 Announce Type: cross Abstract: Autonomous driving has shifted towards end-to-end policy learning, where reliable, interpretable policy evaluation is a fundamental challenge as driving quality is highly context-dependent.