Speed in the Blind Spot: An Interpretability Analysis of Dynamic Perception in VLMs for Autonomous Driving

arXiv:2609.37046 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Comments: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

Project page: https://iv.ee.hm.edu/projects/speed-in-the-blind-spot

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptation — 51× in this paper · explained in 1 episode
• Benchmark — 18× in this paper · explained in 2 episodes
• Grounding — 16× in this paper · explained in 3 episodes
• Linear probe — 9× in this paper · explained in 2 episodes
• Failure Modes — 7× in this paper · explained in 3 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Robustness — 6× in this paper · explained in 5 episodes
• Foundation Model — 5× in this paper · explained in 3 episodes
• Foundation Models — 4× in this paper · explained in 7 episodes
• Interpretability — 4× in this paper · explained in 15 episodes
• Mean Absolute Error — 3× in this paper
• ROOT MEAN SQUARED ERROR — 3× in this paper
• Verification — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Decode — 2× in this paper · explained in 2 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• LoRA Adaptation — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• AI Foundation Model — 1× in this paper · explained in 1 episode
• Adaptability — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Edge Devices — 1× in this paper · explained in 2 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Multimodal Fusion — 1× in this paper · explained in 3 episodes
• PROBE MINUS VERBAL PERFORMANCE IN TABLE II — 1× in this paper
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Temporal Reasoning — 1× in this paper · explained in 2 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Qwen2.5-VL Technical Report
• Qwen3-VL Technical Report
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
• VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models
• How Well Do Vision-Language Models Understand Sequential Driving Scenes? A Sensitivity Study
• SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
• Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models