Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Enhancing Multimodal Large Language Models for Safety-Critical Driving Video Analysis

About

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding. However, their application to safety-critical driving scenarios remains limited by an inability to accurately perceive and reason about rare high-stakes dynamic events, such as collisions or near-collisions. To address this, we introduce a pipeline that enhances MLLM perception by fusing downsampled video frames with synchronized high-frequency telematics data (IMU and GPS) and semantic insights from specialized computer vision models. Our pipeline generates high-quality pseudo-labels, including descriptive captions and question-answer pairs, specifically designed to train MLLMs to identify and describe Safety-Critical Events (SCEs) in real-world driving footage. We show the effectiveness of our approach fine-tuning the open-source QwenVL-2.5 model via DoRA adapters: our experiments demonstrate significant improvements in identifying and explaining safety-critical events, with fewer than 50M trainable parameters and limited computational budget.

Tomaso Trinci, Henrique Pi\~neiro Monteagudo, Leonardo Taccari• 2026

Related benchmarks

TaskDatasetResultRank
3-class Scene Classification (SCE)Private dataset video + IMU
Accuracy87.7
8
CaptioningPrivate dataset video + IMU
ROUGE-L0.44
8
Binary Safety-Critical Event (SCE) identificationPrivate dataset video + IMU
Precision (Positive Class)93.3
8
Binary Safety-Critical Event (SCE) identificationNexar video only
Precision (y=1)85.6
8
Closed QAPrivate dataset video + IMU
Accuracy92.7
8
Open-ended Question AnsweringLingoQA
ROUGE-L28
8
Showing 6 of 6 rows

Other info

Follow for update