# SG-CADVLM: A Context-Aware Decoding Powered Vision Language Model for Safety-Critical Scenario Generation

arXiv: https://arxiv.org/abs/2601.18442 · HTML: https://mlsanity.com/paper/2601.18442/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Driving VLMs and open-vocabulary detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 6 of its 33 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/)

## Builds on (most cited first, 6 of 6)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Multimodal Large Language Model Driven Scenario Testing for Autonomous Vehicles](https://mlsanity.com/paper/2409.06450/) (2024)
- [Text2Scenario: Text-Driven Scenario Generation for Autonomous Driving Test](https://mlsanity.com/paper/2503.02911/) (2025)
- [LMM-enhanced Safety-Critical Scenario Generation for Autonomous Driving System Testing From Non-Accident Traffic Videos](https://mlsanity.com/paper/2406.10857/) (2024)
- [Edge Case Detection in Automated Driving: Methods, Challenges, and Future Directions](https://mlsanity.com/paper/2410.08491/) (2024)
- [ML-SceGen: A Multi-level Scenario Generation Framework](https://mlsanity.com/paper/2501.10782/) (2025)

## Built on by (most cited first, 1 of 1)

- [A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety Assurance](https://mlsanity.com/paper/2610.13479/) (2026)

## Abstract (arXiv)

Autonomous Vehicle (AV) requires rigorous testing in safety-critical scenarios for safety validation, yet its validation is hindered by the high cost of field testing and the lack of fidelity in current simulations for rare safety-critical events. Crash reports offer rich and authentic specifications of real-world accident dynamics, making them a promising resource for Large Language Models and Vision-Language models to generate high-fidelity scenarios. However, the existing models frequently deviate from actual accident characteristics due to context suppression. To address these limitations, this paper presents SG-CADVLM, a framework integrateing Context-Aware Decoding with multimodal input processing to generate safety-critical scenarios from crash reports. The framework mitigates the hallucination of VLMs while generating road geometry and vehicle trajectories simultaneously. The experimental results demonstrate that SG-CADVLM generates combined critical and high-risk scenarios at a rate of 88.1% compared to 31.2% for the baseline methods, representing a 182% improvement, while producing executable simulations for autonomous vehicle testing.