# MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios

arXiv: https://arxiv.org/abs/2412.19406 · HTML: https://mlsanity.com/paper/2412.19406/

## Key facts

- Cited by 8 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 17 of its 42 references that are in the map.
- First posted on arXiv 27 Dec 2024.

## 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, 17 of 17)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [EMMA: End-to-End Multimodal Model for Autonomous Driving](https://mlsanity.com/paper/2410.23262/) (2024)
- [RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model](https://mlsanity.com/paper/2402.10828/) (2024)
- [Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models](https://mlsanity.com/paper/2401.00988/) (2024)
- [HiLM-D: Enhancing MLLMs with Multi-Scale High-Resolution Details for Autonomous Driving](https://mlsanity.com/paper/2309.05186/) (2023)
- [eP-ALM: Efficient Perceptual Augmentation of Language Models](https://mlsanity.com/paper/2303.11403/) (2023)
- [Large Language Models Powered Context-aware Motion Prediction in Autonomous Driving](https://mlsanity.com/paper/2403.11057/) (2024)
- [IDD-X: A Multi-View Dataset for Ego-relative Important Object Localization and Explanation in Dense and Unstructured Traffic](https://mlsanity.com/paper/2404.08561/) (2024)
- [Transcrib3D: 3D Referring Expression Resolution through Large Language Models](https://mlsanity.com/paper/2404.19221/) (2024)

## Built on by (most cited first, 8 of 8)

- [Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis](https://mlsanity.com/paper/2506.11526/) (2025)
- [EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning Ability](https://mlsanity.com/paper/2503.10042/) (2025)
- [Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT](https://mlsanity.com/paper/2505.24182/) (2025)
- [AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models](https://mlsanity.com/paper/2506.09082/) (2025)
- [Multifaceted Evaluation of Audio-Visual Capability for MLLMs: Effectiveness, Efficiency, Generalizability and Robustness](https://mlsanity.com/paper/2504.16936/) (2025)
- [SA-Person: Text-Based Person Retrieval with Scene-aware Re-ranking](https://mlsanity.com/paper/2505.24466/) (2025)
- [MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding](https://mlsanity.com/paper/2507.06072/) (2025)
- [DriveSafe: A Framework for Risk Detection and Safety Suggestions in Driving Scenarios](https://mlsanity.com/paper/2605.16892/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) have shown satisfactory effects in many autonomous driving tasks. In this paper, MLLMs are utilized to solve joint semantic scene understanding and risk localization tasks, while only relying on front-view images. In the proposed MLLM-SUL framework, a dual-branch visual encoder is first designed to extract features from two resolutions, and rich visual information is conducive to the language model describing risk objects of different sizes accurately. Then for the language generation, LLaMA model is fine-tuned to predict scene descriptions, containing the type of driving scenario, actions of risk objects, and driving intentions and suggestions of ego-vehicle. Ultimately, a transformer-based network incorporating a regression token is trained to locate the risk objects. Extensive experiments on the existing DRAMA-ROLISP dataset and the extended DRAMA-SRIS dataset demonstrate that our method is efficient, surpassing many state-of-the-art image-based and video-based methods. Specifically, our method achieves 80.1% BLEU-1 score and 298.5% CIDEr score in the scene understanding task, and 59.6% accuracy in the localization task. Codes and datasets are available at https://github.com/fjq-tongji/MLLM-SUL.