# Tracking Meets Large Multimodal Models for Driving Scenario Understanding

arXiv: https://arxiv.org/abs/2503.14498 · HTML: https://mlsanity.com/paper/2503.14498/

## Key facts

- Cited by 7 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 27 of its 35 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## 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, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Language Is Not All You Need: Aligning Perception with Language Models](https://mlsanity.com/paper/2302.14045/) (2023)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model](https://mlsanity.com/paper/2310.01412/) (2023)
- [LMDrive: Closed-Loop End-to-End Driving with Large Language Models](https://mlsanity.com/paper/2312.07488/) (2023)
- [Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving](https://mlsanity.com/paper/2310.01957/) (2023)
- [Meta-Transformer: A Unified Framework for Multimodal Learning](https://mlsanity.com/paper/2307.10802/) (2023)
- [VLP: Vision Language Planning for Autonomous Driving](https://mlsanity.com/paper/2401.05577/) (2024)
- [ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles](https://mlsanity.com/paper/2405.14062/) (2024)
- [Talk2BEV: Language-enhanced Bird's-eye View Maps for Autonomous Driving](https://mlsanity.com/paper/2310.02251/) (2023)
- [OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping](https://mlsanity.com/paper/2304.10440/) (2023)
- [Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models](https://mlsanity.com/paper/2401.00988/) (2024)
- [Driving Everywhere with Large Language Model Policy Adaptation](https://mlsanity.com/paper/2402.05932/) (2024)
- [Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving](https://mlsanity.com/paper/2309.14491/) (2023)
- [DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario Understanding](https://mlsanity.com/paper/2503.10621/) (2025)
- [ADA-Track++: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association](https://mlsanity.com/paper/2405.08909/) (2024)
- [Poly-MOT: A Polyhedral Framework For 3D Multi-Object Tracking](https://mlsanity.com/paper/2307.16675/) (2023)
- [3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking](https://mlsanity.com/paper/2308.06635/) (2023)
- [Open3DTrack: Towards Open-Vocabulary 3D Multi-Object Tracking](https://mlsanity.com/paper/2410.01678/) (2024)

## Built on by (most cited first, 7 of 7)

- [FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving](https://mlsanity.com/paper/2505.17685/) (2025)
- [Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis](https://mlsanity.com/paper/2506.11526/) (2025)
- [UniDrive-WM: Unified Understanding, Planning and Generation World Model for Autonomous Driving](https://mlsanity.com/paper/2601.04453/) (2026)
- [VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving](https://mlsanity.com/paper/2602.20794/) (2026)
- [UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving](https://mlsanity.com/paper/2512.09864/) (2025)
- [NOVA: Next-step Open-Vocabulary Autoregression for 3D Multi-Object Tracking in Autonomous Driving](https://mlsanity.com/paper/2603.06254/) (2026)
- [Multimodal Action Diffusion for Robust End-to-End Autonomous Driving](https://mlsanity.com/paper/2606.02105/) (2026)

## Abstract (arXiv)

Large Multimodal Models (LMMs) have recently gained prominence in autonomous driving research, showcasing promising capabilities across various emerging benchmarks. LMMs specifically designed for this domain have demonstrated effective perception, planning, and prediction skills. However, many of these methods underutilize 3D spatial and temporal elements, relying mainly on image data. As a result, their effectiveness in dynamic driving environments is limited. We propose to integrate tracking information as an additional input to recover 3D spatial and temporal details that are not effectively captured in the images. We introduce a novel approach for embedding this tracking information into LMMs to enhance their spatiotemporal understanding of driving scenarios. By incorporating 3D tracking data through a track encoder, we enrich visual queries with crucial spatial and temporal cues while avoiding the computational overhead associated with processing lengthy video sequences or extensive 3D inputs. Moreover, we employ a self-supervised approach to pretrain the tracking encoder to provide LMMs with additional contextual information, significantly improving their performance in perception, planning, and prediction tasks for autonomous driving. Experimental results demonstrate the effectiveness of our approach, with a gain of 9.5% in accuracy, an increase of 7.04 points in the ChatGPT score, and 9.4% increase in the overall score over baseline models on DriveLM-nuScenes benchmark, along with a 3.7% final score improvement on DriveLM-CARLA. Our code is available at https://github.com/mbzuai-oryx/TrackingMeetsLMM