# HiLM-D: Enhancing MLLMs with Multi-Scale High-Resolution Details for Autonomous Driving

arXiv: https://arxiv.org/abs/2309.05186 · HTML: https://mlsanity.com/paper/2309.05186/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- Placed in VLMs for autonomous driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 52 of its 75 references that are in the map.
- First posted on arXiv 11 Sep 2023.

## Placed in

- End-to-end autonomous driving / [VLMs for autonomous driving](https://mlsanity.com/driving/vlms-for-autonomous-driving/)

## Builds on (most cited first, 30 of 52)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)

## Built on by (most cited first, 30 of 50)

- [A Survey on Multimodal Large Language Models for Autonomous Driving](https://mlsanity.com/paper/2311.12320/) (2023)
- [VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning](https://mlsanity.com/paper/2402.13243/) (2024)
- [Dolphins: Multimodal Language Model for Driving](https://mlsanity.com/paper/2312.00438/) (2023)
- [Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving](https://mlsanity.com/paper/2312.03661/) (2023)
- [MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance](https://mlsanity.com/paper/2401.02906/) (2024)
- [OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2409.03272/) (2024)
- [Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models](https://mlsanity.com/paper/2401.00988/) (2024)
- [Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization](https://mlsanity.com/paper/2403.08730/) (2024)
- [Embodied Understanding of Driving Scenarios](https://mlsanity.com/paper/2403.04593/) (2024)
- [PerceptionGPT: Effectively Fusing Visual Perception into LLM](https://mlsanity.com/paper/2311.06612/) (2023)
- [LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs](https://mlsanity.com/paper/2312.04372/) (2023)
- [AgentsCoDriver: Large Language Model Empowered Collaborative Driving with Lifelong Learning](https://mlsanity.com/paper/2404.06345/) (2024)
- [Visual Large Language Models for Generalized and Specialized Applications](https://mlsanity.com/paper/2501.02765/) (2025)
- [Empowering Autonomous Driving with Large Language Models: A Safety Perspective](https://mlsanity.com/paper/2312.00812/) (2023)
- [Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models](https://mlsanity.com/paper/2404.12916/) (2024)
- [NuScenes-MQA: Integrated Evaluation of Captions and QA for Autonomous Driving Datasets using Markup Annotations](https://mlsanity.com/paper/2312.06352/) (2023)
- [CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration](https://mlsanity.com/paper/2409.11365/) (2024)
- [[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs](https://mlsanity.com/paper/2412.05819/) (2024)
- [Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities](https://mlsanity.com/paper/2401.08045/) (2024)
- [Personalized Visual Instruction Tuning](https://mlsanity.com/paper/2410.07113/) (2024)
- [Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives](https://mlsanity.com/paper/2402.02968/) (2024)
- [Human-Centric Autonomous Systems With LLMs for User Command Reasoning](https://mlsanity.com/paper/2311.08206/) (2023)
- [Applications of Large Scale Foundation Models for Autonomous Driving](https://mlsanity.com/paper/2311.12144/) (2023)
- [DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Models](https://mlsanity.com/paper/2503.11265/) (2025)
- [LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments, and Future Trends](https://mlsanity.com/paper/2410.15281/) (2024)
- [Bench2Drive-VL: Benchmarks for Closed-Loop Autonomous Driving with Vision-Language Models](https://mlsanity.com/paper/2604.01259/) (2026)
- [World knowledge-enhanced Reasoning Using Instruction-guided Interactor in Autonomous Driving](https://mlsanity.com/paper/2412.06324/) (2024)
- [WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving](https://mlsanity.com/paper/2511.20022/) (2025)
- [Evaluation of Large Language Models for Decision Making in Autonomous Driving](https://mlsanity.com/paper/2312.06351/) (2023)
- [MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios](https://mlsanity.com/paper/2412.19406/) (2024)

## Abstract (arXiv)

Recent efforts to use natural language for interpretable driving focus mainly on planning, neglecting perception tasks. In this paper, we address this gap by introducing ROLISP (Risk Object Localization and Intention and Suggestion Prediction), which towards interpretable risk object detection and suggestion for ego car motions. Accurate ROLISP implementation requires extensive reasoning to identify critical traffic objects and infer their intentions, prompting us to explore the capabilities of multimodal large language models (MLLMs). However, the limited perception performance of CLIP-ViT vision encoders in existing MLLMs struggles with capturing essential visual perception information, e.g., high-resolution, multi-scale and visual-related inductive biases, which are important for autonomous driving. Addressing these challenges, we introduce HiLM-D, a resource-efficient framework that enhances visual information processing in MLLMs for ROLISP. Our method is motivated by the fact that the primary variations in autonomous driving scenarios are the motion trajectories rather than the semantic or appearance information (e.g., the shapes and colors) of objects. Hence, the visual process of HiLM-D is a two-stream framework: (i) a temporal reasoning stream, receiving low-resolution dynamic video content, to capture temporal semantics, and (ii) a spatial perception stream, receiving a single high-resolution frame, to capture holistic visual perception-related information. The spatial perception stream can be made very lightweight by a well-designed P-Adapter, which is lightweight, training-efficient, and easily integrated into existing MLLMs. Experiments on the DRAMA-ROLISP dataset show HiLM-D's significant improvements over current MLLMs, with a 3.7% in BLEU-4 for captioning and 8.7% in mIoU for detection.