# Occ-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models

arXiv: https://arxiv.org/abs/2502.06419 · HTML: https://mlsanity.com/paper/2502.06419/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in Large language models for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 43 of its 54 references that are in the map.
- First posted on arXiv 10 Feb 2025.

## Placed in

- End-to-end autonomous driving / [Large language models for driving](https://mlsanity.com/driving/large-language-models-for-driving/)

## Builds on (most cited first, 30 of 43)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [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)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [All are Worth Words: A ViT Backbone for Diffusion Models](https://mlsanity.com/paper/2209.12152/) (2022)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [Is ChatGPT a General-Purpose Natural Language Processing Task Solver?](https://mlsanity.com/paper/2302.06476/) (2023)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving](https://mlsanity.com/paper/2304.14365/) (2023)
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (2023)
- [OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2304.05316/) (2023)
- [End-to-end Interpretable Neural Motion Planner](https://mlsanity.com/paper/2101.06679/) (2021)
- [OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving](https://mlsanity.com/paper/2311.16038/) (2023)
- [Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving](https://mlsanity.com/paper/2310.01957/) (2023)
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://mlsanity.com/paper/2012.03762/) (2020)
- [OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception](https://mlsanity.com/paper/2303.03991/) (2023)
- [Scene as Occupancy](https://mlsanity.com/paper/2306.02851/) (2023)

## Built on by (most cited first, 28 of 28)

- [FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving](https://mlsanity.com/paper/2505.17685/) (2025)
- [3D and 4D World Modeling: A Survey](https://mlsanity.com/paper/2509.07996/) (2025)
- [DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving](https://mlsanity.com/paper/2602.06521/) (2026)
- [Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future](https://mlsanity.com/paper/2512.16760/) (2025)
- [The Role of World Models in Shaping Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2502.10498/) (2025)
- [Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipes](https://mlsanity.com/paper/2504.15037/) (2025)
- [COME: Adding Scene-Centric Forecasting Control to Occupancy World Model](https://mlsanity.com/paper/2506.13260/) (2025)
- [GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation](https://mlsanity.com/paper/2512.12751/) (2025)
- [Learning Vision-Language-Action World Models for Autonomous Driving](https://mlsanity.com/paper/2604.09059/) (2026)
- [UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving](https://mlsanity.com/paper/2512.09864/) (2025)
- [OccTENS: 3D Occupancy World Model via Temporal Next-Scale Prediction](https://mlsanity.com/paper/2509.03887/) (2025)
- [Occupancy World Model for Robots](https://mlsanity.com/paper/2505.05512/) (2025)
- [I2-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting](https://mlsanity.com/paper/2507.09144/) (2025)
- [Delta-Triplane Transformers as Occupancy World Models](https://mlsanity.com/paper/2503.07338/) (2025)
- [WPT: World-to-Policy Transfer via Online World Model Distillation](https://mlsanity.com/paper/2511.20095/) (2025)
- [SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model](https://mlsanity.com/paper/2511.22039/) (2025)
- [SparseOccVLA: Bridging Occupancy and Vision-Language Models via Sparse Queries for Unified 4D Scene Understanding and Planning](https://mlsanity.com/paper/2601.06474/) (2026)
- [Vision-Centric 4D Occupancy Forecasting and Planning via Implicit Residual World Models](https://mlsanity.com/paper/2510.16729/) (2025)
- [HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation](https://mlsanity.com/paper/2604.28196/) (2026)
- [OWMDrive: Causality-Aware End-to-End Autonomous Driving via 4D Occupancy World Model](https://mlsanity.com/paper/2606.30421/) (2026)
- [YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videos](https://mlsanity.com/paper/2506.18266/) (2025)
- [SuperQuadricOcc: Real-Time Self-Supervised Semantic Occupancy Estimation with Superquadric Volume Rendering](https://mlsanity.com/paper/2511.17361/) (2025)
- [GEM: Gaussian Evolution Model for Occupancy Forecasting and Motion Planning](https://mlsanity.com/paper/2605.17682/) (2026)
- [Reason--Imagine--Act: Closed-Loop LLM Decision Making with World Models for Autonomous Driving](https://mlsanity.com/paper/2605.24004/) (2026)
- [LiAuto-GeoX: Efficient Grounded Driving Transformer](https://mlsanity.com/paper/2606.05774/) (2026)
- [CascadeOcc: Rethinking 3D Occupancy World Models with Cascaded VQ Representations](https://mlsanity.com/paper/2606.27644/) (2026)
- [Geometry-Aware Spatio-Temporal Context Modeling for 4D Occupancy Forecasting](https://mlsanity.com/paper/2608.15279/) (2026)
- [InfraWorld: Motion-Aware World Modeling for Roadside 4D Occupancy Forecasting](https://mlsanity.com/paper/2610.14544/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have made substantial advancements in the field of robotic and autonomous driving. This study presents the first Occupancy-based Large Language Model (Occ-LLM), which represents a pioneering effort to integrate LLMs with an important representation. To effectively encode occupancy as input for the LLM and address the category imbalances associated with occupancy, we propose Motion Separation Variational Autoencoder (MS-VAE). This innovative approach utilizes prior knowledge to distinguish dynamic objects from static scenes before inputting them into a tailored Variational Autoencoder (VAE). This separation enhances the model's capacity to concentrate on dynamic trajectories while effectively reconstructing static scenes. The efficacy of Occ-LLM has been validated across key tasks, including 4D occupancy forecasting, self-ego planning, and occupancy-based scene question answering. Comprehensive evaluations demonstrate that Occ-LLM significantly surpasses existing state-of-the-art methodologies, achieving gains of about 6% in Intersection over Union (IoU) and 4% in mean Intersection over Union (mIoU) for the task of 4D occupancy forecasting. These findings highlight the transformative potential of Occ-LLM in reshaping current paradigms within robotic and autonomous driving.