# GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation

arXiv: https://arxiv.org/abs/2512.23180 · HTML: https://mlsanity.com/paper/2512.23180/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in World models for autonomous driving, one of 11 directions in World models.
- Builds on 71 of its 86 references that are in the map.
- First posted on arXiv 29 Dec 2025.

## Placed in

- World models / [World models for autonomous driving](https://mlsanity.com/wm/world-models-for-autonomous-driving/)
- End-to-end autonomous driving / [Generative simulation for driving](https://mlsanity.com/driving/generative-simulation-for-driving/)

## Builds on (most cited first, 30 of 71)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors](https://mlsanity.com/paper/2310.12190/) (2023)
- [DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model](https://mlsanity.com/paper/2310.01412/) (2023)
- [LangSplat: 3D Language Gaussian Splatting](https://mlsanity.com/paper/2312.16084/) (2023)
- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability](https://mlsanity.com/paper/2405.17398/) (2024)
- [3D-VLA: A 3D Vision-Language-Action Generative World Model](https://mlsanity.com/paper/2403.09631/) (2024)
- [Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving](https://mlsanity.com/paper/2311.17918/) (2023)
- [Neural Scene Graphs for Dynamic Scenes](https://mlsanity.com/paper/2011.10379/) (2020)
- [MagicDrive: Street View Generation with Diverse 3D Geometry Control](https://mlsanity.com/paper/2310.02601/) (2023)
- [Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting](https://mlsanity.com/paper/2401.01339/) (2024)
- [EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision](https://mlsanity.com/paper/2311.02077/) (2023)
- [DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation](https://mlsanity.com/paper/2403.06845/) (2024)
- [ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation](https://mlsanity.com/paper/2503.19755/) (2025)
- [PointMamba: A Simple State Space Model for Point Cloud Analysis](https://mlsanity.com/paper/2402.10739/) (2024)
- [OmniRe: Omni Urban Scene Reconstruction](https://mlsanity.com/paper/2408.16760/) (2024)
- [SUDS: Scalable Urban Dynamic Scenes](https://mlsanity.com/paper/2303.14536/) (2023)

## Built on by (most cited first, 23 of 23)

- [Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models](https://mlsanity.com/paper/2603.21389/) (2026)
- [LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing](https://mlsanity.com/paper/2606.26740/) (2026)
- [MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution](https://mlsanity.com/paper/2604.26283/) (2026)
- [Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding](https://mlsanity.com/paper/2603.19235/) (2026)
- [When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models](https://mlsanity.com/paper/2603.23085/) (2026)
- [A Definition and Roadmap for World Models](https://mlsanity.com/paper/2607.06401/) (2026)
- [RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space](https://mlsanity.com/paper/2602.20685/) (2026)
- [Guided Diffusion-based Generation of Adversarial Objects for Real-World Monocular Depth Estimation Attacks](https://mlsanity.com/paper/2512.24111/) (2025)
- [HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Video](https://mlsanity.com/paper/2606.29333/) (2026)
- [CoSAG: Compact Semantic Anchor Gaussians via Training-Free Rate-Distortion Coding](https://mlsanity.com/paper/2607.10237/) (2026)
- [MSEditor: Toward Consistent Multi-Shot Video Editing](https://mlsanity.com/paper/2608.17559/) (2026)
- [DINO-VO: Learning Where to Focus for Enhanced State Estimation](https://mlsanity.com/paper/2604.04055/) (2026)
- [Appearance Decomposition Gaussian Splatting for Multi-Traversal Reconstruction](https://mlsanity.com/paper/2604.05908/) (2026)
- [LLM-Augmented Traffic Signal Control with LSTM-Based Traffic State Prediction and Safety-Constrained Decision Support](https://mlsanity.com/paper/2604.23902/) (2026)
- [MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation](https://mlsanity.com/paper/2607.14595/) (2026)
- [MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving](https://mlsanity.com/paper/2607.23511/) (2026)
- [Efficient Human-Contact Representation for Human-Scene Interaction](https://mlsanity.com/paper/2608.09388/) (2026)
- [GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors](https://mlsanity.com/paper/2608.12203/) (2026)
- [GaussianDWM++: Language-Grounded 3D Gaussian Driving World Model for Unified Scene Understanding, Editing, and Multi-Modal Generation](https://mlsanity.com/paper/2608.16234/) (2026)
- [SPVC: Structured and Panoptic Video Fixing for Cross-Dataset Driving Scene Rendering](https://mlsanity.com/paper/2608.17420/) (2026)
- [BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World Generation](https://mlsanity.com/paper/2608.22187/) (2026)
- [From Generation to Simulation: How Far Are World Models from Being True Simulators?](https://mlsanity.com/paper/2608.23070/) (2026)
- [LangStreet: Persistent Language Fields for Anchor-Decoded Street Gaussians](https://mlsanity.com/paper/2609.11616/) (2026)

## Abstract (arXiv)

Driving World Models (DWMs) have been developing rapidly with the advances of generative models. However, existing DWMs lack 3D scene understanding capabilities and can only generate content conditioned on input data, without the ability to interpret or reason about the driving environment. Moreover, current approaches represent 3D spatial information with point cloud or BEV features do not accurately align textual information with the underlying 3D scene. To address these limitations, we propose a novel unified DWM framework based on 3D Gaussian scene representation, which enables both 3D scene understanding and multi-modal scene generation, while also enabling contextual enrichment for understanding and generation tasks. Our approach directly aligns textual information with the 3D scene by embedding rich linguistic features into each Gaussian primitive, thereby achieving early modality alignment. In addition, we design a novel task-aware language-guided sampling strategy that removes redundant 3D Gaussians and injects accurate and compact 3D tokens into LLM. Furthermore, we design a dual-condition multi-modal generation model, where the information captured by our vision-language model is leveraged as a high-level language condition in combination with a low-level image condition, jointly guiding the multi-modal generation process. We conduct comprehensive studies on the nuScenes, and NuInteract datasets to validate the effectiveness of our framework. Our method achieves state-of-the-art performance. We will release the code publicly on GitHub https://github.com/dtc111111/GaussianDWM.