# Generating Multimodal Driving Scenes via Next-Scene Prediction

arXiv: https://arxiv.org/abs/2503.14945 · HTML: https://mlsanity.com/paper/2503.14945/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 33 references that are in the map.
- First posted on arXiv 19 Mar 2025.

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

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [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)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles](https://mlsanity.com/paper/2106.11810/) (2021)
- [UniSim: A Neural Closed-Loop Sensor Simulator](https://mlsanity.com/paper/2308.01898/) (2023)
- [MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning](https://mlsanity.com/paper/2109.12674/) (2021)
- [DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving](https://mlsanity.com/paper/2309.09777/) (2023)
- [MagicDrive: Street View Generation with Diverse 3D Geometry Control](https://mlsanity.com/paper/2310.02601/) (2023)
- [SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation](https://mlsanity.com/paper/2405.19620/) (2024)
- [DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation](https://mlsanity.com/paper/2403.06845/) (2024)
- [MotionLM: Multi-Agent Motion Forecasting as Language Modeling](https://mlsanity.com/paper/2309.16534/) (2023)
- [Meta-Sim: Learning to Generate Synthetic Datasets](https://mlsanity.com/paper/1904.11621/) (2019)
- [TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarios](https://mlsanity.com/paper/2210.06609/) (2022)
- [DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving](https://mlsanity.com/paper/2408.00415/) (2024)
- [Language Conditioned Traffic Generation](https://mlsanity.com/paper/2307.07947/) (2023)
- [SceneGen: Learning to Generate Realistic Traffic Scenes](https://mlsanity.com/paper/2101.06541/) (2021)
- [Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation](https://mlsanity.com/paper/2205.03195/) (2022)
- [Trajeglish: Traffic Modeling as Next-Token Prediction](https://mlsanity.com/paper/2312.04535/) (2023)
- [BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction](https://mlsanity.com/paper/2405.17372/) (2024)
- [Solving Motion Planning Tasks with a Scalable Generative Model](https://mlsanity.com/paper/2407.02797/) (2024)
- [DreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes](https://mlsanity.com/paper/2409.04003/) (2024)
- [ComDrive: Comfort-Oriented End-to-End Autonomous Driving](https://mlsanity.com/paper/2410.05051/) (2024)
- [UniGen: Unified Modeling of Initial Agent States and Trajectories for Generating Autonomous Driving Scenarios](https://mlsanity.com/paper/2405.03807/) (2024)

## Built on by (most cited first, 12 of 12)

- [Epona: Autoregressive Diffusion World Model for Autonomous Driving](https://mlsanity.com/paper/2506.24113/) (2025)
- [3D and 4D World Modeling: A Survey](https://mlsanity.com/paper/2509.07996/) (2025)
- [Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory](https://mlsanity.com/paper/2602.02393/) (2026)
- [SimScale: Learning to Drive via Real-World Simulation at Scale](https://mlsanity.com/paper/2511.23369/) (2025)
- [3D Scene Generation: A Survey](https://mlsanity.com/paper/2505.05474/) (2025)
- [X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability](https://mlsanity.com/paper/2506.13558/) (2025)
- [From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMs](https://mlsanity.com/paper/2512.19683/) (2025)
- [DAP: A Discrete-token Autoregressive Planner for Autonomous Driving](https://mlsanity.com/paper/2511.13306/) (2025)
- [OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation](https://mlsanity.com/paper/2606.17536/) (2026)
- [ParaScale: Scale-Calibrated Camera-Motion Transfer via a Gauge-Invariant Parallax Number](https://mlsanity.com/paper/2606.19805/) (2026)
- [Can VLMs Unlock Semantic Anomaly Detection? A Framework for Structured Reasoning](https://mlsanity.com/paper/2510.18034/) (2025)
- [ScenarioControl: Vision-Language Controllable Vectorized Latent Scenario Generation](https://mlsanity.com/paper/2604.17147/) (2026)

## Abstract (arXiv)

Generative models in Autonomous Driving (AD) enable diverse scene creation, yet existing methods fall short by only capturing a limited range of modalities, restricting the capability of generating controllable scenes for comprehensive evaluation of AD systems. In this paper, we introduce a multimodal generation framework that incorporates four major data modalities, including a novel addition of map modality. With tokenized modalities, our scene sequence generation framework autoregressively predicts each scene while managing computational demands through a two-stage approach. The Temporal AutoRegressive (TAR) component captures inter-frame dynamics for each modality while the Ordered AutoRegressive (OAR) component aligns modalities within each scene by sequentially predicting tokens in a fixed order. To maintain coherence between map and ego-action modalities, we introduce the Action-aware Map Alignment (AMA) module, which applies a transformation based on the ego-action to maintain coherence between these modalities. Our framework effectively generates complex, realistic driving scenes over extended sequences, ensuring multimodal consistency and offering fine-grained control over scene elements. Project page: https://yanhaowu.github.io/UMGen/