← Blog

World Model for Autonomous Driving

· Updated

自车规划与控制

WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving

CVPR 2026 arXiv Code

ResWorld: Temporal Residual World Model for End-to-End Autonomous Driving

ICLR 2026 arXiv Code

WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving

AAAI 2026 arXiv

Latent Chain-of-Thought World Modeling for End-to-End Autonomous Driving

CVPR 2026 arXiv

OWMDrive: Causality-Aware End-to-End Autonomous Driving via 4D Occupancy World Model

IROS 2026 arXiv

DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving

ICML 2026 arXiv Project Code

World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model

ICCV 2025 arXiv Code

AdaWM: Adaptive World Model based Planning for Autonomous Driving

ICLR 2025 arXiv

ICLR 2025 arXiv Code

DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving

ICLR 2026 arXiv Code

CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving

ICML 2026 arXiv Code

ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving

ICRA 2026 arXiv Code

Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)

NeurIPS 2025 arXiv

End-to-End Driving with Online Trajectory Evaluation via BEV World Model (WoTE)

ICCV 2025 arXiv Code

联合预测与规划

DriveVA: Video Action Models are Zero-Shot Drivers

ECCV 2026 arXiv Code

DriveLaW: Unifying Planning and Video Generation in a Latent Driving World

CVPR 2026 arXiv Code

FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving (FSDrive)

NeurIPS 2025 arXiv Code

From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction

NeurIPS 2025 arXiv Code

Epona: Autoregressive Diffusion World Model for Autonomous Driving

ICCV 2025 arXiv Project Code

DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers

ICCV 2025 arXiv Project Code

视频与多模态未来生成

UniFuture: A 4D Driving World Model for Future Generation and Perception

ICRA 2026 arXiv Project Code

RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space

CVPR 2026 arXiv Project Code

GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation

CVPR 2026 arXiv Project Code

OmniNWM: Unifying the State-Action-Reward Triad for Closed-Loop Panoramic Driving Navigation World Models

ECCV 2026 arXiv Project Code

MAD: Motion Appearance Decoupling for efficient Driving World Models

CVPR 2026 arXiv Project Code

CausalDrive: Real-time Causal World Models for Autonomous Driving

ECCV 2026 arXiv

DCARL: A Divide-and-Conquer Framework for Autoregressive Long-Trajectory Video Generation

ECCV 2026 arXiv Project

DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation

ICCV 2025 arXiv Project Code

MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction

CVPR 2025 arXiv Code

GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control

CVPR 2025 arXiv Project Code

Generating Multimodal Driving Scenes via Next-Scene Prediction (UMGen)

CVPR 2025 arXiv Project Code

STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation

IROS 2025 arXiv Project

Overcoming Challenges of Long-Horizon Prediction in Driving World Models (Orbis)

NeurIPS 2025 arXiv Project Code

ReSim: Reliable World Simulation for Autonomous Driving

NeurIPS 2025 arXiv Project Code

GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control

ICRA 2026 arXiv Code

占据与语义未来预测

SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model

CVPR 2026 arXiv

DINO-Foresight: Looking into the Future with DINO

NeurIPS 2025 arXiv Project Code

Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers (FUTURIST)

CVPR 2025 arXiv Project Code

DIO: Decomposable Implicit 4D Occupancy-Flow World Model

CVPR 2025 Paper

OccProphet: Pushing the Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with an Observer-Forecaster-Refiner Framework

ICLR 2025 arXiv Code

Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving (PreWorld)

ICLR 2025 arXiv Code

Vision-Centric 4D Occupancy Forecasting and Planning via Implicit Residual World Models

ICRA 2026 arXiv Code

SparseWorld: A Flexible, Adaptive, and Efficient 4D Occupancy World Model Powered by Sparse and Dynamic Queries

AAAI 2026 arXiv Code

OccTENS: 3D Occupancy World Model via Temporal Next-Scale Prediction

ICRA 2026 arXiv

I2-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting

ICCV 2025 arXiv Code

DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving

ICCV 2025 arXiv

LiDAR时序建模

U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences

CVPR 2026 arXiv Code

LaGen: Towards Autoregressive LiDAR Scene Generation

ECCV 2026 arXiv Code

GEM: Generating LiDAR World Model via Deformable Mamba

CVPR 2026 arXiv Code

LiSTAR: Ray-Centric World Models for 4D LiDAR Sequences in Autonomous Driving

ECCV 2026 arXiv Project Code

Towards foundational LiDAR world models with efficient latent flow matching

NeurIPS 2025 arXiv

多交通参与者仿真

Long-term Traffic Simulation via Structured Autoregressive Modeling

ECCV 2026 arXiv

SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model

CVPR 2025 Paper

3D驾驶场景生成

InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models

ICCV 2025 arXiv Project Code

LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding

AAAI 2026 arXiv Project

4D驾驶场景重建与新视角合成

DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation

CVPR 2025 arXiv Project Code

ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration

CVPR 2025 arXiv Project Code

条件场景合成与编辑

UniScene: Unified Occupancy-centric Driving Scene Generation

CVPR 2025 arXiv Project Code

DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes

ICLR 2025 arXiv Project Code

Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks (Dream4Drive)

ICLR 2026 arXiv Project Code

LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences

AAAI 2026 arXiv Project Code

MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control

ICCV 2025 arXiv Project Code

场景理解与联合建模

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

CVPR 2026 arXiv Code

UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving

ECCV 2026 arXiv Project

HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation

ICCV 2025 arXiv Project Code

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

ICRA 2025 arXiv

当前场景感知

GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction

CVPR 2025 arXiv Code

Semi-SMD: Semi-Supervised Metric Depth Estimation via Surrounding Cameras for Autonomous Driving

ICRA 2026 arXiv Code

跨传感器生成

RadarGen: Automotive Radar Point Cloud Generation from Cameras

ECCV 2026 arXiv Project Code

驾驶员动态预测

Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout

ECCV 2026 arXiv

自然语言目标定位

Think Before You Drive: World Model-Inspired Multimodal Grounding

CVPR 2026 arXiv

事故视频生成与理解

AVD2: Accident Video Diffusion for Accident Video Description

ICRA 2025 arXiv Project Code

车辆动力学与逆问题

Unlocking Efficient Vehicle Dynamics Modeling via Analytic World Models

AAAI 2026 arXiv

评测与数据资源

WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

CVPR 2026 arXiv Project Code

A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models

ECCV 2026 arXiv

DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving

ICLR 2026 arXiv Project Code

UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving

ICCV 2025 arXiv Project Code

Drive&Gen: Co-Evaluating End-to-End Driving and Video Generation Models

IROS 2025 arXiv

Advancing Off-Road Autonomous Driving: The Large-Scale ORAD-3D Dataset and Comprehensive Benchmarks

ICRA 2026 arXiv Code

SimWorld: A Unified Benchmark for Simulator-Conditioned Scene Generation via World Model

IROS 2025 arXiv Code