😎 Awesome 3D and 4D World Models

This survey reviews state-of-the-art 3D and 4D world models - systems that learn, predict, and simulate the geometry and dynamics of real environments from multi-modal signals.

We unify terminology, scope, and evaluations, and organize the space into three complementary paradigms by representation:

	Learn generative or predictive models from sequential video streams with geometric and temporal constraints. VideoGen focuses on long-horizon consistency, controllability, and scene-level generation, enabling agents to imagine or forecast plausible video rollouts.
	Model 3D/4D occupancy grids that encode geometry and semantics in voxel space. OccGen provides a physics-consistent scaffold for robust perception, forecasting, and simulation, bridging low-level sensor data and high-level reasoning.
	Leverage point cloud sequences from LiDAR sensors to generate or predict geometry-grounded scenes. LiDARGen emphasizes high-fidelity 3D structure, robustness to environment changes, and applications in safety-critical domains such as autonomous driving.

For more details, kindly refer to our paper and project page. 🚀

📚 Citation

If you find this work helpful for your research, please kindly consider citing our papers:

@article{survey_3d_4d_world_models,
    title   = {{3D} and {4D} World Modeling: A Survey},
    author  = {Lingdong Kong and Wesley Yang and Jianbiao Mei and Youquan Liu and Ao Liang and Dekai Zhu and Dongyue Lu and Wei Yin and Xiaotao Hu and Mingkai Jia and Junyuan Deng and Kaiwen Zhang and Yang Wu and Tianyi Yan and Shenyuan Gao and Song Wang and Linfeng Li and Liang Pan and Yong Liu and Jianke Zhu and Wei Tsang Ooi and Steven C. H. Hoi and Ziwei Liu},
    journal = {arXiv preprint arXiv:2509.07996},
    year    = {2025}
}

@article{worldlens,
    title   = {{WorldLens}: Full-Spectrum Evaluations of Driving World Models in Real World},
    author  = {Ao Liang and Lingdong Kong and Tianyi Yan and Hongsi Liu and Wesley Yang and Ziqi Huang and Wei Yin and Jialong Zuo and Yixuan Hu and Dekai Zhu and Dongyue Lu and Youquan Liu and Guangfeng Jiang and Linfeng Li and Xiangtai Li and Long Zhuo and Lai Xing Ng and Benoit R. Cottereau and Changxin Gao and Liang Pan and Wei Tsang Ooi and Ziwei Liu},
    journal = {arXiv preprint arXiv:2512.10958},
    year    = {2025}
}

Table of Contents

• 0. Background
• 1. Benchmarks & Datasets
  • Benchmarks
  • Workshops
  • Datasets
• 2. World Modeling from Video Generation
  • Data Engines
  • Action Interpreters
  • Neural Simulators
  • Scene Reconstructors
• 3. World Modeling from Occupancy Generation
  • Scene Representors
  • Occupancy Forecasters
  • Autoregressive Simulators
• 4. World Modeling from LiDAR Generation
  • Data Engines
  • Action Forecasters
  • Autoregressive Simulators
• 5. Applications
  • Autonomous Driving
  • Robotics
  • Video Games & XR
  • Digital Twins
  • Other Topics
• 6. Other Resources
  • Tutorials
  • Talks & Seminars
• 7. Acknowledgements

Background

	World modeling has become a cornerstone of modern AI, enabling agents to understand, represent, and predict dynamic environments. While prior research has focused primarily on 2D images and videos, the rapid emergence of native 3D and 4D representations (e.g., RGB-D, occupancy grids, LiDAR point clouds) calls for a dedicated study.

What Are Native 3D Representations?

Unlike 2D projections, native 3D/4D signals directly encode metric geometry, visibility, and motion in the physical coordinates where agents act. Examples include:

• RGB-D imagery (2D images with depth channels)
• Occupancy grids (voxelized maps of free vs. occupied space)
• LiDAR point clouds (3D coordinates from active sensing)
• Neural fields (e.g., NeRF, Gaussian Splatting)

What Are World Models in 3D and 4D?

A 3D/4D world model is an internal representation that allows an agent to imagine, forecast, and interact with its environment in the 3D space.

	Generative World Models: synthesize plausible 3D/4D worlds under conditions (e.g., text prompts, trajectories).
	Predictive World Models: anticipate the future evolution of 3D/4D scenes given past observations and actions.

Together, these models provide the foundation for simulation, planning, and embodied intelligence in complex environments.

1. Benchmarks & Datasets

Benchmarks

WorldLens	VBench	WorldScore

Workshops

Datasets

⏲️ In chronological order, from the earliest to the latest.

Model	Paper	Venue	Website
KITTI	Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite	CVPR 2012
NYUv2	Indoor Segmentation and Support Inference from RGBD Images	ECCV 2012
CARLA	CARLA: An Open Urban Driving Simulator	CoRL 2017
SemanticKITTI	SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences	ICCV 2019
nuScenes	nuScenes: A Multimodal Dataset for Autonomous Driving	CVPR 2020
Waymo Open	Scalability in Perception for Autonomous Driving: Waymo Open Dataset	CVPR 2020
STF	Seeing Through Fog Without Seeing Fog: Deep Multimodal Sensor Fusion in Unseen Adverse Weather	CVPR 2020
Virtual KITTI 2	Virtual KITTI 2	arXiv 2020
Argoverse 2	Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting	NeurIPS 2021
Lyft-Level5	One Thousand and One Hours: Self-Driving Motion Prediction Dataset	CoRL 2021
nuPlan	nuPlan: A Closed-Loop ML-Based Planning Benchmark for Autonomous Vehicles	CVPRW 2021
PandaSet	PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving	ITSC 2022
OpenCOOD	OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication	ICRA 2022
KITTI-360	KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D	TPAMI 2022
CarlaSC	MotionSC: Data Set and Network for Real-Time Semantic Mapping in Dynamic Environments	RA-L 2022
Robo3D	Robo3D: Towards Robust and Reliable 3D Perception against Corruptions	ICCV 2023
OpenOccupancy	OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception	ICCV 2023
Occ3D-nuScenes	Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving	NeurIPS 2023
OpenDV-YouTube	GenAD: Generalized Predictive Model for Autonomous Driving	CVPR 2024
SSCBench	SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving	IROS 2024
NAVSIM	NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking	NeurIPS 2024
DrivingDojo	DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model	NeurIPS 2024
EUVS	Extrapolated Urban View Synthesis Benchmark	ICCV 2025
Pi3DET	Perspective-Invariant 3D Object Detection	ICCV 2025

2. World Modeling from Video Generation

1️⃣ Data Engines

⏲️ In chronological order, from the earliest to the latest.

Model	Paper	Venue	Website	GitHub
BEVControl	BEVControl: Accurately Controlling Street-View Elements with Multi-Perspective Consistency via BEV Sketch Layout	arXiv 2023	-	-
BEVGen	Street-View Image Generation from a Bird's-Eye View Layout	RA-L 2024
MagicDrive	MagicDrive: Street View Generation with Diverse 3D Geometry Control	ICLR 2024
Panacea	Panacea: Panoramic and Controllable Video Generation for Autonomous Driving	CVPR 2024
DrivingDiffusion	DrivingDiffusion: Layout-Guided Multi-View Driving Scene Video Generation with Latent Diffusion Model	ECCV 2024
WoVoGen	WoVoGen: World Volume-Aware Diffusion for Controllable Multi-Camera Driving Scene Generation	ECCV 2024	-
Delphi	Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation	arXiv 2024
SimGen	SimGen: Simulator-Conditioned Driving Scene Generation	NeurIPS 2024
BEVWorld	BEVWorld: A Multimodal World Simulator for Autonomous Driving via Scene-Level BEV Latents	arXiv 2024	-	-
Panacea+	Panacea+: Panoramic and Controllable Video Generation for Autonomous Driving	arXiv 2024		-
DiVE	DiVE: DiT-Based Video Generation with Enhanced Control	arXiv 2024
SyntheOcc	SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs	arXiv 2024
HoloDrive	HoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving	arXiv 2024	-	-
CogDriving	Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention	arXiv 2024		-
UniMLVG	UniMLVG: Unified Framework for Multi-View Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving	arXiv 2024	-
DrivePhysica	Physical Informed Driving World Model	arXiv 2024		-
DriveDreamer-2	DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation	AAAI 2025
SubjectDrive	SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control	AAAI 2025		-
Glad	Glad: A Streaming Scene Generator for Autonomous Driving	ICLR 2025	-
DualDiff	DualDiff: Dual-Branch Diffusion Model for Autonomous Driving with Semantic Fusion	ICRA 2025	-
UniScene	UniScene: Unified Occupancy-Centric Driving Scene Generation	CVPR 2025
DriveScape	DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation	CVPR 2025		-
PerLDiff	PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models	ICCV 2025
MagicDrive-V2	MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control	ICCV 2025		-
DINO-Foresight	DINO-Foresight: Looking into the Future with DINO	NeurIPS 2025
Cosmos-Transfer1	Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control	arXiv 2025
DualDiff+	DualDiff+: Dual-Branch Diffusion for High-Fidelity Video Generation with Reward Guidance	arXiv 2025	-
CoGen	CoGen: 3D Consistent Video Generation via Adaptive Conditioning for Autonomous Driving	arXiv 2025		-
NoiseController	NoiseController: Towards Consistent Multi-View Video Generation via Noise Decomposition and Collaboration	arXiv 2025	-	-
STAGE	STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation	arXiv 2025	-	-
WMReward	Inference-time Physics Alignment of Video Generative Models with Latent World Models	arXiv 2026	-	-

2️⃣ Action Interpreters

⏲️ In chronological order, from the earliest to the latest.

Model	Paper	Venue	Website	GitHub
GAIA-1	GAIA-1: A Generative World Model for Autonomous Driving	arXiv 2023		-
ADriver-I	ADriver-I: A General World Model for Autonomous Driving	arXiv 2023	-	-
Drive-WM	Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving	CVPR 2024
DriveDreamer	DriveDreamer: Towards Real-World-Driven World Models for Autonomous Driving	ECCV 2024
GenAD	GenAD: Generalized Predictive Model for Autonomous Driving	CVPR 2024	-
Vista	Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability	NeurIPS 2024
InfinityDrive	InfinityDrive: Breaking Time Limits in Driving World Models	arXiv 2024		-
DrivingGPT	DrivingGPT: Unifying Driving World Modeling and Planning with Multi-Modal Autoregressive Transformers	arXiv 2024		-
DrivingWorld	DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT	arXiv 2024
GEM	GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control	CVPR 2025
MaskGWM	MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction	CVPR 2025	-
Epona	Epona: Autoregressive Diffusion World Model for Autonomous Driving	ICCV 2025
VaViM & VaVAM	VaViM and VaVAM: Autonomous Driving through Video Generative Modeling	arXiv 2025
MiLA	MiLA: Multi-View Intensive-Fidelity Long-Term Video Generation World Model for Autonomous Driving	arXiv 2025	-
GAIA-2	GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving	arXiv 2025		-
DriVerse	DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment	arXiv 2025	-	-
PosePilot	PosePilot: Steering Camera Pose for Generative World Models with Self-Supervised Depth	arXiv 2025	-	-
ProphetDWM	ProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos	arXiv 2025	-	-
LongDWM	LongDWM: Cross-Granularity Distillation for Building A Long-Term Driving World Model	arXiv 2025
UniDrive-WM	UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving	arXiv 2026		-

3️⃣ Neural Simulators

⏲️ In chronological order, from the earliest to the latest.

Model	Paper	Venue	Website	GitHub
MagicDrive3D	MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes	arXiv 2024
DreamForge	DreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes	arXiv 2024
Doe-1	Doe-1: Closed-Loop Autonomous Driving with Large World Model	arXiv 2024
DrivingSphere	DrivingSphere: Building A High-Fidelity 4D World for Closed-Loop Simulation	CVPR 2025
UMGen	Generating Multimodal Driving Scenes via Next-Scene Prediction	CVPR 2025
DriveArena	DriveArena: A Closed-Loop Generative Simulation Platform for Autonomous Driving	ICCV 2025
InfiniCube	InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models	ICCV 2025
DiST-4D	DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation	ICCV 2025
UniFuture	Seeing the Future, Perceiving the Future: A Unified Driving World Model for Future Generation and Perception	arXiv 2025
Nexus	Decoupled Diffusion Sparks Adaptive Scene Generation	arXiv 2025
Challenger	Challenger: Affordable Adversarial Driving Video Generation	arXiv 2025
Cosmos-Drive	Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models	arXiv 2025

4️⃣ Scene Reconstructors

⏲️ In chronological order, from the earliest to the latest.

Model	Paper	Venue	Website	GitHub
3DGS	3D Gaussian Splatting for Real-Time Radiance Field Rendering	TOG 2023
StreetGaussian	Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting	ECCV 2024
4DGF	Dynamic 3D Gaussian Fields for Urban Areas	NeurIPS 2024
SCube	SCube: Instant Large-Scale Scene Reconstruction using VoxSplats	NeurIPS 2024
HUGS	HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting	CVPR 2024
MagicDrive3D	MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes	arXiv 2024
S3Gaussian	S3Gaussian: Self-Supervised Street Gaussians for Autonomous Driving	arXiv 2024
VDG	VDG: Vision-Only Dynamic Gaussian for Driving Simulation	arXiv 2024
UniGaussian	UniGaussian: Driving Scene Reconstruction from Multiple Camera Models via Unified Gaussian Representations	arXiv 2024	-	-
Stag-1	Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model	arXiv 2024
DrivingRecon	DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving	arXiv 2024	-
OccScene	OccScene: Semantic Occupancy-Based Cross-Task Mutual Learning for 3D Scene Generation	arXiv 2024	-	-
SGD	SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior	WACV 2025	-	-
OmniRe	OmniRe: Omni Urban Scene Reconstruction	ICLR 2025
DriveDreamer4D	DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation	CVPR 2025
DeSiRe-GS	DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes	CVPR 2025	-
SplatAD	SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving	CVPR 2025
ReconDreamer	ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration	CVPR 2025
FreeSim	FreeSim: Toward Free-Viewpoint Camera Simulation in Driving Scenes	CVPR 2025		-
StreetCrafter	StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models	CVPR 2025
FlexDrive	FlexDrive: Toward Trajectory Flexibility in Driving Scene Reconstruction and Rendering	CVPR 2025	-	-
S-NeRF++	S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation	TPAMI 2025	-	-
InfiniCube	InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models	ICCV 2025
DiST-4D	Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation	ICCV 2025
DreamDrive	DreamDrive: Generative 4D Scene Modeling from Street View Images	arXiv 2025		-
Uni-Gaussians	Uni-Gaussians: Unifying Camera and Lidar Simulation with Gaussians for Dynamic Driving Scenarios	arXiv 2025		-
MuDG	MuDG: Taming Multi-Modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction	arXiv 2025
UniFuture	Seeing the Future, Perceiving the Future: A Unified Driving World Model for Future Generation and Perception	arXiv 2025
SceneCrafter	Unraveling the Effects of Synthetic Data on End-to-End Autonomous Driving Humanoid Robots	arXiv 2025	-
ReconDreamer++	ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation	arXiv 2025
RealEngine	RealEngine: Simulating Autonomous Driving in Realistic Context	arXiv 2025	-
GeoDrive	GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control	arXiv 2025	-
PseudoSimulation	Pseudo-Simulation for Autonomous Driving	arXiv 2025	-
Dreamland	Dreamland: Controllable World Creation with Simulator and Generative Models	arXiv 2025		-
Diff4Splat	Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models	arXiv 2025
SpaceTimePilot	SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time	arXiv 2025
FLAG-4D	FLAG-4D: Flow-Guided Local-Global Dual-Deformation Model for 4D Reconstruction	arXiv 2026	-
MotionCrafter	MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE	arXiv 2026

3. World Modeling from Occupancy Generation

1️⃣ Scene Representors

⏲️ In chronological order, from the earliest to the latest.

Model	Paper	Venue	Website	GitHub
SSD	Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data	arXiv 2023	-
SemCity	SemCity: Semantic Scene Generation with Triplane Diffusion	CVPR 2024
WoVoGen	WoVoGen: World Volume-Aware Diffusion for Controllable Multi-Camera Driving Scene Generation	ECCV 2024	-
UrbanDiff	Urban Scene Diffusion through Semantic Occupancy Map	arXiv 2024		-
DrivingSphere	DrivingSphere: Building A High-Fidelity 4D World for Closed-Loop Simulation	CVPR 2025
UniScene	UniScene: Unified Occupancy-Centric Driving Scene Generation	CVPR 2025
OccScene	OccScene: Semantic Occupancy-Based Cross-Task Mutual Learning for 3D Scene Generation	arXiv 2024	-	-
InfiniCube	InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models	ICCV 2025
Control-3D-Scene	Controllable 3D Outdoor Scene Generation via Scene Graphs	ICCV 2025
X-Scene	X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability	arXiv 2025

2️⃣ Occupancy Forecasters

⏲️ In chronological order, from the earliest to the latest.

Model	Paper	Venue	Website	GitHub
Emergent-Occ	Differentiable Raycasting for Self-supervised Occupancy Forecasting	ECCV 2022	-
FF4D	Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting	CVPR 2023
UniWorld	UniWorld: Autonomous Driving Pre-Training via World Models	arXiv 2023	-	-
UniScene	UniScene: Multi-Camera Unified Pre-Training via 3D Scene Reconstruction for Autonomous Driving	arXiv 2023	-
OccWorld	OccWorld: Learning A 3D Occupancy World Model for Autonomous Driving	ECCV 2024
Cam4DOcc	Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications	CVPR 2024	-
DriveWorld	DriveWorld: 4D Pre-Trained Scene Understanding via World Models for Autonomous Driving	CVPR 2024	-	-
OccSora	OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving	arXiv 2024
UnO	UnO: Unsupervised Occupancy Fields for Perception and Forecasting	CVPR 2024		-
LOPR	Self-Supervised Multi-Future Occupancy Forecasting for Autonomous Driving	arXiv 2024	-	-
FSF-Net	FSF-Net: Enhance 4D Occupancy Forecasting with Coarse BEV Scene Flow for Autonomous Driving	arXiv 2024	-	-
OccLLaMA	OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving	arXiv 2024	-	-
DOME	DOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model	arXiv 2024
GaussianAD	GaussianAD: Gaussian-Centric End-to-End Autonomous Driving	arXiv 2024
DFIT-OccWorld	An Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-Assisted Training	arXiv 2024	-	-
Drive-OccWorld	Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving	AAAI 2025
PreWorld	Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving	ICLR 2025	-
OccProphet	OccProphet: Pushing Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with Observer-Forecaster-Refiner Framework	ICLR 2025	-
RenderWorld	RenderWorld: World Model with Self-Supervised 3D Label	ICRA 2025	-	-
Occ-LLM	Occ-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models	ICRA 2025	-	-
EfficientOCF	Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting	CVPR 2025	-	-
DIO	DIO: Decomposable Implicit 4D Occupancy-Flow World Model	CVPR 2025	-	-
T³Former	Temporal Triplane Transformers as Occupancy World Models	arXiv 2025	-	-
UniOcc	UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving	ICCV 2025
COME	COME: Adding Scene-Centric Forecasting Control to Occupancy World Model	arXiv 2025	-
I²World	I²-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting	ICCV 2025	-
OmniNWM	OmniNWM: Omniscient Driving Navigation World Models	arXiv 2025	-
SparseOccVLA	SparseOccVLA: Bridging Occupancy and Vision-Language Models via Sparse Queries for Unified 4D Scene Understanding and Planning	arXiv 2026	-

3️⃣ Autoregressive Simulators

⏲️ In chronological order, from the earliest to the latest.

Model	Paper	Venue	Website	GitHub
SemCity	SemCity: Semantic Scene Generation with Triplane Diffusion	CVPR 2024
XCube	XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies	CVPR 2024
PDD	Pyramid Diffusion for Fine 3D Large Scene Generation	ECCV 2024
OccSora	OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving	arXiv 2024
DynamicCity	DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes	ICLR 2025
DrivingSphere	DrivingSphere: Building A High-Fidelity 4D World for Closed-Loop Simulation	CVPR 2025
InfiniCube	InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models	ICCV 2025
X-Scene	X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability	arXiv 2025
PrITTI	PrITTI: Primitive-Based Generation of Controllable and Editable 3D Semantic Scenes	arXiv 2025

4. World Modeling from LiDAR Generation

1️⃣ Data Engines

⏲️ In chronological order, from the earliest to the latest.

Model	Paper	Venue	Website	GitHub
DUSty	Learning to Drop Points for LiDAR Scan Synthesis	IROS 2021
LiDARGen	Learning to Generate Realistic LiDAR Point Clouds	ECCV 2022	-
DUSty v2	Generative Range Imaging for Learning Scene Priors of 3D LiDAR Data	WACV 2023
UltraLiDAR	UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation	CVPR 2023		-
Copilot4D	Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion	ICLR 2024		-
R2DM	LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models	ICRA 2024
ViDAR	Visual Point Cloud Forecasting enables Scalable Autonomous Driving	CVPR 2024	-
LiDiff	Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion	CVPR 2024	-
LiDM	Towards Realistic Scene Generation with LiDAR Diffusion Models	CVPR 2024	-
RangeLDM	RangeLDM: Fast Realistic LiDAR Point Cloud Generation	ECCV 2024	-
Text2LiDAR	Text2LiDAR: Text-Guided LiDAR Point Cloud Generation via Equirectangular Transformer	ECCV 2024	-
LiDARGRIT	Taming Transformers for Realistic LiDAR Point Cloud Generation	arXiv 2024	-
BEVWorld	BEVWorld: A Multimodal World Simulator for Autonomous Driving via Scene-Level BEV Latents	arXiv 2024	-
SDS	Simultaneous Diffusion Sampling for Conditional LiDAR Generation	arXiv 2024	-	-
DiffSSC	DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models	IROS 2025	-	-
HoloDrive	HoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving	arXiv 2024	-	-
LOGen	LOGen: Toward LiDAR Object Generation by Point Diffusion	arXiv 2024
OLiDM	OLiDM: Object-Aware LiDAR Diffusion Models for Autonomous Driving	AAAI 2025
X-Drive	X-Drive: Cross-Modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios	ICLR 2025	-
LidarDM	LidarDM: Generative LiDAR Simulation in a Generated World	ICRA 2025
LiDAR-EDIT	LiDAR-EDIT: LiDAR Data Generation by Editing the Object Layouts in Real-World Scenes	ICRA 2025
R2Flow	Fast LiDAR Data Generation with Rectified Flows	ICRA 2025
WeatherGen	WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusion	CVPR 2025	-
LiDPM	LiDPM: Rethinking Point Diffusion for Lidar Scene Completion	IV 2025
HERMES	HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation	ICCV 2025
SuperPC	SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization	CVPR 2025		-
SPIRAL	SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding	NeurIPS 2025
3DiSS	Towards Generating Realistic 3D Semantic Training Data for Autonomous Driving	arXiv 2025	-
Distill-DPO	Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion	arXiv 2025	-
DriveX	DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving	arXiv 2025	-	-
OpenDWM	OpenDWM: Open Driving World Models	arXiv 2025	-
RadarGen	RadarGen: Automotive Radar Point Cloud Generation from Cameras	arXiv 2025
La La LiDAR	La La LiDAR: Large-Scale Layout Generation from LiDAR Data	AAAI 2026	-	-
LiDARCrafter	LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences	AAAI 2026
Veila	Veila: Panoramic LiDAR Generation from a Monocular RGB Image	ICRA 2026	-	-

2️⃣ Action Forecasters

⏲️ In chronological order, from the earliest to the latest.

Model	Paper	Venue	Website	GitHub
Copilot4D	Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion	ICLR 2024		-
ViDAR	Visual Point Cloud Forecasting enables Scalable Autonomous Driving	CVPR 2024	-
BEVWorld	BEVWorld: A Multimodal World Simulator for Autonomous Driving via Scene-Level BEV Latents	arXiv 2024	-
HERMES	HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation	ICCV 2025
DriveX	DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving	arXiv 2025	-	-

3️⃣ Autoregressive Simulators

⏲️ In chronological order, from the earliest to the latest.

Model	Paper	Venue	Website	GitHub
HoloDrive	HoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving	arXiv 2024	-	-
LidarDM	LidarDM: Generative LiDAR Simulation in a Generated World	ICRA 2025
OpenDWM	OpenDWM: Open Driving World Models	arXiv 2025	-
LiDARCrafter	LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences	arXiv 2025

5. Applications

1️⃣ Autonomous Driving

Model	Paper	Venue	Website	GitHub
OccSora	OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving	arXiv 2024	-
DFIT-OccWorld	An Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-Assisted Training	arXiv 2024	-	-
LiDARCrafter	LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences	arXiv 2025
UniSim	UniSim: A Neural Closed-Loop Sensor Simulator	CVPR 2023		-
Panacea	Panacea: Panoramic and Controllable Video Generation for Autonomous Driving	CVPR 2024
Delphi	Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation	arXiv 2024
DriveDreamer-2	DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation	AAAI 2025
Panacea+	Panacea+: Panoramic and Controllable Video Generation for Autonomous Driving	arXiv 2024		-
MiLA	MiLA: Multi-View Intensive-Fidelity Long-Term Video Generation World Model for Autonomous Driving	arXiv 2025	-
GAIA-2	GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving	arXiv 2025		-

2️⃣ Robotics

Model	Paper	Venue	Website	GitHub
Habitat 2.0	Habitat 2.0: Training Home Assistants to Rearrange Their Habitat	arXiv 2021	-	-
VLMPS	Visual Language Maps for Robot Navigation	ICRA 2023
-	Foundation Models in Robotics: Applications, Challenges, and the Future	IJRR 2024	-
RoboDreamer	RoboDreamer: Learning Compositional World Models for Robot Imagination	arXiv 2024
BEHAVIOR	BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities	CoRL 2025
BridgeV2W	BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks	arXiv 2026		-

3️⃣ Video Games & XR

Model	Paper	Venue	Website	GitHub
ILVE	Interactive Latent Variable Evolution for the Generation of Minecraft Structures	ICFDG 2021	-	-
ProcTHOR	ProcTHOR: Large-Scale Embodied AI Using Procedural Generation	NeurIPS 2022
WorldGPT	WorldGPT: Empowering LLM as Multimodal World Model	ACM MM 2024	-
WorldExplorer	WorldExplorer: Towards Generating Fully Navigable 3D Scenes	SIGGRAPH Asia 2025
Text2World	Text2World: Benchmarking Large Language Models for Symbolic World Model Generation	arXiv 2025
FlexWorld	FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis	arXiv 2025
Hunyuan-GameCraft	Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition	arXiv 2025
HunyuanWorld 1.0	HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels	arXiv 2025
MGVQ	MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-Group Quantization	arXiv 2025	-
EvoWorld	EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory	arXiv 2025	-
ViewRope	Geometry-Aware Rotary Position Embedding for Consistent Video World Model	arXiv 2026	-	-
MIND	MIND: Benchmarking Memory Consistency and Action Control in World Models	arXiv 2026

4️⃣ Digital Twins

Model	Paper	Venue	Website	GitHub
DynamicCity	DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes	ICLR 2025
UrbanScene3D	Capturing, Reconstructing, and Simulating: the UrbanScene3D Datase	ECCV 2022
UrbanWorld	UrbanWorld: An Urban World Model for 3D City Generation	arXiv 2024
GaussianCity	GaussianCity: Generative Gaussian Splatting for Unbounded 3D City Generation	CVPR 2025
SceneDiffuser++	SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model	CVPR 2025	-	-
CityGenAgent	Imagine a City: CityGenAgent for Procedural 3D City Generation	arXiv 2026		-

5️⃣ Other Topics

Model	Paper	Venue	Website	GitHub
-	Interpreting Physics in Video World Models	arXiv 2026	-	-

6. Other Resources

Tutorials

Talks & Seminars

7. Acknowledgements