Open-source alternatives to Vega

ICLR24 Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

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

GaussianDWM addresses three core challenges in autonomous driving world models:

WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving Yifang Xu 1   Jiahao Cui 1   Feipeng Cai 2   Zhihao Zhu 1   Hanlin Shang 1   Shan Luan 1   Mingwang Xu 1   Neng Zhang 2   Yaoyi Li 2   Jia Cai 2  …

\[Paper\](https://arxiv.org/pdf/2508.11428)

Official implementation of "WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation".

JAX implementation of the PIWM. PIWM is a novel model-based reinforcement learning method built upon DreamerV3. It is typically designed for autonomous driving tasks. It learns to model the driving environment from an individual perspective and enhances the transition dynamic by explicitly…

x Initial commit - x Model zoo - x arXiv version - Code for nuPlan dataset (3D Occupancy Prediction) - Code for LightWheelOcc dataset (3D Occupancy Prediction)

2024/12/04 🚀 We have released the weights for some scenarios based on Street Gaussians, as well as the NTA-IoU calculation script. - 2024/11/29 🚀 Repository Initialization.

HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation

The official code an data for the benchmark with baselines for our paper: Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications

Accepted by ECCV 2024

World models, especially in autonomous driving, are trending and drawing extensive attention due to its capacity for comprehending driving environments. The established world model holds immense potential for the generation of high-quality driving videos, and driving policies for safe…

ICLR 2025 OccProphet: Pushing Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with Observer-Forecaster-Refiner Framework

Epona : Autoregressive Diffusion World Model for Autonomous Driving ICCV 2025 Kaiwen Zhang , Zhenyu Tang , Xiaotao Hu , Xingang Pan , Xiaoyang Guo , Yuan Liu , Jingwei Huang , Yuan Li , Qian Zhang , Xiaoxiao Long ✝ , Xun Cao , Wei Yin §

Yingyan Li, Yuqi Wang, Yang Liu, Jiawei He, Lue Fan† and Zhaoxiang Zhang† [📄 Paper (arXiv:2504.01941)](https://arxiv.org/abs/2504.01941)

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

NRSeg: Noise-Resilient Learning for BEV Semantic Segmentation via Driving World Models IEEE TIP 2026

https://github.com/user-attachments/assets/693ba6d3-46ba-4529-ae3f-dc8a3456e4cc

ICLR2026 ResWorld: Temporal Residual World Model for End-to-End Autonomous Driving

FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving 🎉🎉NeurIPS 2025 spotlight🎉🎉

World Model Powered by Sparse and Dynamic Queries

NEWS - ⭐ GenAD: OpenDV Dataset (CVPR 2024 Hightlight) - Vista (NeurIPS 2024) - DriveLM (ECCV 2024 Oral) - DriveData Survey (SCIENTIA SINICA Informationis 2024) - Related Work Collection --> - OpenScene - OpenLane-V2 Update