This is a navigation system learning project

SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark, led by Hillbot, Inc.

This code corresponds to simulation environments used as part of the MimicGen project.

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models. CVPR 2025.

OASim: an Open and Adaptive Simulator based on Neural Rendering for Autonomous Driving

Generate a Autonumous driving world model by mesh prior.

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

Image composition toolbox: everything you want to know about image composition or object insertion

VaViM and VaVAM: Autonomous Driving through Video Generative Modeling.

An open source code repository of driving world models, with training, inferencing, evaluation tools, and pretrained checkpoints.

Video Generation Foundation Models: https://saiyan-world.github.io/goku/

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction

hybrid SLAM system designed for mapping environments

An official implementation of RoDyGS: Robust Dynamic Gaussian Splatting for Casual Videos

Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation

Generative Models by Stability AI

Pytorch implementation for "DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes"

[ICLR 2025 Oral] The official implementation of "Diffusion-Based Planning for Autonomous Driving with Flexible Guidance"

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

[ECCV 2024] WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation

[NeurIPS 2023] Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models

MetaDrive: Lightweight driving simulator for everyone

Simulator-conditioned Driving Scene Generation

Collect some World Models for Autonomous Driving (and Robotic) papers.