Advancing Open-source World Models

Mastering Diverse Domains through World Models

Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

Voyager is an interactive RGBD video generation model conditioned on camera input, and supports real-time 3D reconstruction.

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

Helios: Real Real-Time Long Video Generation Model

Fast and Universal 3D reconstruction model for versatile tasks

Mastering Atari with Discrete World Models

Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.

Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.

🌐 3D and 4D World Modeling: A Survey

Notably, GenAD & Dataset Survey. A Collection of Foundation Driving Models by OpenDriveLab. For Vista and DriveLM, please refer to individual page.

Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text prompt.

Dream to Control: Learning Behaviors by Latent Imagination

[ICLR 2026] rCM: SOTA JVP-Based Diffusion Distillation & Few-Step Video Generation & Scaling Up sCM/MeanFlow & Real-Time Autoregressive Video Diffusion

A most Frontend Collection and survey of vision-language model papers, and models GitHub repository. Continuous updates.

[CVPR 2026] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

[ACM CSUR 2025] Understanding World or Predicting Future? A Comprehensive Survey of World Models

Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.

A curated list of world models for autonomous driving.

Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation"

[ICCV 2025 ⭐highlight⭐] Implementation of VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory

DayDreamer: World Models for Physical Robot Learning

ICCV 2025 | TesserAct: Learning 4D Embodied World Models

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

World Model based Autonomous Driving Platform in CARLA :car:

Official Code for Epona: Autoregressive Diffusion World Model for Autonomous Driving (ICCV 2025)

A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.