Mastering Diverse Domains through World Models
-
Updated
Apr 11, 2025 - Python
Mastering Diverse Domains through World Models
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.
Mastering Atari with Discrete World Models
Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
[CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving
Dream to Control: Learning Behaviors by Latent Imagination
A curated list of world models for autonomous driving. Keep updated.
DayDreamer: World Models for Physical Robot Learning
A most Frontend Collection and survey of vision-language model papers, and models GitHub repository. Continuous updates.
ICCV 2025 | TesserAct: Learning 4D Embodied World Models
[ICCV 2025 ⭐highlight⭐] Implementation of VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory
An open source code repository of driving world models, with training, inferencing, evaluation tools, and pretrained checkpoints.
A comprehensive survey of forging vision foundation models for autonomous driving, including challenges, methodologies, and opportunities.
World Model based Autonomous Driving Platform in CARLA 🚗
《多模态大模型:新一代人工智能技术范式》作者:刘阳,林倞
A structured implementation of MuZero
Code for "DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT"
[ICLR 2025 Oral] PyTorch code for the paper "Open-World Reinforcement Learning over Long Short-Term Imagination"
Implementation of a framework for Genie2 in Pytorch
A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.
Add a description, image, and links to the world-models topic page so that developers can more easily learn about it.
To associate your repository with the world-models topic, visit your repo's landing page and select "manage topics."