A collection of useful papers and resources on World Models for Manipulation.
Created for the 1X World Model Challenge.
If you want to add a paper, rearrange papers, or create a new category, please contribue :^)
- A Drive in the office (Comma AI)
2024.5[blog]
- 1X World Model Challenge: world modeling challenge for humanoid robots
2024.8[code]
- A Survey on Vision-Language-Action Models for Embodied AI
arXiv 2024.5[paper] - Robot Learning in the Era of Foundation Models: A Survey
arXiv 2023.11[paper]
- UniSim: Learning Interactive Real-World Simulators
ICLR 2024[paper] [website] - RoboDreamer: Learning Compositional World Models for Robot Imagination
ICML 2024[paper] [code] [website] - IRASim: Learning Interactive Real-Robot Action Simulators
arXiv 2024.6[paper] [code] [website] - Structured World Models from Human Videos
RSS 2023[paper] [website] - Learning to Act from Actionless Videos through Dense Correspondences
2023.10[paper] [code] [website] - HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generator
ICIP 2022[paper] [website] - DayDreamer: World Models for Physical Robot Learning
CoRL 2022[paper] [code] [website]
- Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
ICLR 2024[paper] [website] - Mastering Memory Tasks with World Models ICLR 2024, oral [paper] [website]
- Genie: Generative Interactive Environments
arXiv 2024.2[paper] [website] - GAIA-1: A Generative World Model for Autonomous Driving
arXiv 2023.9[paper] [website] - Masked Autoencoding for Scalable and Generalizable Decision Making
arXiv 2023.5[paper] - Transformers are Sample-Efficient World Models
ICLR 2023[paper] [code] - Transformer-based World Models Are Happy With 100k Interactions
ICLR 2023[paper] [code] - Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models
NeurIPS 2022[paper] [code] [website] - Masked World Models for Visual Control
CoRL 2022[paper] [code] [website] - Dream to control: Learning Behaviors By Latent Imagination
ICLR 2020[paper] - World Models
NIPS 2018[paper] [website]
- Awesome World Models for Autonomous Driving [code]