Robot-Factored World Models via Robot Rendering
cs.RO, cs.CV
Submitted: 2026-07-24
Updated: 2026-11-02
Code: https://github.com/aigc-apps/VideoX-Fun
Terminology
Sources
- DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
- World-Gymnast: Training Robots with Reinforcement Learning in a World Model
- WorldGym: World Model as An Environment for Policy Evaluation
- Mastering Diverse Domains through World Models
- Cosmos World Foundation Model Platform for Physical AI
- DreamGen: Unlocking Generalization in Robot Learning through Video World Models
- GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving
- AdaWorld: Learning Adaptable World Models with Latent Actions
- CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
- CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- Learning Latent Action World Models In The Wild
- AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
- DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory
- MotionStream: Real-Time Video Generation with Interactive Motion Controls
- FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models
- Dexterous World Models
- Wan: Open and Advanced Large-Scale Video Generative Models
- DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation