Research PreviewVideo Gentextvideo3dUpdated June 5, 2026
AnchorWorld
Model Overview
AnchorWorld is a undisclosed-parameter model developed by Academic/Research. Released on 2026-06-05.
📊 Quick Specs
Specification Table
| Specification | Value |
|---|---|
| Parameters | undisclosed |
| Task | video-generation |
| Modality | text, video, 3d |
| License | Other/Custom |
| Type | research-preview |
✨ Key Features
- Embodied 3D Human Motion Control (SMPL-X)
- Hybrid-View Exogenous Training Supervision
- Evolvable Anchor-View Scene Customization
- Flow-Matching Diffusion Transformer (DiT) Architecture
- Unified 3D World Coordinate Grounding
🔗 Resources
- Hugging Face: AnchorWorld
- GitHub: Repository
- Paper: arXiv
- Website: Project Page
📜 License & Access
Other/Custom — See repository for specific license details.
Key Features
Embodied 3D Human Motion Control (SMPL-X)
Feature 01✦
Hybrid-View Exogenous Training Supervision
Feature 02✦
Evolvable Anchor-View Scene Customization
Feature 03✦
Flow-Matching Diffusion Transformer (DiT) Architecture
Feature 04✦
Unified 3D World Coordinate Grounding
Feature 05✦
You might also want to compare
Verified Sources
Tags
research-previewworld-modelegocentric-simulationvideo-generation3d-motion
Model Specs
Parameters
Undisclosed
Context Window
undisclosed
License
Other/Custom
Deployment
self-hostable
Resources & Links
Curator Notes
Partially enriched via migration on 2026-07-25. Manual review recommended.
Compare Specs
Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.
Compare Model