RESEARCH PAPERYear 2026
DreamDojo: A Real-Time Robot World Model from Large-Scale Human Videos
Classification
View four quadrants- Major category
- WAMs
- Quadrant
- Not applicable
- Architecture
- Not applicable
- Prediction paradigm
- Not applicable
- Subcategories
- Neural world simulatorsLatent action pretraining
- Source review status
- Verified from primary sources
Category review. DreamDojo adapts a video foundation model to action-conditioned robot dynamics, and a separate policy/value pipeline uses its predicted candidate futures for planning. This is a task-specific world-model-and-control system, not the Cosmos or WAN component it builds upon. Reading evidence
Contribution
A contribution summary has not been added yet.
Abstract
An abstract has not been added yet.
Affiliations
Not listed in the collection.