RESEARCH PAPER
LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE
Classification
View four quadrants- Major category
- Benchmarks & simulators
- Quadrant
- Not applicable
- Architecture
- Not applicable
- Prediction paradigm
- Not applicable
- Subcategories
- Neural world simulators
- Source review status
- Verified from primary sources
Category review. LongScape trains context-routed diffusion experts for variable-length embodied video chunks. Supplied action annotations segment training videos, but inference generates videos from an image/instruction without producing robot controls. It is a task-specific world simulator rather than a reusable video foundation model. 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.