RESEARCH PAPER
WorldAgen: Unified State-Action Prediction with Test-Time World Model Training
Classification
View four quadrants- Major category
- WAMs
- Architecture
- One Model
- Prediction paradigm
- Joint prediction
- Source review status
- Not assigned
Category review. Shared Transformer heads predict actions and action-conditioned future observations; observation-based test-time training adapts the shared model from executed transitions. Action and future-observation heads share the Transformer with action-first factorization. Reading evidence
Contribution
WorldAgen shares a Transformer between action prediction and future-observation prediction, then adapts the shared representation using exploratory target-environment transitions. Simulated manipulation improves after observation-only test-time training (TTT), while implementation ambiguities and unreported uncertainty limit the strength of the generalization claim.
Abstract
An abstract has not been added yet.
Affiliations
Northwestern University