RESEARCH PAPER

Learning to Use Imagination: Progress-Conditioned Future Utilization for World Action Models

Yijie Zhu; Zitong Yu; Wei Li; Hui Ma; Wen Li; Rui Shao; Liqiang Nie

Classification

View four quadrants
Major category
WAMs
Quadrant
Not assigned
Architecture
Not assigned
Prediction paradigm
Not assigned
Source review status
Not assigned

Category review. A progress encoder uses executed action-observation feedback to modulate future-token attention in a joint video-action generator that produces control chunks. Reading evidence

AT A GLANCE

Contribution

ProWAM learns execution progress from recent action–observation feedback and recurrent memory, then uses that state to redistribute imagined-future attention inside a joint video–action policy. Its strongest evidence combines executed manipulation results with ablations separating progress estimation from future utilization.

Abstract

An abstract has not been added yet.

Affiliations

Harbin Institute of Technology (Shenzhen), China; Great Bay University, Dongguan, China; University of Electronic Science and Technology of China, Chengdu, China