AI RESEARCH
Fast-WAM: Do World Action Models Need Test-time Future Imagination?
arXiv CS.AI
•
ArXi:2603.16666v1 Announce Type: cross World Action Models (WAMs) have emerged as a promising alternative to Vision-Language-Action (VLA) models for embodied control because they explicitly model how visual observations may evolve under action. Most existing WAMs follow an imagine-then-execute paradigm, incurring substantial test-time latency from iterative video denoising, yet it remains unclear whether explicit future imagination is actually necessary for strong action performance.