works on
benchmark dataset 1long-term video understanding 1multimodal world modeling 1spatial reasoning 1temporal continuity 1

From the 1 of 3 linked papers with an AI index.

collaborators
Showing cs.ROShow all

1 paper · 1 filter

cs.RO2026

FBFM: A Training-Free Asynchronous Feedback Mechanism for Flow-Matching in World-Action Models Execution

Peize Li, Ruimeng Zhang, Ru Zhang +3

Although world-action models (WAMs) enhance long-horizon robot control by predicting visual evolution before acting, long-horizon reliability demands repeated re-grounding in real…