Preprint
Jul 2026
DC-WAM: Dynamic-Centric Visual Supervision and Reasoning for World-Action Models
This work proposes DC-WAM, a dynamic-centric WAM framework that redistributes supervision and computation in the RGB video branch that consistently improves policy performance, especially under out-of-distribution perturbations in lighting, object appearance, and background texture.
Haoyuan Ji, Lingxiang Fan, Shang Su et al.
· 0 citations