LARS D. WELCH; SVEN WATKINS; TARUN M. RAMAN; MASSIMO WAGNER. Multi-Modal Robotic World Modeling via Physically Consistent Video Generation and Cross-View Representation Alignment. Computational Intelligence Systems, [S. l.], v. 4, n. 1, 2026. Disponível em: https://scivexus.org/index.php/CIS/article/view/365. Acesso em: 27 may. 2026.