Rethinking Video Generation Model for the Embodied World Paper • 2601.15282 • Published 22 days ago • 43
Rethinking Video Generation Model for the Embodied World Paper • 2601.15282 • Published 22 days ago • 43
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head Paper • 2601.07832 • Published Jan 12 • 52
MAGREF: Masked Guidance for Any-Reference Video Generation Paper • 2505.23742 • Published May 29, 2025 • 11