OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer Paper β’ 2604.24762 β’ Published 15 days ago β’ 13
RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation Paper β’ 2601.05241 β’ Published Jan 8 β’ 24
Frame In-N-Out Collection The model zoo for "Unbounded Controllable Image-to-Video Generation." β’ 8 items β’ Updated Mar 2 β’ 2
MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning Paper β’ 2509.22281 β’ Published Sep 26, 2025 β’ 33
Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data Paper β’ 2507.07095 β’ Published Jul 9, 2025 β’ 56