LayerFlow: A Unified Model for Layer-aware Video Generation Paper • 2506.04228 • Published Jun 4 • 13
LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning? Paper • 2503.19990 • Published Mar 25 • 36
VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control Paper • 2501.01427 • Published Jan 2 • 55