Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression Paper • 2512.05081 • Published 5 days ago • 28
MATRIX: Mask Track Alignment for Interaction-aware Video Generation Paper • 2510.07310 • Published Oct 8 • 35
DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization Paper • 2402.09812 • Published Feb 15, 2024 • 16