PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
Paper ⢠2603.25730 ⢠Published ⢠50
AIGC, Segmentation, World Model
EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing
GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering