GestureHYDRA: Semantic Co-speech Gesture Synthesis via Hybrid Modality Diffusion Transformer and Cascaded-Synchronized Retrieval-Augmented Generation Paper • 2507.22731 • Published Dec 30, 2025 • 2
ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration Paper • 2604.01043 • Published 10 days ago • 11
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing Paper • 2603.11593 • Published 29 days ago • 25