arxiv:2604.14148
Liyang Chen
leoniuschen
ยท
AI & ML interests
Multimodal Video Generation
Recent Activity
authored a paper about 11 hours ago
From Inpainting to Editing: A Self-Bootstrapping Framework for Context-Rich Visual Dubbing authored a paper about 11 hours ago
DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation authored a paper about 12 hours ago
Seedance 2.0: Advancing Video Generation for World ComplexityOrganizations
None yet
models 0
None public yet
datasets 0
None public yet