UniSwap: Streaming Audio-Visual Identity Swapping for Talking Videos
Paper • 2608.11752 • Published • 20
AI & ML interests
multi-subject preserving generation
Recent Activity
View all activity
jamesliu1217
authored 4
papers 2 days ago
LiveAnimate: Stable Long-Form Streaming Human Animation in Real-Time
Paper • 2608.11745 • Published • 21
AVA-Encoder: Towards Agent-Native Video Representation Learning
Paper • 2608.12313 • Published • 14
What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems
Paper • 2608.07565 • Published • 28
jamesliu1217
authored a
paper 20 days ago
yychai
authored 6
papers 27 days ago
HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement
Paper • 2607.18217 • Published • 61
DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation
Paper • 2606.26058 • Published • 67
Graceful Forgetting in Generative Language Models
Paper • 2505.19715 • Published
Foundation Cures Personalization: Recovering Facial Personalized Models' Prompt Consistency
Paper • 2411.15277 • Published
Few-Shot Font Generation by Learning Fine-Grained Local Styles
Paper • 2205.09965 • Published
Effective Quantization for Diffusion Models on CPUs
Paper • 2311.16133 • Published • 5
jamesliu1217
authored a
paper 27 days ago
jamesliu1217
authored a
paper 3 months ago
jamesliu1217
submitted a
paper to Daily Papers 3 months ago
jamesliu1217
authored a
paper 4 months ago
jamesliu1217
authored 3
papers 8 months ago
Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model
Paper • 2403.07764 • Published • 1
Stable-Hair v2: Real-World Hair Transfer via Multiple-View Diffusion Model
Paper • 2507.07591 • Published
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Paper • 2512.04677 • Published • 179
jamesliu1217
authored 2
papers about 1 year ago