FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait
Paper
•
2412.01064
•
Published
•
47
•
8
Taekyung Ki
taekyungki
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
TiDAR: Think in Diffusion, Talk in Autoregression
upvoted
a
paper
3 days ago
Adaptive Multi-Agent Response Refinement in Conversational Systems
upvoted
a
paper
4 days ago
Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion
Models
Organizations
commented
a
paper
7 months ago
commented
a
paper
9 months ago