FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait
Paper
•
2412.01064
•
Published
•
47
•
8
Taekyung Ki
taekyungki
AI & ML interests
Ph.D. Student at KAIST
Recent Activity
upvoted
a
paper
2 days ago
THINKSAFE: Self-Generated Safety Alignment for Reasoning Models
upvoted
a
paper
6 days ago
Advancing Open-source World Models
authored
a paper
8 days ago
Self-Refining Video Sampling
Organizations
commented
a
paper
10 months ago
commented
a
paper
12 months ago