Taekyung Ki's picture

Taekyung Ki

taekyungki

·

https://taekyungki.github.io

taekyungki

AI & ML interests

Ph.D. Student at KAIST

Recent Activity

upvoted a paper about 11 hours ago

EXAONE 4.5 Technical Report

upvoted a paper 7 days ago

Do World Action Models Generalize Better than VLAs? A Robustness Study

upvoted a paper 11 days ago

EgoSim: Egocentric World Simulator for Embodied Interaction Generation

View all activity

Organizations

authored 2 papers 3 months ago

Self-Refining Video Sampling

Paper • 2601.18577 • Published Jan 26 • 25

Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

Paper • 2601.00664 • Published Jan 2 • 57

authored a paper 10 months ago

Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models

Paper • 2506.07177 • Published Jun 8, 2025 • 23

authored 3 papers over 1 year ago

StyleLipSync: Style-based Personalized Lip-sync Video Generation

Paper • 2305.00521 • Published Apr 30, 2023

Learning to Generate Conditional Tri-plane for 3D-aware Expression Controllable Portrait Animation

Paper • 2404.00636 • Published Mar 31, 2024

FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait

Paper • 2412.01064 • Published Dec 2, 2024 • 47