Taekyung Ki

TAEKYUNG KI

I am a researcher at DeepBrainAI (alternative military service) working on generative models and computer vision.

Bio: In December 2023, I joined DeepBrainAI as a researcher on computer vision and generative models. I was a researcher at AITRICS working in the same field. I started research on deep learning in February 2021. I received M.S in mathematics in February 2021, and B.S. in mathematics in February 2019.

I am interested in the following research topics:

Generative models (Score and Flow Matching, etc.)
3D Gaussian Splatting and Neural Implicit Representation
Human video generation
Human motion representation learning
Audio-visual representation learning
Few-shot adaptation and personalization

If you have an interest in the above research topics, feel free to drop me an e-mail.

Mail Twitter Scholar Github LinkedIn

News

[Dec. 2024] New preprint out. FLOAT, audio-driven talking portrait generation with latent flow matching
[July 2024] One paper accepted to ECCV 2024
[Dec. 2023] I moved to DeepBrainAI (alternative military service until Mar. 2025)
[July 2023] One paper accepted to ICCV 2023
[Mar. 2022] Alternative military service starting at AITRICS

Publications

* : Equal contribution, † : Corresponding author

FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait
Taekyung Ki, Dongchan Min, Gyeongsu Chae
arXiv 2024
Paper | ProjectPage |

@article{ki2024float,
    title={FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait},
    author={Ki, Taekyung and Min, Dongchan and Chae, Gyeongsu},
    journal={arXiv preprint arXiv:2412.01064},
    year={2024}
    }

Learning to Generate Conditional Tri-plane for 3D-aware Expression Controllable Portrait Animation
Taekyung Ki, Dongchan Min, Gyeongsu Chae
European Conference on Computer Vision (ECCV) 2024, Milano, Italy
Paper | ProjectPage |

 @inproceedings{ki2025learning,
    title={Learning to Generate Conditional Tri-plane for 3D-aware Expression Controllable Portrait Animation},
    author={Ki, Taekyung and Min, Dongchan and Chae, Gyeongsu},
    booktitle={European Conference on Computer Vision},
    pages={476--493},
    year={2025},
    organization={Springer}
    }

StyleLipSync: Style-based Personalized Lip-sync Video Generation
Taekyung Ki^*, Dongchan Min^*
IEEE/CVF International Conference on Computer Vision (ICCV) 2023, Paris, France
Paper | ProjectPage | Supp | ArXiv | Code |

 @InProceedings{Ki_2023_ICCV,
        author    = {Ki, Taekyung and Min, Dongchan},
        title     = {StyleLipSync: Style-based Personalized Lip-sync Video Generation},
        booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
        month     = {October},
        year      = {2023},
        pages     = {22841-22850}
        }

Deep Scattering Network with Max-pooling
Taekyung Ki, Youngmi Hur^†
IEEE 2021 Data Compression Conference (DCC), Snowbird UT, USA
Paper | Code |

 @InProceedings{ki2021deep, 
        author = {Taekyung Ki and Youngmi Hur}, 
        title = {Deep Scattering Network with Max-pooling}, 
        booktitle = {2021 Data Compression Conference, DCC 2021}, 
        year = {2021}
        }

Awards and Honors

[Oct. 2021] 1st Prize Winner, NLP-based Math-Word Problem Track in 2021 AI Grand Challenge (AGC), funded by Ministry of Science and ICT.
[Feb. 2019] Graduation with top honors in mathematics

- This website is based on the lightweight and easy-to-use template from Michael Niemeyer .