Yuantian Huang

I am currently working as a research engineer on the Graphics Team at CyberAgent AI Lab.

Previously, I earned my Ph.D. in 2024 from the University of Tsukuba under the supervision of Assoc. Prof. Satoshi Iizuka and Prof. Kazuhiro Fukui.

My research interests span image and video editing and generation, computer graphics, and computer vision.

E-mail: huang_yuantian (at) cyberagent.co.jp

news

Jul 26, 2026	A co-author paper accepted to TMLR.
Mar 24, 2026	A co-author paper accepted to the CVPR 2026 Workshop on Video Generative Models: Benchmarks and Evaluation.
Jan 22, 2025	A co-author paper accepted to ICLR 2025 as an Oral.

selected publications

2024

Controllable Multi-domain Semantic Artwork Synthesis

Yuantian Huang, Satoshi Iizuka, Edgar Simo-Serra, and 1 more author

Computational Visual Media, 2024

Bib URL PDF Website Demo

@article{Huang2024CMSAS,
  author = {Huang, Yuantian and Iizuka, Satoshi and Simo-Serra, Edgar and Fukui, Kazuhiro},
  journal = {Computational Visual Media},
  title = {Controllable Multi-domain Semantic Artwork Synthesis},
  volume = {10},
  number = {2},
  pages = {355--373},
  year = {2024},
  publisher = {Springer},
  url = {https://doi.org/10.1007/s41095-023-0356-2}
}

2023

Free-View Expressive Talking Head Video Editing

Yuantian Huang, Satoshi Iizuka, and Kazuhiro Fukui

In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023

Top 3% Paper Recognition

Bib URL PDF Code Website Demo

@inproceedings{Huang2023FETE,
  author = {Huang, Yuantian and Iizuka, Satoshi and Fukui, Kazuhiro},
  booktitle = {ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {Free-View Expressive Talking Head Video Editing},
  year = {2023},
  pages = {1-5},
  doi = {10.1109/ICASSP49357.2023.10095745},
  note = {Top 3% Paper Recognition},
}