I am interested in deep generative models such as GANs, diffusion models, and flow matching.
Affiliation
Apr 2020–Mar 2024Undergraduate School of Electrical and Electronic Engineering, Kyoto University
Apr 2024–Mar 2026Master's course of Department of Technology Management for Innovation, Graduate School of Engineering, University of Tokyo (Matsuo & Iwasawa Lab)
Apr 2026–PresentDoctoral course of Department of Technology Management for Innovation, Graduate School of Engineering, University of Tokyo (Matsuo & Iwasawa Lab)
Publications
International Conference (Peer-reviewed)
Yuta Oshima, Daiki Miyake, Kohsei Matsutani, Yusuke Iwasawa, Masahiro Suzuki, Yutaka Matsuo, and Hiroki Furuta, "Multibanana: A challenging benchmark for multi-reference text-to-image generation," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, pp. 448–460.
Daiki Miyake, Akihiro Iohara, Yu Saito, and Toshiyuki Tanaka, "Negative-prompt inversion: Fast image inversion for editing with text-guided diffusion models," 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025, pp. 2063–2072.
Domestic Conference (Non-peer-reviewed)
Daiki Miyake, Masahiro Suzuki, and Yutaka Matsuo, "Frequency-ordered Autoregressive Image Generation Model with Adaptive Scheduling," 2026 Annual Conference of the Japanese Society for Artificial Intelligence, 2026.
Daiki Miyake, Masahiro Suzuki, and Yutaka Matsuo, "Minimizing Wasserstein distance by discriminator for flow matching," 2025 Annual Conference of the Japanese Society for Artificial Intelligence, 2025.
