People
Genki Osada Chief Researcher, LY Research
Joined LY Corporation after working at Fuji Xerox (now Fujifilm) and Philips Japan. Obtained a Ph.D. in Engineering from the University of Tsukuba in 2022. Interested in unsupervised machine learning, with a recent focus on density estimation, latent spaces, manifolds, and their applications.
Publications
-
- CONFERENCE (INTERNATIONAL)
- Local Curvature Smoothing with Stein's Identity for Efficient Score Matching
- Genki Osada, Makoto Shing (Sakana AI), Takashi Nishide (University of Tsukuba)
- The 38th Annual Conference on Neural Information Processing Systems
- December 19, 2024
-
- CONFERENCE (INTERNATIONAL)
- Understanding Likelihood of Normalizing Flow and Image Complexity through the Lens of Out-of-Distribution Detection
- Genki Osada, Tsubasa Takahashi, Takashi Nishide (University of Tsukuba)
- Thirty-Eighth AAAI Conference on Artificial Intelligence
- March 24, 2024
-
- CONFERENCE (INTERNATIONAL)
- Frequency-aware GAN for Adversarial Manipulation Generation
- Peifei Zhu, Genki Osada, Hirokatsu Kataoka (LINE / AIST), Tsubasa Takahashi
- 2023 International Conference on Computer Vision
- October 02, 2023
-
- CONFERENCE (DOMESTIC)
- 書類偽装検出モデルの実現に向けた画像生成と学習方法の提案
- 八尋 一宇 (東京都大学), 長谷川 麟太郎 (慶應義塾大学), 岡本 大和, 長田 元気, 朱 佩菲, 片岡 裕雄 (LINE / AIST)
- 第29回画像センシングシンポジウム
- June 14, 2023
-
- CONFERENCE (INTERNATIONAL)
- Out-of-Distribution Detection with Reconstruction Error and Typicality-based Penalty
- Genki Osada, Takahashi Tsubasa, Budrul Ahsan (IBM), Takashi Nishide (University of Tsukuba)
- IEEE/CVF Winter Conference on Applications of Computer Vision
- January 03, 2023
-
- WORKSHOP (INTERNATIONAL)
- Mixed Samples Data Augmentation with Replacing Latent Vector Components in Normalizing Flow
- Genki Osada, Budrul Ahsan (IBM), Takashi Nishide (University of Tsukuba)
- 2022 Conference on Neural Information Processing Systems
- November 28, 2022