Hello World!

2024

• I will visit The University of Melbourne🇦🇺.
• I will attend ERCIM/JST Joint Workshop 2024 @Budapest🇭🇺.
• I will visit IIT @ Genova, University of Trento, and Fondazione Bruno Kessler @ Trento🇮🇹.
• I will attend ECCV to organize an ECCV workshop entitled “The Dark Side of Generative AIs and Beyond”.
• I will visit CENTAI @ Torino🇮🇹.
• I will visit Wien🇦🇹 to attend ICML.
• I will visit Aix-Marseille University @ Marseille🇫🇷 and present at Workshop on mathematical foundations of machine learning.
• I will vist A*STAR🇸🇬 and attend A*STAR-CFAR_RIKEN-AIP Workshop.
• I will attend RIKEN-IIT Joint Workshop in ML/AI.
• Our paper “Self-attention Networks Localize When QK-eigenspectrum Concentrates” (Bao et al.) is accepted at ICML.
• We will organize an ECCV workshop entitled “The Dark Side of Generative AIs and Beyond”.
• My research proposal is accepted at Initiative on Promotion of Supercomputing for Young or Women Researchers, Information Technology Center, The University of Tokyo.
• My research proposal is accepted at the Acceleration phase of JST ACT-X.
• I will present at Workshop on Functional Inference and Machine Intelligence.
• I will attend DL 2024.
• I will attend Machine Learning Summer School Okinawa as a program committee.

2023

• Our paper “Sketch-based Semantic Retrieval of Medical Images” (Kobayashi et al.) has been accepted at Medical Image Analysis.
• We will present “Non-commutative $C^\ast$-algebra Net” at QTML 2023 @ Geneve, Switzerland.
• Our paper “An Empirical Investigation of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration” (Naganuma & Hataya) has been accepted at ICCV Workshop 2023 on Uncertainty Quantification for Computer Vision.
• I will visit Nicolaus Copernicus University Poland from Sep 25th to 30th.
• Our paper “Will Large-scale Generative Models Corrupt Future Datasets?” has been accepted at ICCV 2023.
• Our paper “Towards AI-driven radiology education: A self-supervised segmentation-based framework for high-precision medical image editing” (Kobayashi et al.) has been accepted at MICCAI 2023 as an oral presentation.
• I will visit MILA at Montreal and attend CVPR in June.
• I will give a talk at UTokyo ICEPP.
• I will visit IIT at Genova in May.
• I will attend AISTATS at Valencia in April.
• I will visit Vietnam Institute for Advanced Study in Mathematics at Hanoi in April.
• I will visit EPFL CIS (Switzerland) and Fraunhofer IIS (Germany) from 8th to 15th March 2023.
• Our paper “Nyström Method for Accurate and Scalable Implicit Differentiation” has been accepted at AISTATS 2023.

2022

• I joined RIKEN ADSP and RIKEN AIP as a postdoctral researcher
• I recieved a doctal degree as a representative student of the graduate school of Information Science and Techonology, UTokyo.
• I defended my PhD thesis.
• I visited IIT (Genova, Italy) from July 8th.
• Our paper “DJMix: Unsupervised Task-agnostic Image Augmentation for Improving Robustness of Convolutional Neural Networks” is accepted to IJCNN 2022.

2021

• I visited IIT (Genova, Italy) from October 1st to December 17th.
• Our paper “Meta Approach to Data Augmentation Optimization” is accepted to WACV 2022.
• My research proposal has been accepted in JST’s ACT-X.
• Call for NeurIPS meetups is now out!
• I will present about Faster AutoAugment and its applications at AIP Open seminar.
• Our paper “Graph Energy-based Model for Molecular Graph Generation” is accepted at EBM workshop 2021 as a contributed talk.
• I will serve as a meetup chair for NeurIPS 2021.
• My research proposal has been accepted in JSPS’s travel grant.
• My research proposals have been accepted by Microsoft Research Asia, and RIISE at UTokyo.
• We organized a NeurIPS meetup and Women in ML in Japan: https://neuripsmeetupjapan.github.io.
• Our paper “Decomposing Normal and Abnormal Features of Medical Images for Content-based Image Retrieval” is accepted at ML4H 2020.

Preprints

• Ryuichiro Hataya, Kota Matsui, Masaaki Imaizumi, “Automatic Domain Adaptation by Transformers in In-Context Learning,” 2024. arXiv
• Yuka Hashimoto ${}^\star$, Ryuichiro Hataya ${}^\star$, “Quantum Circuit $C^\ast$-algebra Net,” 2024. arXiv
• Ryuichiro Hataya, Yoshinobu Kawahara, “Glocal Hypergradient Estimation with Koopman Operator,” 2024. arXiv
• Leonardo Placidi, Ryuichiro Hataya, Toshio Mori, Koki Aoyama, Hayata Morisaki, Kosuke Mitarai, and Keisuke Fujii, “MNISQ: A Large-Scale Quantum Circuit Dataset for Machine Learning on/for Quantum Computers in the NISQ era,” 2023. arXiv
• Ryuichiro Hataya ${}^\star$, and Yuka Hashimoto ${}^\star$, “Noncommutative $C^\ast$-algebra Net: Learning Neural Networks with Powerful Product Structure in $C^\ast$-algebra,” 2023. arXiv
• Ryuichiro Hataya, Hideki Nakayama, and Kazuki Yoshizoe, “Graph Energy-based Model for Substructure Preserving Molecular Design.” 2021. arxiv

Others

• Ryuichiro Hataya, Kota Matsui, Masaaki Imaizumi, “Automatic Domain Adaptation by Transformers in In-Context Learning, " ICML Workshop on In-Context Learning, 2024. (Peer Reviewed Short Paper)
• Ryuichiro Hataya, Masaaki Imaizumi, “Transformers as Stochastic Optimizers,” ICML Workshop on In-Context Learning, 2024. (Peer Reviewed Short Paper)
• Ryuichiro Hataya, Yuka Hashimoto, “Noncommutative $C^\ast$-algebra Nets,” International Conference on Quantum Techinques in Machine Learning, 2023. (Peer Reviewed Etended Abstract)
• Hiroki Naganuma, Ryuichiro Hataya, “An Empirical Investigation of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration,” ICCV 2023 Workshop on Uncertainty Quantification for Computer Vision, 2023. (Peer Reviewed Etended Abstract arXiv)
• Ryuichiro Hataya, Hideki Nakayama, and Kazuki Yoshizoe, “Graph Energy-based Model for Molecular Graph Generation.” EBM Workshop at ICLR 2021, 2021. (Peer Reviewed, Contributed Talk)
• Kazuma Kobayashi, Ryuichiro Hataya, Yusuke Kurose, Tatsuya Harada, and Ryuji Hamamoto, “Decomposing Normal and Abnormal Features of Medical Images for Content-based Image Retrieval.” Machine Learning for Health Workshop at NeurIPS 2020. (Peer Reviewed, Extended Abstract)
• Ryuichiro Hataya, Kumiko Matsui, and Tomoki Karasawa, “Learning to Identify Large Fossils using Deep Convolutional Neural Networks”, Geological Society of America Abstracts with Programs. Vol 52, No. 6, 2020.
• Ryuichiro Hataya, and Hideki Nakayama, “Unifying semi-supervised and robust leaning by mixup.” Workshop on Learning from Limited Labeled Data at ICLR 2019, 2019. (Peer Reviewed, Spotlight)

• “Gradient-based Hyperparameter Optimization for Deep Learning”, University of Trento, Oct, 2024.
• “Will Large-scale Generative Models Corrupt Future Datasets?”, (in Japanese) FIT2024, Sep, 2024.
• “Automatic Domain Adaptation by Transformers in In-Context Learning,” CIRM Workshop on mathematical foundations of machine learning, July 2024.
• “Automatic Domain Adaptation by Transformers in In-Context Learning,” A*STAR-CFAR_RIKEN-AIP Workshop, June 2024. Slides
• “Automatic Domain Adaptation by Transformers in In-Context Learning,” (in Japanese) Zapping Seminar, June 2024.
• “Gradient-based Hyperparameter Optimization”, (in Japanese) The 53rd IBISML seminar, March 2024.
• “Deep learning and data augmentation”, (in Japanese) The 4th TREFOIL seminar, Feburary 2024.
• “Determinantal point processes and their applications in machine learning,” (in Japanese) ICEPP seminar, June 2023．
• “Towards accurate and scalable gradient-based hyperparameter optimization,” Istituto Italiano di Tecnologia, May, 2023.
• “Noncommutative $C^\ast$-algebra Nets,” Japan-Vietnam AI Forum, April 2023.
• “Bayesian Model Selection for Deep Learning” (in Japanese), Zapping Seminar, 2022.
• “Data Augmentation for Deep Learning” (in Japanese), Ehime University DS Research Seminar, 2021.
• “Data Augmentation for Deep Learning” (in Japanese), Symposium on Sensing via Image Information, 2021.
• “Data Augmentation for Deep Learning” (in Japanese), StatsML Symposium, 2020.
• “Gradient-based Hyperparameter Optimization” (in Japanese), Zapping Seminar, 2020.

Talks

• “On Dataset Contamination by Large Generative Models” (In Japanese), JSAI, May 2024.
• “On Dataset Contamination by Large Generative Models” (In Japanese), Mathematical Informatics Research Workshop @ Akita, October 2023.
• “Stable Gradient-based Hyperparameter Optimization,” RIKEN AIP & NCU Workshops 2023, September 2023.