About
Short Bio
I am a senior research scientist at SB Intuitions and a program-specific assistant professor at Kyoto University. Previously, I was a postdoctoral researcher at RIKEN. I received my PhD in Information Science and Technology from the University of Tokyo in 2022.
News
2026
- Our paper “RAPTOR: Accurate and Scalable Rational Polar Decomposition for the Muon Algorithm” has been accepted at ECML PKDD 2026. See you in September in Napoli🇮🇹.
- Our paper “Provable Data Scaling Law for Meta Learning via Complexity Minimization,” coauthored with K. Fukuchi (University of Tsukuba) and K. Matsui (Kyoto University), has been accepted at the High-dimensional Learning Dynamics (HiLD) workshop at ICML 2026.
- Our paper “Provable Target Sample Complexity Improvements as Pre‑Trained Models Scale,” coauthored with K. Fukuchi (University of Tsukuba) and K. Matsui (Kyoto University), has been accepted at AISTATS 2026.
Older news
2025
- I will visit Artois University and Inria Centre at the University of Bordeaux🇫🇷.
- I will join Kyoto University as a Program-Specific Assistant Professor.
- Our paper “An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration” (coauthored with H. Naganuma) is accepted at TMLR.
- I will visit Nicolaus Copernicus University @ Torun, Poland to attend NOW🇵🇱.
- My research proposal is accepted at JST BOOST Fostering Researchers in Emerging AI Program.
- I quit my position at RIKEN AIP and join SB Intuitions as a senior research scientist.
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.
Projects
Research Interests
- Gradient-based hyperparameter optimization
- Efficient and scalable deep learning
- Applications of machine learning to other research fields (medical imaging, palaeontology, chemistry, physics, etc.)
Publications
- 2026
- Sci. Data 2026MNISQ: A Large-Scale Quantum Circuit Dataset for Machine Learning in the NISQ Era
Leonardo Placidi, Ryuichiro Hataya, Toshio Mori, Koki Aoyama, Hayata Morisaki, Kosuke Mitarai, Keisuke Fujii
Scientific Data, 2026PaperBibTeX
@article{placidi2026mnisq, author = {Placidi, Leonardo and Hataya, Ryuichiro and Mori, Toshio and Aoyama, Koki and Morisaki, Hayata and Mitarai, Kosuke and Fujii, Keisuke}, title = {{MNISQ}: A Large-Scale Quantum Circuit Dataset for Machine Learning in the {NISQ} Era}, journal = {Scientific Data}, year = {2026}, month = may, url = {https://www.nature.com/articles/s41597-026-07493-9}, } - ECML PKDD 2026RAPTOR: Accurate and Scalable Rational Polar Decomposition for the Muon Algorithm
Ryuichiro Hataya
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2026PaperBibTeX
@inproceedings{hataya2026raptor, author = {Hataya, Ryuichiro}, title = {{RAPTOR}: Accurate and Scalable Rational Polar Decomposition for the Muon Algorithm}, booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases}, year = {2026}, url = {https://link.springer.com/chapter/10.1007/978-3-032-37670-1_3}, } - AISTATS 2026Provable Target Sample Complexity Improvements as Pre-Trained Models Scale
Kazuto Fukuchi, Ryuichiro Hataya, Kota Matsui
International Conference on Artificial Intelligence and Statistics, 2026arXivBibTeX
@inproceedings{fukuchi2026provable, author = {Fukuchi, Kazuto and Hataya, Ryuichiro and Matsui, Kota}, title = {Provable Target Sample Complexity Improvements as Pre-Trained Models Scale}, booktitle = {International Conference on Artificial Intelligence and Statistics}, year = {2026}, } - ICML-W 2026Provable Data Scaling Law for Meta Learning via Complexity Minimization
Kazuto Fukuchi, Ryuichiro Hataya, Kota Matsui
ICML Workshop on High-dimensional Learning Dynamics, 2026 · Peer-reviewed short paperBibTeX
@inproceedings{fukuchi2026scaling, author = {Fukuchi, Kazuto and Hataya, Ryuichiro and Matsui, Kota}, title = {Provable Data Scaling Law for Meta Learning via Complexity Minimization}, booktitle = {ICML Workshop on High-dimensional Learning Dynamics}, year = {2026}, } - 2025
- TMLR 2025An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration
Hiroki Naganuma*, Ryuichiro Hataya*, Kotaro Yoshida, Ioannis Mitliagkas
Transactions on Machine Learning Research, 2025OpenReviewBibTeX
@article{naganuma2025empirical, author = {Naganuma, Hiroki and Hataya, Ryuichiro and Yoshida, Kotaro and Mitliagkas, Ioannis}, title = {An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration}, journal = {Transactions on Machine Learning Research}, year = {2025}, month = apr, } - 2024
- MedIA 2024Sketch-based Semantic Retrieval of Medical Images
Kazuma Kobayashi, Lin Gu, Ryuichiro Hataya, Takaaki Mizuno, Mototaka Miyake, Hirokazu Watanabe, Masamichi Takahashi, Yasuyuki Takamizawa, Yukihiro Yoshida, Satoshi Nakamura, Nobuji Kouno, Amina Bolatkan, Yusuke Kurose, Tatsuya Harada, Ryuji Hamamoto
Medical Image Analysis, 2024PaperBibTeX
@article{kobayashi2024sketch, author = {Kobayashi, Kazuma and Gu, Lin and Hataya, Ryuichiro and Mizuno, Takaaki and Miyake, Mototaka and Watanabe, Hirokazu and Takahashi, Masamichi and Takamizawa, Yasuyuki and Yoshida, Yukihiro and Nakamura, Satoshi and Kouno, Nobuji and Bolatkan, Amina and Kurose, Yusuke and Harada, Tatsuya and Hamamoto, Ryuji}, title = {Sketch-based Semantic Retrieval of Medical Images}, journal = {Medical Image Analysis}, volume = {92}, year = {2024}, month = feb, url = {https://www.sciencedirect.com/science/article/pii/S1361841523003201}, } - ICML 2024Self-attention Networks Localize When QK-eigenspectrum Concentrates
Han Bao, Ryuichiro Hataya, Ryo Karakida
International Conference on Machine Learning, 2024PaperBibTeX
@inproceedings{bao2024selfattention, author = {Bao, Han and Hataya, Ryuichiro and Karakida, Ryo}, title = {Self-attention Networks Localize When {QK}-eigenspectrum Concentrates}, booktitle = {International Conference on Machine Learning}, year = {2024}, url = {https://proceedings.mlr.press/v235/bao24b.html}, } - arXiv 2024Automatic Domain Adaptation by Transformers in In-Context Learning
Ryuichiro Hataya, Kota Matsui, Masaaki Imaizumi
arXiv, 2024arXivBibTeX
@misc{hataya2024automatic, author = {Hataya, Ryuichiro and Matsui, Kota and Imaizumi, Masaaki}, title = {Automatic Domain Adaptation by Transformers in In-Context Learning}, year = {2024}, eprint = {2405.16819}, archiveprefix = {arXiv}, } - arXiv 2024Quantum Circuit $C^\ast$-algebra Net
Yuka Hashimoto*, Ryuichiro Hataya*
arXiv, 2024arXivBibTeX
@misc{hashimoto2024quantum, author = {Hashimoto, Yuka and Hataya, Ryuichiro}, title = {Quantum Circuit $C^\ast$-algebra Net}, year = {2024}, eprint = {2404.06218}, archiveprefix = {arXiv}, } - arXiv 2024Glocal Hypergradient Estimation with Koopman Operator
Ryuichiro Hataya, Yoshinobu Kawahara
arXiv, 2024arXivBibTeX
@misc{hataya2024glocal, author = {Hataya, Ryuichiro and Kawahara, Yoshinobu}, title = {Glocal Hypergradient Estimation with {Koopman} Operator}, year = {2024}, eprint = {2402.02741}, archiveprefix = {arXiv}, } - ICML-W 2024Automatic Domain Adaptation by Transformers in In-Context Learning
Ryuichiro Hataya, Kota Matsui, Masaaki Imaizumi
ICML Workshop on In-Context Learning, 2024 · Peer-reviewed short paperBibTeX
@inproceedings{hataya2024icl, author = {Hataya, Ryuichiro and Matsui, Kota and Imaizumi, Masaaki}, title = {Automatic Domain Adaptation by Transformers in In-Context Learning}, booktitle = {ICML Workshop on In-Context Learning}, year = {2024}, } - ICML-W 2024Transformers as Stochastic Optimizers
Ryuichiro Hataya, Masaaki Imaizumi
ICML Workshop on In-Context Learning, 2024 · Peer-reviewed short paperBibTeX
@inproceedings{hataya2024stochastic, author = {Hataya, Ryuichiro and Imaizumi, Masaaki}, title = {Transformers as Stochastic Optimizers}, booktitle = {ICML Workshop on In-Context Learning}, year = {2024}, } - 2023
- ICCV 2023Will Large-scale Generative Models Corrupt Future Datasets?
Ryuichiro Hataya, Han Bao, Hiromi Arai
International Conference on Computer Vision, 2023PaperBibTeX
@inproceedings{hataya2023corrupt, author = {Hataya, Ryuichiro and Bao, Han and Arai, Hiromi}, title = {Will Large-scale Generative Models Corrupt Future Datasets?}, booktitle = {International Conference on Computer Vision}, year = {2023}, url = {https://openaccess.thecvf.com/content/ICCV2023/html/Hataya_Will_Large-scale_Generative_Models_Corrupt_Future_Datasets_ICCV_2023_paper.html}, } - MICCAI 2023Towards AI-driven Radiology Education: A Self-supervised Segmentation-based Framework for High-precision Medical Image Editing
Kazuma Kobayashi, Lin Gu, Ryuichiro Hataya, Mototaka Miyake, Yasuyuki Takamizawa, Sono Ito, Hirokazu Watanabe, Yukihiro Yoshida, Hiroki Yoshimura, Tatsuya Harada, Ryuji Hamamoto
Medical Image Computing and Computer-Assisted Intervention, 2023 · OralBibTeX
@inproceedings{kobayashi2023radiology, author = {Kobayashi, Kazuma and Gu, Lin and Hataya, Ryuichiro and Miyake, Mototaka and Takamizawa, Yasuyuki and Ito, Sono and Watanabe, Hirokazu and Yoshida, Yukihiro and Yoshimura, Hiroki and Harada, Tatsuya and Hamamoto, Ryuji}, title = {Towards {AI}-driven Radiology Education: A Self-supervised Segmentation-based Framework for High-precision Medical Image Editing}, booktitle = {Medical Image Computing and Computer-Assisted Intervention}, year = {2023}, } - AISTATS 2023Nyström Method for Accurate and Scalable Implicit Differentiation
Ryuichiro Hataya, Makoto Yamada
International Conference on Artificial Intelligence and Statistics, 2023arXivBibTeX
@inproceedings{hataya2023nystrom, author = {Hataya, Ryuichiro and Yamada, Makoto}, title = {Nystr{\"o}m Method for Accurate and Scalable Implicit Differentiation}, booktitle = {International Conference on Artificial Intelligence and Statistics}, year = {2023}, } - arXiv 2023Noncommutative $C^\ast$-algebra Net: Learning Neural Networks with Powerful Product Structure in $C^\ast$-algebra
Ryuichiro Hataya*, Yuka Hashimoto*
arXiv, 2023arXivBibTeX
@misc{hataya2023noncommutative, author = {Hataya, Ryuichiro and Hashimoto, Yuka}, title = {Noncommutative $C^\ast$-algebra Net: Learning Neural Networks with Powerful Product Structure in $C^\ast$-algebra}, year = {2023}, eprint = {2302.01191}, archiveprefix = {arXiv}, } - QTML 2023Noncommutative $C^\ast$-algebra Nets
Ryuichiro Hataya, Yuka Hashimoto
International Conference on Quantum Techniques in Machine Learning, 2023 · Peer-reviewed extended abstractBibTeX
@inproceedings{hataya2023qtml, author = {Hataya, Ryuichiro and Hashimoto, Yuka}, title = {Noncommutative $C^\ast$-algebra Nets}, booktitle = {International Conference on Quantum Techniques in Machine Learning}, year = {2023}, } - ICCV-W 2023An Empirical Investigation of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration
Hiroki Naganuma, Ryuichiro Hataya
ICCV Workshop on Uncertainty Quantification for Computer Vision, 2023 · Peer-reviewed extended abstractarXivBibTeX
@inproceedings{naganuma2023empirical, author = {Naganuma, Hiroki and Hataya, Ryuichiro}, title = {An Empirical Investigation of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration}, booktitle = {ICCV Workshop on Uncertainty Quantification for Computer Vision}, year = {2023}, } - 2022
- IJCNN 2022DJMix: Unsupervised Task-agnostic Image Augmentation for Improving Robustness of Convolutional Neural Networks
Ryuichiro Hataya, Hideki Nakayama
International Joint Conference on Neural Networks, 2022BibTeX
@inproceedings{hataya2022djmix, author = {Hataya, Ryuichiro and Nakayama, Hideki}, title = {{DJMix}: Unsupervised Task-agnostic Image Augmentation for Improving Robustness of Convolutional Neural Networks}, booktitle = {International Joint Conference on Neural Networks}, year = {2022}, } - WACV 2022Meta Approach to Data Augmentation Optimization
Ryuichiro Hataya, Jan Zdenek, Kazuki Yoshizoe, Hideki Nakayama
Winter Conference on Applications of Computer Vision, 2022PDFBibTeX
@inproceedings{hataya2022meta, author = {Hataya, Ryuichiro and Zdenek, Jan and Yoshizoe, Kazuki and Nakayama, Hideki}, title = {Meta Approach to Data Augmentation Optimization}, booktitle = {Winter Conference on Applications of Computer Vision}, year = {2022}, } - 2021
- MedIA 2021Decomposing Normal and Abnormal Features of Medical Images for Content-Based Image Retrieval of Glioma Imaging
Kazuma Kobayashi, Ryuichiro Hataya, Yusuke Kurose, Mototaka Miyake, Masamichi Takahashi, Akiko Nakagawa, Tatsuya Harada, Ryuji Hamamoto
Medical Image Analysis, 2021PaperBibTeX
@article{kobayashi2021decomposing, author = {Kobayashi, Kazuma and Hataya, Ryuichiro and Kurose, Yusuke and Miyake, Mototaka and Takahashi, Masamichi and Nakagawa, Akiko and Harada, Tatsuya and Hamamoto, Ryuji}, title = {Decomposing Normal and Abnormal Features of Medical Images for Content-Based Image Retrieval of Glioma Imaging}, journal = {Medical Image Analysis}, volume = {74}, year = {2021}, month = dec, url = {https://www.sciencedirect.com/science/article/pii/S1361841521002723}, } - ICASSP 2021Visualizing Association in Exemplar-based Classification
Taiga Kashima, Ryuichiro Hataya, Hideki Nakayama
International Conference on Acoustics, Speech, and Signal Processing, 2021BibTeX
@inproceedings{kashima2021visualizing, author = {Kashima, Taiga and Hataya, Ryuichiro and Nakayama, Hideki}, title = {Visualizing Association in Exemplar-based Classification}, booktitle = {International Conference on Acoustics, Speech, and Signal Processing}, year = {2021}, } - arXiv 2021Graph Energy-based Model for Substructure Preserving Molecular Design
Ryuichiro Hataya, Hideki Nakayama, Kazuki Yoshizoe
arXiv, 2021arXivBibTeX
@misc{hataya2021graph, author = {Hataya, Ryuichiro and Nakayama, Hideki and Yoshizoe, Kazuki}, title = {Graph Energy-based Model for Substructure Preserving Molecular Design}, year = {2021}, eprint = {2102.04600}, archiveprefix = {arXiv}, } - ICLR-W 2021Graph Energy-based Model for Molecular Graph Generation
Ryuichiro Hataya, Hideki Nakayama, Kazuki Yoshizoe
EBM Workshop at ICLR, 2021 · Contributed talkOpenReviewBibTeX
@inproceedings{hataya2021graphebm, author = {Hataya, Ryuichiro and Nakayama, Hideki and Yoshizoe, Kazuki}, title = {Graph Energy-based Model for Molecular Graph Generation}, booktitle = {EBM Workshop at ICLR}, year = {2021}, } - 2020
- ECCV 2020Faster AutoAugment: Learning Augmentation Strategies using Backpropagation
Ryuichiro Hataya, Jan Zdenek, Kazuki Yoshizoe, Hideki Nakayama
European Conference on Computer Vision, 2020PaperBibTeX
@inproceedings{hataya2020faster, author = {Hataya, Ryuichiro and Zdenek, Jan and Yoshizoe, Kazuki and Nakayama, Hideki}, title = {Faster {AutoAugment}: Learning Augmentation Strategies using Backpropagation}, booktitle = {European Conference on Computer Vision}, year = {2020}, url = {http://www.ecva.net/papers/eccv_2020/papers_ECCV/html/4830_ECCV_2020_paper.php}, } - ML4H 2020Decomposing Normal and Abnormal Features of Medical Images for Content-based Image Retrieval
Kazuma Kobayashi, Ryuichiro Hataya, Yusuke Kurose, Tatsuya Harada, Ryuji Hamamoto
Machine Learning for Health Workshop at NeurIPS, 2020 · Peer-reviewed extended abstractBibTeX
@inproceedings{kobayashi2020decomposing, author = {Kobayashi, Kazuma and Hataya, Ryuichiro and Kurose, Yusuke and Harada, Tatsuya and Hamamoto, Ryuji}, title = {Decomposing Normal and Abnormal Features of Medical Images for Content-based Image Retrieval}, booktitle = {Machine Learning for Health Workshop at NeurIPS}, year = {2020}, } - GSA 2020Learning to Identify Large Fossils using Deep Convolutional Neural Networks
Ryuichiro Hataya, Kumiko Matsui, Tomoki Karasawa
Geological Society of America Abstracts with Programs, 2020BibTeX
@inproceedings{hataya2020fossils, author = {Hataya, Ryuichiro and Matsui, Kumiko and Karasawa, Tomoki}, title = {Learning to Identify Large Fossils using Deep Convolutional Neural Networks}, booktitle = {Geological Society of America Abstracts with Programs}, volume = {52}, number = {6}, year = {2020}, } - 2019
- ICIP 2019LOL: Learning To Optimize Loss Switching Under Label Noise
Ryuichiro Hataya, Hideki Nakayama
International Conference on Image Processing, 2019BibTeX
@inproceedings{hataya2019lol, author = {Hataya, Ryuichiro and Nakayama, Hideki}, title = {{LOL}: Learning To Optimize Loss Switching Under Label Noise}, booktitle = {International Conference on Image Processing}, year = {2019}, } - ICLR-W 2019Unifying Semi-supervised and Robust Learning by Mixup
Ryuichiro Hataya, Hideki Nakayama
Workshop on Learning from Limited Labeled Data at ICLR, 2019 · SpotlightBibTeX
@inproceedings{hataya2019unifying, author = {Hataya, Ryuichiro and Nakayama, Hideki}, title = {Unifying Semi-supervised and Robust Learning by Mixup}, booktitle = {Workshop on Learning from Limited Labeled Data at ICLR}, year = {2019}, }
* equal contribution
Other Research Activities
Invited Talks
- “Developing Japanese Vision Language Models,” NOW, Nicolaus Copernicus University, Jan 2025.
older information
- “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.
Research Grants
- BOOST Fostering Researchers in Emerging AI Program, Japan Science and Technology Agency, ¥50M, 2025-2029.
older information
- Grant-in-Aid for Young Scientists, Japan Society for the Promotion of Science, ¥3.2M, 2025-2026.
- ACT-X Acceleration phase, Japan Science and Technology Agency, ¥5.0M, 2024.
- Grant-in-Aid for Research Activity Start-up, Japan Society for the Promotion of Science, ¥2.2M, 2023-2024.
- ACT-X, Japan Science and Technology Agency, ¥4.5M, 2021-2024.
- Overseas Challenge Program for Young Researchers by JSPS, ¥1.4M, 2021.
- Microsoft Research Asia Collaborative Research Program (D-CORE 2021) by MSRA, ¥1.0M, 2021.
- Sprouting Research RA’s in Value Exchange Engineering by RIISE@UTokyo, ¥2.0M, 2020-2022.
Awards
- Microsoft Research Asia D-Core Award, 2020.
- Best Student Paper Award, The 23rd Meeting on Image Recognition and Understanding, 2020.
Others
- Program Committee of MLSS Okinawa 2027.
- Program Committee of IBIS 2026.
- Reviewer for NeurIPS, ICCV, ICLR, CVPR, ICML, ECCV 2019~.
older information
- Organizer of ECCV 2024 Workshop The Dark Side of Generative AIs and Beyond.
- Organizer of YAML 2024.
- Program Committee of MLSS Okinawa 2024.
- Program Committee of IBIS 2023.
- Meetup Chair of NeurIPS, 2021.
- Organizer of NeurIPS meetup Japan & Women in ML, 2020.
- Volunteer for ICML, and ICLR, 2020.
Contact
Contact me via research@${last_name}.tokyo.