Takeru Miyato

Takeru Miyato

(Last updated: Feb.26, 2024)

Ph.D. student @ Autonomous Vision Group, University of Tübingen


E-mail : takeru.miyato(at)gmail.com


Google Scholar


Ph.D. student at Autonomous Vision Group, University of Tübingen under ELLIS Ph.D program. I am supervised by Andreas Geiger (UTübingen) and Max Welling (UvA). I am also working for Preferred Networks, Inc. as a part-time researcher.
I worked at ATR, Google Brain (as an intern) and did my Master at Integrated System Biology Labratory, Kyoto University.

Selected Publications

For the full publication list, please see my Google Scholar profile

  1. Takeru Miyato, Bernhard Jaeger, Max Welling, and Andreas Geiger
    GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers.
    ICLR, 2024.
    [project page] [code] [arXiv] [OpenReview]
  2. Masanori Koyama, Kenji Fukumizu, Kohei Hayashi, and Takeru Miyato
    Neural Fourier Transform: A General Approach to Equivariant Representation Learning.
    ICLR, 2024.
    [code] [arXiv] [OpenReview]
  3. Takeru Miyato*, Masanori Koyama*, and Kenji Fukumizu
    Unsupervised Learning of Equivariant Structure from Sequences.
    NeurIPS, 2022.
    [code] [arXiv] [OpenReview] [poster]
  4. Takeru Miyato, Shin-ichi Maeda, Masanori Koyama and Shin Ishii
    Virtual Adversarial Training : A Regularization Method for Supervised and Semi-Supervised Learning.
    IEEE TPAMI, 2019.
    [code (TF)] [code (Chainer)] [arXiv]
  5. Takeru Miyato, Toshiki Kataoka, Masanori Koyama and Yuichi Yoshida
    Spectral Normalization for Generative Adversarial Networks.
    ICLR, 2018. (accepted for oral presentation)
    [code] [code (on ImageNet)] [OpenReview]
  6. Takeru Miyato and Masanori Koyama
    cGANs with Projection Discriminator.
    ICLR, 2018.
    [code] [OpenReview]
  7. Takeru Miyato, Andrew M. Dai and Ian Goodfellow
    Adversarial Training Methods for Semi-Supervised Text Classification.
    ICLR, 2017.
    [code (Chainer, by @aonotas)] [code (TF)] [arXiv] [slide] [poster] [OpenReview]


Working Experiences

Hosted on GitHub Pages — Theme by orderedlist