Skip to content
View ymgw55's full-sized avatar
8 followers · 9 following

Achievements

Achievement: QuickdrawAchievement: YOLOAchievement: StarstruckAchievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Achievements

Achievement: QuickdrawAchievement: YOLOAchievement: StarstruckAchievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Highlights

  • Pro

Block or report ymgw55

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ymgw55/README.md

GitHub Stats Card

Organizations

Shimodaira Lab, Kyoto University

education

  • DCS in Machine Learning, Shimodaira Lab, Department of System Science, Informatics, Kyoto University, present

  • MCS in Machine Learning, Shimodaira Lab, Department of System Science, Informatics, Kyoto University, 2022

  • BSc in Mathematics, Nakano Lab, Department of Mathematics, Science, Kyoto University, 2020

Biography

I'm a doctoral student at Shimodaira Lab, Department of System Science, Informatics, Kyoto University. My research interests lie in Machine Learning, especially Natural Language Processing and Optimal Transport.

Pinned Loading

  1. shimo-lab/Universal-Geometry-with-ICA shimo-lab/Universal-Geometry-with-ICA Public

    Discovering Universal Geometry in Embeddings with ICA

    Python 16

  2. WSMD WSMD Public

    Improving word mover’s distance by leveraging self-attention matrix

    Python 9

  3. Axis-Tour Axis-Tour Public

    Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings

    Python

  4. Cosine-Similarity-via-ICA Cosine-Similarity-via-ICA Public

    Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings

    1

  5. Norm-and-Variance Norm-and-Variance Public

    Norm of Mean Contextualized Embeddings Determines their Variance

  6. SCESAME SCESAME Public

    Zero-Shot Edge Detection with SCESAME: Spectral Clustering-based Ensemble for Segment Anything Model Estimation

    C 15 1