Yoshinari Fujinuma (藤沼祥成)

prof_pic.jpg

I’m currently a member of technical staff at Patronus AI. Prior to joining Patronus AI, I was a member of technical staff at Cantina Labs and a senior applied scientist at AWS AI Labs. I also earned a computer science PhD with focus on cross-lingual NLP from University of Colorado Boulder.

Fill free to ping me on Bluesky, Twitter, Github, or by E-mail. (E-mail is the best way to contact me.)

My CV is here.

If you want to have a casual chat with me, feel free to grab a spot at this Calendly link.

Fun Facts:

news

Apr 8, 2026 Our paper titled “Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge” is accepted to ACL Findings 2026!
Apr 4, 2026 Our new preprint titled “Unlocking Prompt Infilling Capability for Diffusion Language Models” is now on arXiv!
Oct 23, 2025 Uploaded the slides I used for my talk tour in Japan during 2023-2024 titled “Visually-Rich Documentを軸とした多言語処理の動向”

selected publications

2022

  1. acl2022_preview.png
    Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability
    Yoshinari Fujinuma, Jordan Boyd-Graber, and Katharina Kann
    In Proceedings of the Association for Computational Linguistics (ACL), 2022

2019

  1. acl2019_preview.png
    A Resource-Free Evaluation Metric for Cross-Lingual Word Embeddings based on Graph Modularity
    Yoshinari Fujinuma, Jordan Boyd-Graber, and Michael J. Paul
    In Proceedings of the Association for Computational Linguistics (ACL), 2019