Kazuki Yano

Ph.D. student @ Tohoku NLP Group.
Visiting Scholar @ Carnegie Mellon University.

I am a second-year Ph.D. student in Information Science at Fundamental AI lab (member of Tohoku NLP Group) at Tohoku University, advised by Prof. Jun Suzuki. I am also a Research Fellow in the JST BOOST Program. From October 2026 to March 2027, I am a Visiting Scholar at WAVLab, Language Technologies Institute, Carnegie Mellon University, advised by Prof. Shinji Watanabe.

My research focuses on large language model pre-training, training dynamics, and efficient model scaling, with recent work on multimodal foundation models and adapting text LLMs to new modalities.

yano.kazuki [at] dc.tohoku.ac.jp

News

Oct 2026 I joined Carnegie Mellon University as a Visiting Scholar at WAVLab, advised by Prof. Shinji Watanabe.
June 2026 I started as a Research Fellow at Amazon Japan G.K..
June 2026 My first author paper "Multimodal Depth Up-scaling" accepted at INTERSPEECH 2026.
Jan 2026 My first author paper "WSO" accepted at ICLR 2026.
Jan 2026 Two papers accepted at EACL 2026.