Mitigating Forgettingin Language Modelsfor Efficient Learning

I study training methods that suppress forgetting, retain prior knowledge, and improve performance with lower compute.

For collaboration, internships, or talks, please contact me.View all publications

Selected Publications

2025PreprintarXiv

An Open and Reproducible Deep Research Agent for Long-Form Question Answering

Ikuya Yamada, Wataru Ikeda, Ko Yoshida, Mengyu Ye, Hinata Sugimoto, Masatoshi Suzuki, Hisanori Ozaki, Jun Suzuki

RAGDeep Research Agent

We present an open deep research system for long-form question answering, selected as a winning system in the text-to-text track of the MMU-RAG competition at NeurIPS 2025.

PDF DOI Code

2026OtherNLP 2026

MoEアーキテクチャによる破滅的忘却の抑制効果の評価

Hinata Sugimoto, Jaesung Lee, Ko Yoshida, Jun Suzuki

LLMMoECatastrophic Forgettingpretraining

We evaluate the effectiveness of MoE architecture in suppressing catastrophic forgetting during pretraining.

PDF

News

Dec 22, 2025Awarded "Best Static Evaluation (Open-Source) in Text-to-Text" at NeurIPS 2025 Competition MMU-RAGent.