Masaru Isonuma
165 posts
@m_isonuma
JSPS overseas research fellow @EdinburghNLP #NLProc
Our paper has been accepted as a spotlight in the position paper track at #ICML2026 We argue that post-hoc opt-outs of copyrighted material from trained models (e.g., unlearning, guardrails) cannot legally cure infringement. arxiv.org/abs/2604.18649
#ICLR #ICLR2025 Tomorrow! Apr 26th🚨 Come check out our poster at #273 from 10:30 am to 12:30 pm! TLDR; Dataset distillation normally compresses data by matching model gradients. We reversed it: creating data that have opposite gradients and makes models unlearn toxicities.
New paper: "What's New in My Data? Novelty Exploration via Contrastive Generation," w/ @iatitov at @EdinburghNLP arxiv.org/abs/2410.14765 With no access to the data, but only access to the pre-trained and fine-tuned model, we can reveal novel aspects of the fine-tuning dataset.
I left Edinburgh and joined the National Institute for Informatics R&D Center for LLMs and the Tohoku Univ. Center for language AI research. I’m so grateful to @iatitov for hosting me in his group across two years. I learned a lot from him, resulting in fruitful research work.
〈プレスリリース〉国家戦略分野の若手研究者及び博士後期課程学生の育成事業（#BOOST）次世代AI人材育成プログラム（若手研究者支援）における令和6年度新規研究課題の決定について jst.go.jp/pr/info/info17… 325件の応募があり、80件の研究課題を採択しました。 #JST #科学技術振興機構
