I have two papers accepted at #ACL2026 🎉
My first-author paper (w/ @MasahiroKaneko_, @ayaniwa1213, @preslav_nakov, @chokkanorg) proposes ExaGPT, an interpretable AI text detector that identifies a text by checking whether it shares more similar spans with human-written or machine-generated texts from a datastore. It presents these spans as evidence, allowing users to assess how reliably correct the decision is.
See you in San Diego! 🇺🇸
@aclmeeting#NLP#LLM
A co-authored paper on multi-image spatial reasoning was accepted at #ICML2026 🇰🇷!
Big shoutout to the lead author, Masanari Oi @stjohn2007 for all the hard work!
Our paper accepted to #ICML2026 🇰🇷(first author)!
This paper is on budget-aligned test-time scaling of LLMs.
It is my first ML conference paper!
Huge thanks to my co-authors ! @dai0NLP@chokkanorg
Preprint: arxiv.org/abs/2602.09574
More details soon!
Also at #ICLR2026 🇧🇷: Presenting Best-of-∞ on behalf of lead author @jkomiyama_ — principled Bayesian stopping that approximates the N→∞ majority-voting limit, plus optimal LLM-ensemble weights via MILP!
🕓25th April, 10:30 AM
📍Pavilion 4, #4710
w/ @jkomiyama_@stillpedant
Excited to present SureLock at #ICLR2026 🇧🇷 — a principled decoding method that locks converged tokens in Masked Diffusion Language Models, cutting 30–50% FLOPs at same quality!
w/ @Bollegala@MasahiroKaneko_@chokkanorg
🕙 Friday, 24th April, 10:30 AM
📍Pavilion 3 (#826)
I have four papers accepted at #ACL2026 🥳
LLMs can give the right answer for the wrong reason. My first-author paper w/ @Bollegala, @eltimster shows that checking how a model thinks, not just its final answer, reveals hidden social biases across 8 languages & 13 bias categories.
I’m in San Diego for #NeurIPS2025! I’ll be presenting a poster on Dec 3 from 11:00 AM to 2:00 PM about how sharing a model’s thinking processes can influence jailbreak success rates, with takeaways from both theoretical and experimental studies 😃
neurips.cc/virtual/2025/loc/…