postdoc @sciencetokyo_en, prev @Penn @mbzuai
Tokyo, Japan
Joined May 2020
- Tweets173
- Following821
- Followers478
- Likes3.6K
Pinned Tweet
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
Ryuto Koike retweeted
I’ll be giving a tutorial on diffusion language models at AACL-IJCNLP 2026 on Nov. 10
w/ @Bollegala
🔗 dllm-aacl.github.io/
(Slides coming soon!)
#aacl2026 @aaclmeeting
💭Grateful for the opportunity to organize my perspective on this fast-moving field and share it with the NLP community. This will be my first tutorial, so it’s a bit of a personal challenge for me as well. Looking forward to the discussions :)
Ryuto Koike retweeted
Introducing Pangram Image 1.0, our newest model for AI image and video detection.
Pangram Image 1.0 identifies 99.2% of AI-generated images while maintaining a 0.27% FPR.
It integrates into our Chrome extension, so you can check for AI images and video anywhere on the web.
Ryuto Koike retweeted
We've been working towards AI image and video detection for months, and now it's finally here.
There were a lot of challenges along the way. There are way more AI image/video models than frontier LLMs, and their outputs are more diverse. Most phone cameras, including iPhones, do some level of AI postprocessing to add detail to real photos.
We had to build a model that's robust to this postprocessing while understanding the difference between AI edits and fully AI-generated visuals.
I think the heatmap feature is a really important step forward and a huge differentiator over other models which typically report scores as a binary confidence.
Please try it out!!
Ryuto Koike retweeted
🚨 [Token][ization] Paper Alert 🚨
Tokenization is a wildly understudied area of language modeling despite it having effects across all of NLP. Over the past ~8 months, 32 (!) tokenizer researchers put together the most comprehensive survey of the field. Check it out!
Ryuto Koike retweeted
#MIRU2026 では、ICML2026に採択されたMulti-view spatial reasoningに関する研究を発表します！
- 8/4（火）招待講演 1A：コンベンションホール講演会場① 9:30–10:30（口頭：5分）
- 8/4（火）インタラクティブ IS1：イベント・展示ホール 16:00–18:00（ポスター）
初MIRU🤞
Ryuto Koike retweeted
Excited to share that our paper got accepted to COLM 2026!! 🎉
Huge thanks to my co-authors @Youmima1015 @stjohn2007 @sponddd @chokkanorg!
This paper introduces a method for synthesizing instruction-tuning datasets using contrastive decoding.
@COLM_conf
Thank you all for stopping by our poster at #ACL2026! That was a really great discussion :)
I’m heading to Seoul for #ICML2026!
(pic w/ @preslav_nakov)
Presenting today @ Grand Hall, 9:00-10:30.
Come say hi👋
Thanks to @MasahiroKaneko_ , @ayaniwa1213 , @preslav_nakov , @chokkanorg for the collaboration!
#ACL2026
Ryuto Koike retweeted
#NLPコロキウム での発表で使用した「攻めのAI安全性：必知論文N本🔥」の拡張版スライドを公開しました！
関連研究を追加し、内容がさらにパワーアップしています💪
ぜひご覧ください！
speakerdeck.com/kanekomasahi…
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!
Two first-author papers accepted to #ICML2026 🇰🇷 !
- Human-like multi-image spatial reasoning in multimodal LLMs (@silviasetitech @sponddd @dai0NLP Prof. Inoue @chokkanorg)
- Autoregressive direct preference optimization (Mahiro Ukai @MasahiroKaneko_ @chokkanorg Prof. Inoue)
Ryuto Koike retweeted
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!
Ryuto Koike retweeted
Our paper of #ICLR2026 🇧🇷 established a multilingual and regional benchmark for jailbreak-induced fake news generation, covering 34 regions and 22 languages! (w/ @ayaniwa1213, @eltimster)
📅 Apr. 24, 3:15–5:45 PM, #5315
📃 arxiv.org/abs/2603.01291
🤗 github.com/kanekomasahiro/ja…
Ryuto Koike retweeted
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
Ryuto Koike retweeted
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)
Ryuto Koike retweeted
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.
先月に博士（学術）学位をいただきました！また光栄なことに所属コースの修了代表に選出いただきました😊
指導教員の岡﨑先生@chokkanorgをはじめ、3年間関わってくださった皆様のおかげです。本当にありがとうございました。
引き続きどうぞよろしくお願いいたします🤝
Ryuto Koike retweeted
#NLP2026 では最優秀論文賞、最優秀賞、若手奨励賞×2、委員特別賞×2、ELYZA賞、サイバーエージェント賞を共著論文が受賞しました👐
主著者 (@stjohn2007, @sponddd, @koshiro_sa110, @ayaniwa1213, @yangliu_nlp) の皆様おめでとうございます🥳 また、運営＆審査員の皆様ありがとうございました！
