Kazuhiro Takemoto (@kztakemoto) 's Twitter Profile
Kazuhiro Takemoto

@kztakemoto

竹本和広. 九州工大 教授. Professor at Kyutech. Network Science, Machine Learning Security, and Bioinformatics.

ID: 42547844

linkhttps://kztakemoto.github.io calendar_today26-05-2009 02:48:07

9,9K Tweet

1,1K Followers

643 Following

BarzelLab (@baruchbarzel) 's Twitter Profile Photo

Paper Paper Paper 📢 Out in Nature Communications Observing network dynamics through sentinel nodes Here: nature.com/articles/s4146… Thanks N. Masuda and N. MacLaren for leading this collaboration Here is what all the fuss is about 👇👇👇

Paper Paper Paper 📢
Out in <a href="/NatureComms/">Nature Communications</a> 
Observing network dynamics through sentinel nodes
Here: nature.com/articles/s4146…

Thanks N. Masuda and N. MacLaren for leading this collaboration

Here is what all the fuss is about 👇👇👇
Saumitra Kulkarni (@saumitranetsci) 's Twitter Profile Photo

Excited to share our new paper in npj Journals Science of Food! 🎉 Using network science, we map ingredient pairings and uncover unique “culinary fingerprints.” w/ Claudio C, Federico Battiston, Iacopo Iacopini, Andrea Santoro and vito latora Network Science Institute nature.com/articles/s4153…

九州工業大学 (@kyutech) 's Twitter Profile Photo

【TOPICS】筑紫女学園高等学校1年生を対象に2025年度第2回進路選択特別講演会を実施しました kyutech.ac.jp/whats-new/topi… 「そのときAIは誰を見殺しにするか?~AI倫理を考える~」と題した進路選択特別講演を実施。 究極の選択をテーマに、生徒の皆さんとAIの判断について活発な議論を交わしました。

【TOPICS】筑紫女学園高等学校1年生を対象に2025年度第2回進路選択特別講演会を実施しました
kyutech.ac.jp/whats-new/topi…

「そのときAIは誰を見殺しにするか?~AI倫理を考える~」と題した進路選択特別講演を実施。

究極の選択をテーマに、生徒の皆さんとAIの判断について活発な議論を交わしました。
Kazuhiro Takemoto (@kztakemoto) 's Twitter Profile Photo

These findings challenge theoretical models that assume accurate self-awareness of network positions and highlight the need to reconsider the implications for key-player interventions in public health, education, and organizational contexts.

Kazuhiro Takemoto (@kztakemoto) 's Twitter Profile Photo

Results from our short-term visiting student (April-June 2025). Congrats! 短期訪問学生(2025.4-6)の成果です。おめでとう。ieeexplore.ieee.org/document/11252…

Kazuhiro Takemoto (@kztakemoto) 's Twitter Profile Photo

修士学生がGIW XXXIV ISCB-Asia 2025で医療分野でのVLMの敵対的脆弱性に関する口頭発表しました。Shiroshima, a master student, gave a talk on adversarial vulnerability of VLM for healthcare in GIW XXXIV ISCB-Asia 2025. academic.oup.com/bib/article/26…

松本 (@gggtta) 's Twitter Profile Photo

日本バイオインフォマティクス学会によるオープンアクセスの日本語総説誌『JSBi Bioinformatics Review』の第6巻2号を公開しました。今号では、総説記事2編を掲載します。jstage.jst.go.jp/browse/jsbibr/…

Albert-László Barabási (@barabasi) 's Twitter Profile Photo

From blood vessels to neurons, physical networks are modeled as wires optimized for length. In nature we how surface minimization, via a surprising link to string theory, explains brain and vascular architecture, including neuronal sprouting. Paper: barabasi.com/science/public…

From blood vessels to neurons, physical networks are  modeled as wires optimized for length. In <a href="/Nature/">nature</a>  we how surface minimization, via a surprising link to string theory, explains brain and vascular architecture, including neuronal sprouting.
Paper: barabasi.com/science/public…
Eduardo G. Altmann (@eduardogaltmann) 's Twitter Profile Photo

"Meso-scale structures in signed networks", new preprint with Wei Zhang, Olga Boichak (Olga Boїchak🇺🇦), Tristram J Alexander, and Tiago P. Peixoto (Tiago Peixoto) arxiv.org/abs/2512.11281

"Meso-scale structures in signed networks", new preprint with Wei Zhang, Olga Boichak (<a href="/olgarithmic/">Olga Boїchak🇺🇦</a>), Tristram J Alexander, and Tiago P. Peixoto (<a href="/tiagopeixoto/">Tiago Peixoto</a>) 

arxiv.org/abs/2512.11281
Yoshihiro Yamanishi (@yoshihiroyamani) 's Twitter Profile Photo

2026年度人工知能学会全国大会(JSAI2026)で、AI創薬のオーガナイズドセッション(OS)を開催します。皆様の参加をお待ちしております。 申込(演題・要旨)締切:1/28、原稿(2〜4ページ)締切:2/18。 OS-24 AI駆動型創薬研究の新潮流(田部井靖生,山西芳裕,瀧川一学) ai-gakkai.or.jp/jsai2026/os/

Kazuhiro Takemoto (@kztakemoto) 's Twitter Profile Photo

プレプリント。スケールさえすればLLMには道徳的判断能力が出現する・・・かも。 arxiv.org/abs/2601.17637

Kazuhiro Takemoto (@kztakemoto) 's Twitter Profile Photo

プレプリント:Graph Attention Networkを用いてダイレクトリプログラミング誘導因子を高精度で予測するとともにその生物的解釈も行える方法を提案しました。弊学科 濱野研 修士学生の成果(私はお手伝い)。 biorxiv.org/content/10.648…

Kazuhiro Takemoto (@kztakemoto) 's Twitter Profile Photo

Preprint: We propose a method for highly accurate prediction of direct reprogramming induction factors using Graph Attention Networks with biological interpretability. biorxiv.org/content/10.648…

Kazuhiro Takemoto (@kztakemoto) 's Twitter Profile Photo

[論文出版] 淡水微細藻類の最大公開データセットLMFM-12を構築し、顕微鏡画像分類におけるドメイン特化データセットの重要性を示しました。博士学生の研究です。 sciencedirect.com/science/articl…

Kazuhiro Takemoto (@kztakemoto) 's Twitter Profile Photo

[New Paper] We developed LMFM-12, the largest public freshwater microalgae dataset. Our analysis demonstrates the importance of domain-specific datasets for microscopy-based classification. PhD student research. sciencedirect.com/science/articl…

NetScience (@net_science) 's Twitter Profile Photo

Scaling laws for function diversity and specialization across socioeconomic and biological complex systems pnas.org/doi/abs/10.107…

elvis (@omarsar0) 's Twitter Profile Photo

Can AI agents agree? Communication is one of the biggest challenges in multi-agent systems. New research tests LLM-based agents on Byzantine consensus games, scenarios where agents must agree on a value even when some participants behave adversarially. The main finding: valid

Can AI agents agree?

Communication is one of the biggest challenges in multi-agent systems.

New research tests LLM-based agents on Byzantine consensus games, scenarios where agents must agree on a value even when some participants behave adversarially.

The main finding: valid