◼︎Bibliographic information Paul Yoo, Jiaxian Guo, Yutaka Matsuo, Shixiang Shane Gu. “DreamSparse: Escaping from Plato’s Cave with 2D Diffusion Model Given Sparse Views.” Neural Information Processing Systems (NeurIPS 2023) ◼︎Overview Synthesizing novel view images from a few views is a challenging but practical problem. Existing methods often struggle with producing high-quality results or necessitate per-object…
◼︎Bibliographic information Hitoshi Nakanishi, Masahiro Suzuki, Yutaka Matsuo: HAWK-Net: Hierarchical Attention Weighted Top-K Network for High-resolution Image Classification ◼︎Overview To handle high-resolution images on finite computational resources, many research has been conducted on hierarchical networks to load features in only the most meaningful local regions. However, it is difficult to determine the correct number and…
Sorry, this entry is only available in Japanese. For the sake of viewer convenience, the content is shown below in the alternative language. You may click the link to switch the active language.
坂田教授・各務教授・田中准教授とともに、松尾教授が企画・監修を務める「ディープテック起業実践演習」の申込みを10/4まで受け付けております。多くのエキスパート登壇に加え、最終発表は総長の前で発表、さらに優秀者はコミュニティ“DICE”への参加の他、選抜式の海外研修などの機会があります。また、履修による単位の付与対象は、東京大学大学院生、東京工業大学大学院生その他の単位互換協定校在籍生約30-40名（所属研究科、学年不問）とします。多くの皆様からのチャレンジをお待ちしています！
詳細はこちらをご覧ください
→https://entredu.t.u-tokyo.ac.jp/2023a/
◼︎書誌情報 Xin Zhang，Shixiang Shane Gu, Yutaka Matsuo, Yusuke Iwasawa : Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains 人工知能学会論文誌, 第38巻 6号 J-STAGE ◼︎概要 Domain generalization (DG) is a difficult transfer learning problem aiming to learn a generalizable model for unseen domains. Recent foundation models (FMs) are robust to many distribution shifts and, therefore,…
松尾が登壇したG1ベンチャー2023の記事が公開されました。
Sorry, this entry is only available in Japanese. For the sake of viewer convenience, the content is shown below in the alternative language. You may click the link to switch the active language.
松尾研究室主催の公開講座「世界モデルと知能 2023」を開講します。
受講を希望される方は下記ページを参考にしてください。
Mr. Hiroki Furuta, a second-year doctoral student in our laboratory, has been selected in the “SCIENCE & TECHNOLOGY & LOCAL” category of “FORBES JAPAN 30 UNDER 30 2023”. For details, please see the official website below. https://forbesjapan.com/feat/30under30/2023/honorees/?cat=stl <Award comment> This is a very prestigious award and I feel honored to receive it. My sincere appreciation…
Press Release: Matsuo Laboratory, The University of Tokyo Release of Weblab-10B: A 10 Billion-Parameter Bilingual Language Model Supporting Japanese and English ※ The following is a partial English translation of the press release issued on August 22, 2023. Please refer to the Japanese version for the original. Original: Press Release_2023/08/22 Tokyo, [2023/08/22] —…
Matsuo-lab organized and conducted a program called “LLM Special Boot Camp,” where participants could learn about deep learning and generative AI through lectures and hands-on exercises. Among the attendees were Prime Minister Kishida and Assistant Prime Minister Murai. (August 14, 2023) For more details, please refer to the following news articles: ▼Asahi https://www.asahi.com/articles/ASR8G6X84R8GUTFK002.html?iref=pc_photo_gallery_breadcrumb ▼Sankei…
日本語