Research
研究
研究業績
カテゴリー
研究領域
年
-
パーソナライズ画像生成における参照画像の複製効果の定量的評価と改善
大坂洋豊, 鈴木雅大, 松尾豊
情報処理学会論文誌, 2025
-
大規模画像言語モデルにおける事実性バイアスの体系的な分析
冨山翔司、山下佳威、 鈴木雅大、 落合桂一、松尾豊
情報処理学会論文誌
-
Efficient Object-Centric Representation Learning using Masked Generative Modeling
Akihiro Nakano, Masahiro Suzuki, Yutaka Matsuo
Transactions on Machine Learning Research (TMLR)
-
サマリレベルでの画像の利用法を用いたマルチモーダル翻訳手法の提案
冨山翔司, 味曽野雅史, 鈴木雅大, 落合桂一, 岩澤有祐, 松尾豊
知能と情報
-
The Geometry of Phase Transitions in Diffusion Models: Tubular Neighbourhoods and Singularities
Manato Yaguchi(*) , Kotaro Sakamoto(*) , Ryosuke Sakamoto(*) , Masato Tanabe(*) , Masatomo Akagawa(*) , Yusuke Hayashi(*) , Masahiro Suzuki, Yutaka Matsuo “The Geometry of Phase Transitions in Diffusion Models: Tubular Neighbourhoods and Singularities”. Transactions on Machine Learning Research (TMLR). (*) Equal Contribution
Transactions on Machine Learning Research (TMLR)
-
Disappearance of Timestep Embedding: A Case Study on Neural ODE and Diffusion Models
Bum Jun Kim, Yoshinobu Kawahara, Sang Woo Kim
Transactions on Machine Learning Research (TMLR)
-
Continual Pre-training on Character-Level Noisy Texts Makes Decoder-based Language Models Robust Few-shot Learners
Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa
Transactions of the Association for Computational Linguistics (TACL)
-
Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks
Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo
Transactions on Machine Learning Research (TMLR)
-
Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web
Hiroki Furuta, Yutaka Matsuo, Aleksandra Faust, Izzeddin Gur.
Transactions on Machine Learning Research (TMLR).
-
Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials
Hiroki Furuta, Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo
Transactions on Machine Learning Research (TMLR).