Research
研究
研究業績
カテゴリー
研究領域
年
-
Efficient Object-Centric Representation Learning using Masked Generative Modeling
Akihiro Nakano, Masahiro Suzuki, Yutaka Matsuo
Transactions on Machine Learning Research (TMLR)
-
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)
-
ガウス過程潜在変数モデルとニューラルネットワークの統合によるマルチエージェント記号創発と潜在表現学習
中村友昭, 鈴木雅大, 谷口彰, 谷口忠大
日本ロボット学会誌（レター）, (2024)
-
Pixyz: a Python library for developing deep generative models
Masahiro Suzuki, Takaaki Kaneko, Yutaka Matsuo: Pixyz
Advanced Robotics, (2023)
-
Learning Global Spatial Information for Multi-View Object-Centric Models
Yuya Kobayashi, Masahiro Suzuki, Yutaka Matsuo
Advanced Robotics, (2023).
-
深層生成モデルによる背景情報を利用したシーン解釈
小林由弥, 鈴木雅大, 松尾豊
人工知能学会論文誌, 第38巻3号, (2023).
-
End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization
Shohei Taniguchi, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo
International Conference on Machine Learning (ICML 2023) July 2023.
-
Interaction-Based Disentanglement of Entities for Object-Centric World Models
Akihiro Nakano, Masahiro Suzuki, Yutaka Matsuo.
“InteractioInternational Conference on Learning Representations (ICLR2023)
-
Langevin Autoencoders for Learning Deep Latent Variable Models
Shohei Taniguchi, Yusuke Iwasawa, Wataru Kumagai, Yutaka Matsuo
Advances in Neural Information Processing Systems 35 (NeurIPS 2022).
-
A survey of multimodal deep generative models
Masahiro Suzuki, Yutaka Matsuo
Advanced Robotics.(2022)