Research
Publications
Category
Research Area
Year
-
WorldPack: Dynamic Frame Compression for Long-Context Video World Modeling
Yuta Oshima, Yusuke Iwasawa, Masahiro Suzuki, Yutaka Matsuo, Hiroki Furuta
Transactions on Machine Learning Research (TMLR), 2026
-
SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces
Yuta Oshima, Shohei Taniguchi, Masahiro Suzuki, Yutaka Matsuo
New Generation Computing (NGC), 2026
-
Enhancing Unimodal Latent Representations in Multimodal VAEs through Iterative Amortized Inference
Yuta Oshima, Masahiro Suzuki, Yutaka Matsuo
New Generation Computing (NGC), 2026
-
Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search
Yuta Oshima, Masahiro Suzuki, Yutaka Matsuo, Hiroki Furuta.
Advances in Neural Information Processing Systems (NeurIPS 2025), December 2025
-
Efficient Object-Centric Representation Learning using Masked Generative Modeling
Akihiro Nakano, Masahiro Suzuki, Yutaka Matsuo
Transactions on Machine Learning Research (TMLR), 2025
-
Model-based reinforcement learning using model mediators in dynamic multi-agent environments
今井翔太, 岩澤有祐, 松尾豊
人工知能学会論文誌, Vol.38, No.5, (2023)
-
Pixyz: a Python library for developing deep generative models
Masahiro Suzuki, Takaaki Kaneko, Yutaka Matsuo: Pixyz
Advanced Robotics, (2023)
-
World Models and Predictive Coding for Cognitive and Developmental Robotics
Tadahiro Taniguchi, Shingo Murata, Masahiro Suzuki, Dimitri Ognibene, Pablo Lanillos, Emre Ugur, Lorenzo Jamone, Tomoaki Nakamura, Alejandra Ciria, Bruno Lara, Giovanni Pezzulo
Frontiers and Challenges, Advanced Robotics, (2023)
-
Learning Global Spatial Information for Multi-View Object-Centric Models
Yuya Kobayashi, Masahiro Suzuki, Yutaka Matsuo
Advanced Robotics, (2023).
-
Scene interpretation using background information from deep generative models
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).