Research
Publications
Category
Research Area
Year
-
LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer
Machel Reid and Victor Zhong
Findings of the Association for Computational Linguistics: The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021).
-
Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-Reinforcement Learning
Kei Akuzawa, Yusuke Iwasawa, Yutaka Matsuo
Learning for Dynamics and Control (L4DC)
-
Detecting Object-level Scene Changes with Viewpoint Difference using Graph Matching
Kento Doi, Ryuhei Hamaguchi, Yusuke Iwasawa, Masaki Onishi, Yutaka Matsuo, Ken Sakurada.
2021 IEEE International Conference on Robotics and Automation (ICRA2022). May 2021. [paper]
-
Group Equivariant Conditional Neural Processes
Makoto Kawano, Wataru Kumagai, Akiyoshi Sannai, Yusuke Iwasawa, and Yutaka Matsuo.
International Conference on Learning Representations 2021 (ICLR2021).
-
Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization
Tatsuya Matsushima, Hiroki Furuta, Yutaka Matsuo, Ofir Nachum, and Shixiang Shane Gu.
International Conference on Learning Representations 2021 (ICLR2021).
-
Variational Inference for Learning Representations of Natural Language Edits
Edison Marrese-Taylor, Machel Reid and Yutaka Matsuo.
The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21). February 2021.
-
2021 World Robot Competition Service Robot Category Partner Robot Challenge: Second Place
T. Matsushima et al.
-
DORi: Discovering Object Relationships for Moment Localization of a Natural Language Query in a Video
Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Basura Fernando, Hongdong Li and Stephen Gould
The IEEE Winter Conference on Applications of Computer Vision (WACV). January 2021
-
Pixyz: a framework for developing deep generative models
Tutorial on Deep Probabilistic Generative Models for Robotics (IROS2020)
-
JSAI2018 Excellence Award: “Improving Robustness to Long Action Sequences by Partitioning into Subtasks and Predicting Abstracted Actions in Instruction Following.”
篠田 一聡,竹澤 祐貴,鈴木 雅大,岩澤 有祐,松尾 豊