| 2025 | ICIP | Rethinking the Backbone in Class Imbalanced Federated Source Free Domain Adaptation: the Utility of Vision Foundation Models. | Kosuke Kihara, Junki Mori, Taiki Miyagawa, Akinori F. Ebihara |
| 2025 | ICLR | Learning the Optimal Stopping for Early Classification within Finite Horizons via Sequential Probability Ratio Test. | Akinori F. Ebihara, Taiki Miyagawa, Kazuyuki Sakurai, Hitoshi Imaoka |
| 2025 | WACV | Federated Source-Free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data. | Junki Mori, Kosuke Kihara, Taiki Miyagawa, Akinori F. Ebihara, Isamu Teranishi, Hisashi Kashima |
| 2023 | ICASSP | Toward Asymptotic Optimality: Sequential Unsupervised Regression of Density Ratio for Early Classification. | Akinori F. Ebihara, Taiki Miyagawa, Kazuyuki Sakurai, Hitoshi Imaoka |
| 2022 | IJCNN | Convolutional Neural Networks for Time-dependent Classification of Variable-length Time Series. | Azusa Sawada, Taiki Miyagawa, Akinori F. Ebihara, Shoji Yachida, Toshinori Hosoi |
| 2021 | ICLR | Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and Accuracy. | Akinori F. Ebihara, Taiki Miyagawa, Kazuyuki Sakurai, Hitoshi Imaoka |
| 2021 | ICML | The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization. | Taiki Miyagawa, Akinori F. Ebihara |