Fumiya Uchiyama

According to our database, Fumiya Uchiyama authored at least 4 papers between 2019 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

How Semantically Informative is an Image?: Measuring the Covariance-Weighted Norm of Contrastive Learning Embeddings.

Fumiya Uchiyama, Rintaro Yanagi, Shohei Taniguchi, Shota Takashiro, Masahiro Suzuki, Hirokatsu Kataoka, Yusuke Iwasawa, Yutaka Matsuo

CoRR, June, 2025

Crypto-LLM: Two-Stage Language Model Pre-training with Ciphered and Natural Language Data.

Yohei Kobashi, Fumiya Uchiyama, Takeshi Kojima, Andrew Gambardella, Qi Cao, Yusuke Iwasawa, Yutaka Matsuo

Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 2025

2024

Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance?

Fumiya Uchiyama, Takeshi Kojima, Andrew Gambardella, Qi Cao, Yusuke Iwasawa, Yutaka Matsuo

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

2019

Learning More with Less: Conditional PGGAN-based Data Augmentation for Brain Metastases Detection Using Highly-Rough Annotation on MR Images.

Changhee Han, Kohei Murao, Tomoyuki Noguchi, Yusuke Kawata, Fumiya Uchiyama, Leonardo Rundo, Hideki Nakayama, Shin'ichi Satoh

Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019