Hiroaki Yamagiwa

According to our database, Hiroaki Yamagiwa authored at least 16 papers between 2023 and 2026.

Collaborative distances:

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

2026

Domain Mixture Design via Log-Likelihood Differences for Aligning Language Models with a Target Model.

Ryo Kishino, Riku Shiomi, Hiroaki Yamagiwa, Momose Oyama, Hidetoshi Shimodaira

CoRR, March, 2026

Measuring Affinity between Attention-Head Weight Subspaces via the Projection Kernel.

Hiroaki Yamagiwa, Yusuke Takase, Hidetoshi Shimodaira

CoRR, January, 2026

2025

Revealing Language Model Trajectories via Kullback-Leibler Divergence.

Ryo Kishino, Yusuke Takase, Momose Oyama, Hiroaki Yamagiwa, Hidetoshi Shimodaira

CoRR, May, 2025

Mapping 1,000+ Language Models via the Log-Likelihood Vector.

Momose Oyama, Hiroaki Yamagiwa, Yusuke Takase, Hidetoshi Shimodaira

CoRR, February, 2025

Likelihood Variance as Text Importance for Resampling Texts to Map Language Models.

Momose Oyama, Ryo Kishino, Hiroaki Yamagiwa, Hidetoshi Shimodaira

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

Norm of Mean Contextualized Embeddings Determines their Variance.

Hiroaki Yamagiwa, Hidetoshi Shimodaira

Proceedings of the 31st International Conference on Computational Linguistics, 2025

Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings.

Hiroaki Yamagiwa, Momose Oyama, Hidetoshi Shimodaira

Proceedings of the 31st International Conference on Computational Linguistics, 2025

Mapping 1, 000+ Language Models via the Log-Likelihood Vector.

Momose Oyama, Hiroaki Yamagiwa, Yusuke Takase, Hidetoshi Shimodaira

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Quantifying Lexical Semantic Shift via Unbalanced Optimal Transport.

Ryo Kishino, Hiroaki Yamagiwa, Ryo Nagata, Sho Yokoi, Hidetoshi Shimodaira

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

2024

Predicting Drug-Gene Relations via Analogy Tasks with Word Embeddings.

Hiroaki Yamagiwa, Ryoma Hashimoto, Kiwamu Arakane, Ken Murakami, Shou Soeda, Momose Oyama, Mariko Okada, Hidetoshi Shimodaira

CoRR, 2024

Zero-Shot Edge Detection with SCESAME: Spectral Clustering-based Ensemble for Segment Anything Model Estimation.

Hiroaki Yamagiwa, Yusuke Takase, Hiroyuki Kambe, Ryosuke Nakamoto

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops, 2024

Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings.

Hiroaki Yamagiwa, Yusuke Takase, Hidetoshi Shimodaira

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Understanding Higher-Order Correlations Among Semantic Components in Embeddings.

Momose Oyama, Hiroaki Yamagiwa, Hidetoshi Shimodaira

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

Shimo Lab at "Discharge Me!": Discharge Summarization by Prompt-Driven Concatenation of Electronic Health Record Sections.

Yunzhen He, Hiroaki Yamagiwa, Hidetoshi Shimodaira

Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, 2024

2023

Improving word mover's distance by leveraging self-attention matrix.

Hiroaki Yamagiwa, Sho Yokoi, Hidetoshi Shimodaira

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

Discovering Universal Geometry in Embeddings with ICA.

Hiroaki Yamagiwa, Momose Oyama, Hidetoshi Shimodaira

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023