Author

Yuichi Tateno

h-index 0 View on Semantic Scholar

We have 1 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Bekko Embedding: Parameter-Efficient Multilingual Retrieval with Ultra-Compact Encoders

This work presents Bekko Embedding, a competitive multilingual retrieval model that handles inputs of up to 8192 tokens, and on long-input retrieval (NanoLongEmbed) a25m is the strongest dense model in the authors' comparison.

Yuichi Tateno · arXiv.org · 0 citations