Elamur Research⌕
☰
home / authors / Benjamin Minixhofer

Benjamin Minixhofer

Benjamin Minixhofer has 2 papers in our library, in 2022–2025, most of them on Language models & pretraining, Tokenization & segmentation, Multilingual & cross-lingual NLP; often with Ivan Vulić.

2 papers in our library · 2022–2025

OpenAlex · ORCID · h-index 4 · 23 works · 73 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 98 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #6798

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓University of CambridgeCambridge · United Kingdom2021–2026 · 14 paperscurrent🎓Johannes Kepler University of LinzLinz · Austria2021–2022 · 5 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 work

🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 2 worksTokenization & segmentation · 2 worksMultilingual & cross-lingual NLP · 1 work

💡 Concepts 1Key ideas and methods explained on our concept pages.Subword tokenization · 1 work

 Works by year

2020s

20251 paper20221 paper

 Papers

The most cited first (OpenAlex and our library).

  1. WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models (2022 · 91 citations)
    Pretraining large language models is expensive, and most strong models exist only for English. Massively multilingual models lose quality as more languages are added, and training a monolingual model from scratch in another language needs roughly as much compute as the original English model. The authors propose…
  2. Retrofitting Large Language Models with Dynamic Tokenization (2025 · 11 citations)
    Most language models use a fixed subword tokenizer. This tokenizer often splits non-English text into too many pieces, which makes inference slower and more costly and spreads quality unevenly across languages. The authors adapt existing subword-based models to segment text adaptively, without retraining them. For…

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language modelsConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Benjamin Minixhofer, Fabian Paischer, Navid Rekabsaz2022 · 91 citations
  2. Retrofitting Large Language Models with Dynamic TokenizationAnnual Meeting of the Association for Computational Linguistics (ACL)Darius Feher, Ivan Vulić, Benjamin Minixhofer2025 · 11 citations
  3. Retrofitting language models to operate over bytes ↗Nature · no summary yetBenjamin Minixhofer et al.2026 · 1 citation

 Co-authors here

1 co-author with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 98 times (of the 149,439 papers whose bibliographies we read); 19 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/benjamin-minixhofer/