Elamur Research⌕
☰
home / authors / Arash Ahmadian

Arash Ahmadian

Arash Ahmadian has 2 papers in our library, in 2023–2024, most of them on Language models & pretraining, Multilingual & cross-lingual NLP; often with Acyr Locatelli, Ahmet Ustun, Daniel D'souza.

2 papers in our library · 2023–2024

OpenAlex · h-index 6 · 18 works · 112 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 436 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #4441

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 TorontoToronto · Canada2022–2024 · 6 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

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

🧭 Topics 2Research subjects and languages the work is about.Multilingual & cross-lingual NLP · 1 workLanguage models & pretraining · 1 work

 Works by year

2020s

20241 paperAya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier20231 paperPushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning

 Papers

The most cited first (OpenAlex and our library).

  1. Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier (2024 · 180 citations)
    Multilingual LLMs usually do worse outside English and a few high-resource languages, and poor tokenization makes them slower and more expensive for other languages.
  2. Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning (2023 · 66 citations)
    Mixture of Experts (MoE) models route inputs to specialized sub-networks while keeping compute constant. However, they are costly because every expert must be stored and, when fine-tuned, updated. Zadouri et al. (Cohere for AI) ask whether MoE can still help in instruction tuning when only a tiny share of weights may…

All works

4 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. Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs · original ↗ · no summary yet · Proceedings of the 62nd Annual Meeting of the Association for Computational…Arash Ahmadian et al.2024 · 201 citations
  2. Aya Expanse: Combining Research Breakthroughs for a New Multilingual FrontierJohn Dang, Shivalika Singh, Daniel D'souza, et al.arXiv:2412.04261 · 180 citations
  3. Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction TuningTed Zadouri, Ahmet Ustun, Arash Ahmadian, et al.arXiv:2309.05444 · 66 citations
  4. The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm · original ↗ · no summary yet · Proceedings of the 2024 Conference on Empirical Methods in Natural Language…Aakanksha et al.2024 · 47 citations

 Co-authors here

7 co-authors 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 436 times (of the 141,840 papers whose bibliographies we read); 31 citing papers with a page here →.

Updated

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