Elamur Research⌕
☰
home / authors / Fartash Faghri

Fartash Faghri

Fartash Faghri has 2 papers in our library, in 2024–2026, most of them on Language models & pretraining, Efficient models & compression; often with Mehrdad Farajtabar, Minsik Cho, Fatih Ilhan.

2 papers in our library · 2024–2026

OpenAlex · ORCID · h-index 12 · 51 works · 1,661 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 190 times in our library · 5 more in our library without a page yet · ⭐ Paper Stars ranking: #11509

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

🏢AppleCupertino · United States2022–2025 · 11 papers🎓University of TorontoToronto · Canada2013–2022 · 6 papersEducation 2013–2014 · MSc, Computer ScienceEducation since 2017 · PhD, Computer Science🎓Sharif University of TechnologyTehran · Iran2008–2012 · 1 paperEducation 2008–2012 · BSc, Computer Engineering

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

 Fields, topics and concepts

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

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 1 workEfficient models & compression · 1 work

 Works by year

2020s

20261 paper20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization (2024 · 8 citations)
    Training large language models from random weights is slow and costly, while small models are cheap but less accurate.
  2. Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why (2026 · 7 citations)
    On-policy distillation gives a student model dense, per-token supervision, either from a larger external teacher or from the student itself conditioned on privileged context such as a correct solution.

All works

7 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. A Study of Gradient Variance in Deep Learning ↗arXiv (Cornell University) · no summary yetFartash Faghri et al.2020 · 12 citations
  2. Scaling Smart: Accelerating Large Language Model Pre-training with Small Model InitializationarXiv:2409.12903Mohammad Samragh, Iman Mirzadeh, Keivan Alizadeh Vahid, et al.2024 · 8 citations
  3. Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and WhyarXiv:2605.10889Mohammadreza Armandpour, Fatih Ilhan, David Harrison, et al.2026 · 7 citations
  4. Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pre-training ↗Findings of the Association for Computational Linguistics: EACL 2026 · no summary yetJeffrey Li et al.2026
  5. Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining ↗arXiv (Cornell University) · no summary yetJeffrey Li et al.2026
  6. FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations ↗arXiv (Cornell University) · no summary yetCheng-Yu Hsieh et al.2025
  7. A Non-asymptotic comparison of SVRG and SGD: tradeoffs between compute and speed ↗no summary yetQingru Zhang et al.2019

 Co-authors here

6 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 190 times (of the 149,439 papers whose bibliographies we read); 58 citing papers with a page here →.

Updated

↑ back to top

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