Elamur Research⌕
☰
home / authors / Dan Alistarh

Dan Alistarh

Dan Alistarh has 3 papers in our library, in 2024–2026, most of them on Language models & pretraining, Efficient models & compression; often with Amirkeivan Mohtashami, Bo Li, Martin Jaggi.

3 papers in our library · 2024–2026

OpenAlex · ORCID · Wikidata · h-index 30 · 321 works · 4,061 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 454 times in our library · 5 more in our library without a page yet · ⭐ Paper Stars ranking: #5128

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

🎓Institute of Science and Technology AustriaKlosterneuburg · Austria2017–2026 · 172 papersEmploymentcurrent🏢Red HatRaleigh · United States2025–2026 · 8 paperscurrent🎓Lancaster UniversityLancaster · United Kingdom2026 · 1 papercurrent🏢Microsoft ResearchCambridge · United Kingdom2014–2017 · 18 papers🎓École Polytechnique Fédérale de LausanneLausanne · Switzerland2008–2025 · 17 papersEducation🎓ETH ZurichZurich · Switzerland2013–2020 · 14 papers🏢MicrosoftRedmond · United States2014–2016 · 5 papers🎓Massachusetts Institute of TechnologyCambridge · United States2013 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 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 8The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 3 worksComputer Science · 3 worksArtificial Intelligence · 3 worksLanguage and Linguistics · 3 worksEngineering · 1 workComputer Vision and Pattern Recognition · 2 worksElectrical and Electronic Engineering · 1 workComputational Theory and Mathematics · 1 work

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

 Works by year

2020s

20261 paper20251 paper20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs (2024 · 254 citations)
    Quantizing large language models to 4 bits is hard because activations contain outliers: individual channels whose values are many times larger than the rest.
  2. “Give Me BF16 or Give Me Death”? Accuracy-Performance Trade-Offs in LLM Quantization (2025 · 21 citations)
    Quantization is the most common way to make LLM inference cheaper. However, practitioners lack systematic evidence on how much accuracy each popular format sacrifices and what speed or cost savings it delivers. The authors quantize the whole Llama-3.1 family (8B, 70B, 405B) into three formats with broad hardware…
  3. Speculative Decoding Speed-of-Light: Optimal Lower Bounds via Branching Random Walks (2026 · 1 citation)
    Speculative decoding speeds up LLM inference. A cheap drafter proposes a sequence or tree of tokens, and the target model checks up to P of them in one parallel pass. It has been unclear how much speedup this approach can deliver in principle. Pankratov and Alistarh derive what they call the first tight limit for any…

All works

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

  1. QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding ↗arXiv:1610.02132 · no summary yetDan Alistarh et al.2016 · 962 citations
  2. QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMsConference on Neural Information Processing Systems (NeurIPS)Saleh Ashkboos, Amirkeivan Mohtashami, Maximilian L. Croci, et al.2024 · 254 citations
  3. The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models ↗Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · no summary yetEldar Kurtic et al.2022 · 115 citations
  4. Extreme Compression of Large Language Models via Additive Quantization ↗ICML 2024 · no summary yetVage Egiazarian et al.2024 · 84 citations
  5. “Give Me BF16 or Give Me Death”? Accuracy-Performance Trade-Offs in LLM QuantizationAnnual Meeting of the Association for Computational Linguistics (ACL)Eldar Kurtic, Alexandre Noll Marques, Shubhra Pandit, et al.2025 · 21 citations
  6. MLSys: The New Frontier of Machine Learning Systems ↗arXiv (Cornell University) · no summary yetAlexander Ratner et al.2019 · 19 citations
  7. Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization ↗arXiv:2404.03605 · no summary yetAniruddha Nrusimha et al.2024 · 6 citations
  8. Speculative Decoding Speed-of-Light: Optimal Lower Bounds via Branching Random WalksConference of the European Chapter of the Association for Computational Linguistics (EACL)Sergey Pankratov, Dan Alistarh2026 · 1 citation

 Co-authors here

3 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 454 times (of the 149,439 papers whose bibliographies we read); 25 citing papers with a page here →.

Updated

↑ back to top

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