--- title: "Max Tegmark — author profile and papers" description: "Max Tegmark, The NSF AI Institute for Artificial Intelligence and Fundamental Interactions: 2 papers on Elamur Research (2023), h-index 109 —…" canonical: "https://research.elamur.ai/free/en/authors/max-tegmark/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/max-tegmark/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Max Tegmark # Max Tegmark Max Tegmark has 2 papers in our library, in 2023, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/). 2 papers in our library · 2023 current affiliation [The NSF AI Institute for Artificial Intelligence and Fundamental Interactions](https://ror.org/04pvzz946) · Cambridge United States; [Massachusetts Institute of Technology](https://md.research.elamur.ai/free/en/universities/massachusetts-institute-of-technology/) · Cambridge United States [OpenAlex](https://openalex.org/A5091601455) · [ORCID](https://orcid.org/0000-0001-7670-7190) · [Wikidata](https://www.wikidata.org/wiki/Q2076321) · [**h-index 109**](https://openalex.org/authors/A5091601455) · [423 works](https://openalex.org/works?filter=author.id:A5091601455) · [63,665 citations](https://openalex.org/works?filter=author.id:A5091601455&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works in our library](https://md.research.elamur.ai/free/en/authors/max-tegmark/#papers) · [270 citations in our library](https://md.research.elamur.ai/free/en/authors/max-tegmark/cited-by/) · 8 more works in our library · [⭐ Paper Star rank #3874](https://md.research.elamur.ai/free/en/paper-stars/page/39/#star-3874) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Max+Tegmark) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Max+Tegmark) · [dblp](https://dblp.org/search?q=Max+Tegmark) · [ACL Anthology](https://aclanthology.org/search/?q=Max+Tegmark) ## Affiliations [🎓**Massachusetts Institute of Technology** Cambridge · United States 2004–2026 · 228 papers*current**employment (Wikidata)*](https://md.research.elamur.ai/free/en/universities/massachusetts-institute-of-technology/) · [🔬**The NSF AI Institute for Artificial Intelligence and Fundamental Interactions** Cambridge · United States 2021–2026 · 25 papers*current*](https://ror.org/04pvzz946) · [🎓**University of Pennsylvania** Philadelphia · United States 1997–2006 · 98 papers](https://md.research.elamur.ai/free/en/universities/university-of-pennsylvania/) · [🔬**Institute for Advanced Study** Princeton · United States 1996–2001 · 48 papers](https://ror.org/00f809463) · [🔬**Max Planck Institute for Physics** Munich · Germany 1994–1998 · 21 papers](https://ror.org/0079jjr10) · [🔬**Max Planck Institute for Astrophysics** Garching · Germany 1995–1998 · 11 papers](https://ror.org/017qcv467) · [🎓**University of California, Berkeley** Berkeley · United States 1993–2013 · 9 papers*education (Wikidata)*](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) · [🔬**Max Planck Society** Munich · Germany 1995–1997 · 4 papers](https://md.research.elamur.ai/free/en/labs/max-planck-society/) · [🤝**Theiss Research** La Jolla · United States 2016–2020 · 3 papers](https://ror.org/00scjnx30) · [🤝**Foundational Questions Institute** Decatur · United States 2007–2014 · 2 papers](https://ror.org/016en1t86) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 14 more institutions on single bylines are not listed. ## Topics [Language models & pretraining 1](https://md.research.elamur.ai/free/en/topics/language-models/) · [Efficient models & compression 1](https://md.research.elamur.ai/free/en/topics/efficient-models/) ## Works by year ### 2020s [**2023** 2 papers](https://md.research.elamur.ai/free/en/authors/max-tegmark/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://md.research.elamur.ai/free/en/papers/marks-2023-geometry-truth-emergent-linear-structure/)** *(2023 · 160 citations)* LLMs sometimes state things that are false even when they seem to "know" better. Earlier attempts to detect truthfulness by probing internal activations generalized poorly, which raised doubts about whether those probes found truth or only features that correlate with it. Marks and Tegmark study this question in… 2. **[The Quantization Model of Neural Scaling](https://md.research.elamur.ai/free/en/papers/michaud-2023-quantization-model-neural-scaling/)** *(2023 · 27 citations)* The paper tackles a puzzle about scaling. Average loss falls smoothly as a power law when models and datasets grow, yet specific abilities often seem to switch on abruptly. To reconcile the two, the authors propose the Quantization Hypothesis. It holds that prediction tasks rely on a countable set of discrete skills… ## Also in our library 8 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Cited by Papers of our library cite their works 270 times (of the 140,884 papers whose bibliographies we read); [13 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/max-tegmark/cited-by/).