Elamur Research⌕
☰
home / authors / Michael Y. Li

Michael Y. Li

Michael Y. Li has 4 papers in our library, in 2023–2025, most of them on Language models & pretraining, Reasoning; often with Noah D. Goodman, Emmanuel J. Candès, Jure Leskovec.

4 papers in our library · 2023–2025

OpenAlex · ORCID · Wikidata · h-index 12 · 46 works · 1,027 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 76 times in our library · ⭐ Paper Stars ranking: #8344

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

🎓Stanford UniversityStanford · United States2022–2026 · 7 paperscurrent🏥BC Cancer AgencyVancouver · Canada2017–2025 · 17 papers🎓University of British ColumbiaVancouver · Canada2019–2024 · 7 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 12The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 3 worksComputer Science · 3 worksCognitive Neuroscience · 1 workExperimental and Cognitive Psychology · 1 workNeuroscience · 1 workPsychology · 1 workArts and Humanities · 2 worksLanguage and Linguistics · 2 worksDecision Sciences · 1 workInformation Systems and Management · 1 workMaterials Chemistry · 1 workMaterials Science · 1 work

🧭 Topics 2Research subjects and languages the work is about.Reasoning · 1 workLanguage models & pretraining · 1 work

 Works by year

2020s

20252 papers20241 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Why think step by step? Reasoning emerges from the locality of experience (2023 · 65 citations)
    Chain-of-thought prompting often makes large language models answer better, yet it adds no new information.
  2. Automated Hypothesis Validation with Agentic Sequential Falsifications (2025 · 19 citations)
    Large language models can now propose scientific hypotheses faster than people can check them. Many of these claims are also abstract statements that cannot be tested directly. The authors present POPPER, an agent-based system that judges free-form natural-language hypotheses by trying to refute them, following Karl…
  3. Automated Statistical Model Discovery with Language Models (2024 · 14 citations)
    Building a good statistical model usually requires both a skilled modeler and a domain expert. Earlier automation systems, such as the Automatic Statistician, only worked inside a hand-designed domain-specific language (DSL) with a fixed search routine. The authors propose BoxLM, which lets large language models fill…
  4. BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery (2025 · 4 citations)
    BoxingGym addresses a gap in evaluating LLM-based scientific agents. Earlier work tested experimental design and model discovery separately, and no benchmark examined the full loop of proposing a theory, gathering data and revising the theory. The authors built 10 environments based on real scientific models from…

 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 76 times (of the 149,439 papers whose bibliographies we read); 30 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/michael-y-li/