--- title: "Roozbeh Yousefzadeh — author profile and papers · Reasoning" description: "Roozbeh Yousefzadeh, Yale University: 4 papers on Elamur Research (2024–2025), h-index 5 — affiliations, topics, co-authors and who cites…" canonical: "https://research.elamur.ai/free/en/authors/roozbeh-yousefzadeh/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/roozbeh-yousefzadeh/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Roozbeh Yousefzadeh # Roozbeh Yousefzadeh Roozbeh Yousefzadeh has 4 papers in our library, in 2024–2025, most of them on [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/), [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/); often with [Azim Ospanov](https://md.research.elamur.ai/free/en/authors/azim-ospanov/), [Farzan Farnia](https://md.research.elamur.ai/free/en/authors/farzan-farnia/), [Haoxiong Liu](https://md.research.elamur.ai/free/en/authors/haoxiong-liu/). 4 papers in our library · 2024–2025 [OpenAlex](https://openalex.org/A5084130340) · [ORCID](https://orcid.org/0000-0003-4551-5342) · [**h-index 5**](https://openalex.org/authors/A5084130340) · [34 works](https://openalex.org/works?filter=author.id:A5084130340) · [139 citations](https://openalex.org/works?filter=author.id:A5084130340&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 4 works in our library](https://md.research.elamur.ai/free/en/authors/roozbeh-yousefzadeh/#papers) · [🔗 Cited 35 times in our library](https://md.research.elamur.ai/free/en/authors/roozbeh-yousefzadeh/cited-by/) · [⭐ Paper Stars ranking: #10141](https://md.research.elamur.ai/free/en/paper-stars/page/102/#star-10141) 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=Roozbeh+Yousefzadeh) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Roozbeh+Yousefzadeh) · [dblp](https://dblp.org/search?q=Roozbeh+Yousefzadeh) · [ACL Anthology](https://aclanthology.org/search/?q=Roozbeh+Yousefzadeh) ## Affiliations [🎓**Yale University** New Haven · United States 2019–2025 · 17 papersEmployment 2019–2022 · Postdoc*current*](https://md.research.elamur.ai/free/en/universities/yale-university/) · [🏥**VA Connecticut Healthcare System** West Haven · United States 2021–2023 · 10 papers](https://ror.org/000rgm762) · [🎓**University of Maryland, College Park** College Park · United States 2019 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-of-maryland-college-park/) 🏛️**Huawei Hong Kong Research Center** Hong Kong · [China](https://md.research.elamur.ai/free/en/countries/china/) 2023–2025Employment 2023–2025 · Researcher [🏢**Lightmatter** Boston · United States 2022–2023Employment 2022–2023 · Applied Scientist](https://ror.org/018extf73) 🏛️**University of Maryland at College Park** College Park · [United States](https://md.research.elamur.ai/free/en/countries/united-states/) 2015–2019Education 2015–2019 · PhD, Computer ScienceEducation 2015–2017 · M.S., Computer Science [🎓**Johns Hopkins University** Baltimore · United States 2014–2015Education 2014–2015 · Graduate Certificate, Civil Engineering](https://md.research.elamur.ai/free/en/universities/johns-hopkins-university/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 5 The field of science this work belongs to (OpenAlex fields).[Computer Science · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Computational Theory and Mathematics · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) · [Arts and Humanities · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 1 work](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) 🧭 Topics 2 Research subjects and languages the work is about.[Reasoning · 2 works](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Language models & pretraining · 1 work](https://md.research.elamur.ai/free/en/topics/language-models/) ## Works by year ### 2020s [**2025** 3 papers](https://md.research.elamur.ai/free/en/authors/roozbeh-yousefzadeh/year/2025/) · [**2024** 1 paper](https://md.research.elamur.ai/free/en/authors/roozbeh-yousefzadeh/year/2024/) ## Papers The most cited first (OpenAlex and our library). 1. **[APOLLO: Automated LLM and Lean Collaboration for Advanced Formal Reasoning](https://md.research.elamur.ai/free/en/papers/ospanov-2025-apollo-automated-llm-lean-collaboration/)** *(2025 · 17 citations)* Automated theorem proving with LLMs usually relies on brute-force sampling: a model writes complete Lean proofs, sometimes thousands of times, and the verifier only reports pass or fail. 2. **[Mathesis: Towards Formal Theorem Proving from Natural Languages](https://md.research.elamur.ai/free/en/papers/xuejun-2025-mathesis-towards-formal-theorem-proving/)** *(2025 · 9 citations)* Current LLM theorem provers for Lean 4 assume their input is already a formal statement written by an expert. Real problems, however, are stated in natural language. Mathesis targets the full chain from informal problem to verified proof. Its pipeline has three stages: 3. **[A Lean Dataset for International Math Olympiad: Small Steps towards Writing Math Proofs for Hard Problems](https://md.research.elamur.ai/free/en/papers/yousefzadeh-2024-lean-dataset-international-math-olympiad/)** *(2024 · 7 citations)* Formal theorem proving in Lean lacks high-quality reference material. Even miniF2F, the community's standard benchmark, has public formal proofs for only 6 of the 20 IMO problems in its test set. Without reference proofs, it is hard to tell where automated provers go wrong. The authors wrote original Lean 4 proofs… 4. **[miniF2F-Lean Revisited: Reviewing Limitations and Charting a Path Forward](https://md.research.elamur.ai/free/en/papers/ospanov-2025-minif2f-lean-revisited-reviewing-limitations/)** *(2025 · 4 citations)* This NeurIPS 2025 paper examines miniF2F, a widely used benchmark of 488 competition-style math problems with paired natural-language and Lean statements. ## Co-authors here 6 co-authors with a page, the most papers together first. - [Azim Ospanov](https://md.research.elamur.ai/free/en/authors/azim-ospanov/) ×3 - [Farzan Farnia](https://md.research.elamur.ai/free/en/authors/farzan-farnia/) ×2 - [Haoxiong Liu](https://md.research.elamur.ai/free/en/authors/haoxiong-liu/) - [Jianyuan Zhong](https://md.research.elamur.ai/free/en/authors/jianyuan-zhong/) - [Jing Xiong](https://md.research.elamur.ai/free/en/authors/jing-xiong/) - [Zijin Feng](https://md.research.elamur.ai/free/en/authors/zijin-feng/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/) ×2: [NeurIPS 2025](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/) ×2 ## Cited by Papers of our library cite their works 35 times (of the 149,439 papers whose bibliographies we read); [10 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/roozbeh-yousefzadeh/cited-by/). Updated 3 November 2026