Elamur Research⌕
☰
home / authors / Zicheng Xu

Zicheng Xu

Zicheng Xu has 2 papers in our library, in 2024, most of them on Language models & pretraining, Reasoning; often with Tian Ye, Yuanzhi Li, Zeyuan Allen-Zhu.

2 papers in our library · 2024

OpenAlex · h-index 2 · 3 works · 10 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 79 times in our library · ⭐ Paper Stars ranking: #8660

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

🏢GoogleMountain View · United States2025 · 2 paperscurrent

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 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksComputer Vision and Pattern Recognition · 2 worksLanguage and Linguistics · 2 works

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

 Works by year

2020s

20242 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process (2024 · 58 citations)
    Do language models actually reason through grade-school math, or do they reuse memorized templates? Internet-pretrained models cannot answer this because of possible benchmark contamination, so the authors built iGSM, a synthetic generator of GSM8K-style word problems.
  2. Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems (2024 · 31 citations)
    Strong language models still make reasoning slips. They can often fix these when prompted to re-check their work, but not while they are generating. This paper asks whether the ability to catch and repair errors mid-solution can be built in during pretraining. To keep the experiments controlled, the authors use iGSM…

 Co-authors here

3 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 79 times (of the 149,439 papers whose bibliographies we read); 34 citing papers with a page here →.

Updated

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