---
title: "Chiyuan Zhang — author profile and papers — Elamur Research"
description: "Chiyuan Zhang: 4 papers on Elamur Research (2015–2025), h-index 44 — affiliations, topics, co-authors and who cites them in our library."
canonical: "https://research.elamur.ai/free/en/authors/chiyuan-zhang/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/chiyuan-zhang/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Chiyuan Zhang

# Chiyuan Zhang

Chiyuan Zhang has 4 papers in our library, in 2015–2025, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/); often with [Bill Yuchen Lin](https://md.research.elamur.ai/free/en/authors/bill-yuchen-lin/), [Bing Xu](https://md.research.elamur.ai/free/en/authors/bing-xu/), [Bo Li](https://md.research.elamur.ai/free/en/authors/bo-li/).

4 papers in our library · 2015–2025

[OpenAlex](https://openalex.org/A5016054994) · [ORCID](https://orcid.org/0009-0003-5419-8606) · [**h-index 44**](https://openalex.org/authors/A5016054994) · [160 works](https://openalex.org/works?filter=author.id:A5016054994) · [12,843 citations](https://openalex.org/works?filter=author.id:A5016054994&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[📄 4 works in our library](https://md.research.elamur.ai/free/en/authors/chiyuan-zhang/#papers) · [🔗 Cited 1,076 times in our library](https://md.research.elamur.ai/free/en/authors/chiyuan-zhang/cited-by/) · [7 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #1446](https://md.research.elamur.ai/free/en/paper-stars/page/15/#star-1446)

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=Chiyuan+Zhang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Chiyuan+Zhang) · [dblp](https://dblp.org/search?q=Chiyuan+Zhang) · [ACL Anthology](https://aclanthology.org/search/?q=Chiyuan+Zhang)

## Affiliations

[🏢**Google** Mountain View · United States 2018–2026 · 34 papers](https://md.research.elamur.ai/free/en/companies/google/) · [🎓**Massachusetts Institute of Technology** Cambridge · United States 2014–2019 · 9 papers](https://md.research.elamur.ai/free/en/universities/massachusetts-institute-of-technology/) · [🎓**Zhejiang University** Hangzhou · China 2010–2018 · 9 papers](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) · [🔬**McGovern Institute for Brain Research** Cambridge · United States 2014–2018 · 2 papers](https://md.research.elamur.ai/free/en/labs/mcgovern-institute-for-brain-research/) · [🏛️**China Tobacco** Jinrongjie · China Employment](https://ror.org/030d08e08)

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 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 6 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/) · [Computer Vision and Pattern Recognition · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Hardware and Architecture · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/hardware-and-architecture/) · [Arts and Humanities · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/)

🧭 Topics 2 Research subjects and languages the work is about.[Language models & pretraining · 2 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Reasoning · 1 work](https://md.research.elamur.ai/free/en/topics/reasoning/)

💡 Concepts 1 Key ideas and methods explained on our concept pages.[Machine learning · 1 work](https://md.research.elamur.ai/free/en/concepts/machine-learning/)

## Works by year

### 2020s

[**2025** 1 paper](https://md.research.elamur.ai/free/en/authors/chiyuan-zhang/year/2025/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/chiyuan-zhang/year/2023/) · [**2020** 1 paper](https://md.research.elamur.ai/free/en/authors/chiyuan-zhang/year/2020/)

### 2010s

[**2015** 1 paper](https://md.research.elamur.ai/free/en/authors/chiyuan-zhang/year/2015/)

## Papers

The most cited first (OpenAlex and our library).

1. **[MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems](https://md.research.elamur.ai/free/en/papers/chen-2015-mxnet-flexible-efficient-machine-learning/)** *(2015 · 2,000 citations)* Deep learning developers usually have to pick between two styles. Imperative tensor code is easy to debug and works with host-language tools. Declarative computation graphs expose the whole structure, so the system can optimize it. MXNet tries to give users both styles in one library. Network structure is described…
2. **[What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://md.research.elamur.ai/free/en/papers/feldman-2020-neural-networks-memorize-why-discovering/)** *(2020 · 193 citations)* Deep networks routinely fit outliers and mislabeled training points. Classical generalization theory treats this as harmful overfitting, so it cannot explain why it happens. Feldman's earlier "long tail theory" argued that memorization is needed for near-optimal accuracy when data contain many rare subpopulations…
3. **[Preventing Generation of Verbatim Memorization in Language Models Gives a False Sense of Privacy](https://md.research.elamur.ai/free/en/papers/ippolito-2023-preventing-generation-verbatim-memorization-language/)** *(2023 · 68 citations)* Much work on training-data leakage in language models treats memorization as an exact substring match with the training set, and some deployed safeguards, such as GitHub Copilot's option to block suggestions matching public code, rely on this view.
4. **[On Memorization of Large Language Models in Logical Reasoning](https://md.research.elamur.ai/free/en/papers/xie-2025-memorization-large-language-models-logical/)** *(2025 · 45 citations)* LLMs score well on hard reasoning benchmarks yet still fail on trivial questions. This raises the suspicion that some benchmark success comes from recalling familiar problems. The authors test this idea in a controlled setting. They define LiMem, a memorization score that multiplies a model's accuracy on a puzzle set…

## All works

11 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. [**MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems arXiv:1512.01274**Tianqi Chen, Mu Li, Yutian Li, et al.*2015 · 2,000 citations*](https://md.research.elamur.ai/free/en/papers/chen-2015-mxnet-flexible-efficient-machine-learning/)
2. **[Understanding deep learning requires rethinking generalization ↗](https://arxiv.org/abs/1611.03530) arXiv:1611.03530 · no summary yet**Chiyuan Zhang et al.*2016 · 1,174 citations*
3. **[Deduplicating Training Data Makes Language Models Better ↗](https://aclanthology.org/2022.acl-long.577/) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Katherine Lee et al.*2022 · 623 citations*
4. **[A Study on Overfitting in Deep Reinforcement Learning ↗](https://arxiv.org/abs/1804.06893) arXiv (Cornell University) · no summary yet**Chiyuan Zhang et al.*2018 · 242 citations*
5. [**What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation arXiv:2008.03703**Vitaly Feldman, Chiyuan Zhang*2020 · 193 citations*](https://md.research.elamur.ai/free/en/papers/feldman-2020-neural-networks-memorize-why-discovering/)
6. **[Preventing Generation of Verbatim Memorization in Language Models Gives a False Sense of Privacy](https://md.research.elamur.ai/free/en/papers/ippolito-2023-preventing-generation-verbatim-memorization-language/) [International Natural Language Generation Conference (INLG)](https://md.research.elamur.ai/free/en/venues/inlg/)**Daphne Ippolito, Florian Tramer, Milad Nasr, et al.*2023 · 68 citations*
7. **[MUSE: Machine Unlearning Six-Way Evaluation for Language Models ↗](https://arxiv.org/abs/2407.06460) arXiv (Cornell University) · no summary yet**Weijia Shi et al.*2024 · 65 citations*
8. **[On Memorization of Large Language Models in Logical Reasoning](https://md.research.elamur.ai/free/en/papers/xie-2025-memorization-large-language-models-logical/) [International Joint Conference on Natural Language Processing (IJCNLP)](https://md.research.elamur.ai/free/en/venues/ijcnlp/)**Chulin Xie, Yangsibo Huang, Chiyuan Zhang, et al.*2025 · 45 citations*
9. **[MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations ↗](https://arxiv.org/abs/2502.06453) arXiv:2502.06453 · no summary yet**Kaixuan Huang et al.*2025 · 42 citations*
10. **[Evaluating Copyright Takedown Methods for Language Models ↗](https://doi.org/10.52202/079017-4415) neural information processing systems · no summary yet**Boyi Wei et al.*2024 · 25 citations*
11. **[Fantastic Copyrighted Beasts and How (Not) to Generate Them ↗](https://arxiv.org/abs/2406.14526) arXiv (Cornell University) · no summary yet**Luxi He et al.*2024 · 9 citations*

## Co-authors here

12 of 17 co-authors with a page, the most papers together first.

- [Bill Yuchen Lin](https://md.research.elamur.ai/free/en/authors/bill-yuchen-lin/)
- [Bing Xu](https://md.research.elamur.ai/free/en/authors/bing-xu/)
- [Bo Li](https://md.research.elamur.ai/free/en/authors/bo-li/)
- [Chulin Xie](https://md.research.elamur.ai/free/en/authors/chulin-xie/)
- [Daphne Ippolito](https://md.research.elamur.ai/free/en/authors/daphne-ippolito/)
- [Florian Tramer](https://md.research.elamur.ai/free/en/authors/florian-tramer/)
- [Katherine Lee](https://md.research.elamur.ai/free/en/authors/katherine-lee/)
- [Matthew Jagielski](https://md.research.elamur.ai/free/en/authors/matthew-jagielski/)
- [Milad Nasr](https://md.research.elamur.ai/free/en/authors/milad-nasr/)
- [Min Lin](https://md.research.elamur.ai/free/en/authors/min-lin/)
- [Mu Li](https://md.research.elamur.ai/free/en/authors/mu-li/)
- [Nicholas Carlini](https://md.research.elamur.ai/free/en/authors/nicholas-carlini/)

## Venues

Where their works here were published, the most works first, with the editions of those that have a page.

- [International Joint Conference on Natural Language Processing (IJCNLP)](https://md.research.elamur.ai/free/en/venues/ijcnlp/): [IJCNLP 2025](https://md.research.elamur.ai/free/en/venues/ijcnlp/2025/)
- [International Natural Language Generation Conference (INLG)](https://md.research.elamur.ai/free/en/venues/inlg/): [INLG 2023](https://md.research.elamur.ai/free/en/venues/inlg/2023/)
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- neural information processing systems

## Cited by

Papers of our library cite their works 1,076 times (of the 149,439 papers whose bibliographies we read); [206 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/chiyuan-zhang/cited-by/).

Updated 2 November 2026