--- title: "Yong Yu — author profile and papers" description: "Yong Yu, Shanghai Jiao Tong University: 2 papers on Elamur Research (2018–2021), h-index 76 — affiliations, topics, co-authors and who cites them in our…" canonical: "https://research.elamur.ai/free/en/authors/yong-yu/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/yong-yu/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Yong Yu # Yong Yu Yong Yu's papers here concern neural text generation, spanning [text generation](https://md.research.elamur.ai/free/en/topics/text-generation/) in general and [machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) in particular. Two questions recur across them: how generative language models can be compared in a fair and reproducible way, and how translation systems can decode quickly without giving up output quality. The most cited of these works is [Texygen: A Benchmarking Platform for Text Generation Models](https://md.research.elamur.ai/free/en/papers/zhu-2018-texygen-benchmarking-platform-text-generation/) (2018). It responds to the difficulty of evaluating open-domain generators, especially those built on GANs. No single metric reflects how good such a model is, implementations are frequently not shared, and apparent improvements in quality may simply be bought with reduced diversity. The [Glancing Transformer for Non-Autoregressive Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/qian-2021-glancing-transformer-non-autoregressive-neural/) (2021) addresses translation models that produce every target token in parallel. Such models are fast but usually fall short of autoregressive Transformers. The paper proposes the Glancing Language Model, a training method that leaves the standard non-autoregressive architecture unchanged. During training, the model first predicts in parallel and is then shown some of the reference words, with the number adjusted according to how its first attempt compares with the reference. The newer of the two papers shifts attention from benchmarking generators to the speed and accuracy of translation. It aims to recover quality without the repeated decoding passes that iterative refinement methods require. Yu is affiliated with [Shanghai Jiao Tong University](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/). Co-authors on these papers include [Weinan Zhang](https://md.research.elamur.ai/free/en/authors/weinan-zhang/), [Hao Zhou](https://md.research.elamur.ai/free/en/authors/hao-zhou/), [Lei Li](https://md.research.elamur.ai/free/en/authors/lei-li/) and [Mingxuan Wang](https://md.research.elamur.ai/free/en/authors/mingxuan-wang/). Yong Yu has 2 papers in our library, in 2018–2021, most of them on [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/), [Text generation](https://md.research.elamur.ai/free/en/topics/text-generation/); often with [Weinan Zhang](https://md.research.elamur.ai/free/en/authors/weinan-zhang/), [Hao Zhou](https://md.research.elamur.ai/free/en/authors/hao-zhou/), [Lei Li](https://md.research.elamur.ai/free/en/authors/lei-li/). 2 papers in our library · 2018–2021 current affiliation [Shanghai Jiao Tong University](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/), Shanghai, China [OpenAlex](https://openalex.org/A5001571390) · [ORCID](https://orcid.org/0000-0003-0281-8271) · [**h-index 76**](https://openalex.org/authors/A5001571390) · [532 works](https://openalex.org/works?filter=author.id:A5001571390) · [29 731 citations](https://openalex.org/works?filter=author.id:A5001571390&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works in our library](https://md.research.elamur.ai/free/en/authors/yong-yu/#papers) · [583 citations in our library](https://md.research.elamur.ai/free/en/authors/yong-yu/cited-by/) · 7 more works in our library · [⭐ Paper Star rank #2551](https://md.research.elamur.ai/free/en/paper-stars/page/26/#star-2551) 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=Yong+Yu) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Yong+Yu) · [dblp](https://dblp.org/search?q=Yong+Yu) · [ACL Anthology](https://aclanthology.org/search/?q=Yong+Yu) ## Affiliations - [Shanghai Jiao Tong University](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) · Shanghai, China —current · 2001–2026 on 442 papers - [Yunnan University](https://ror.org/0040axw97) · Kunming, China —2008–2025 on 28 papers - [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) · Beijing, China —2012–2024 on 4 papers - [University of Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) · Beijing, China —2018–2024 on 4 papers - [University of California, Santa Barbara](https://md.research.elamur.ai/free/en/universities/university-of-california-santa-barbara/) · Santa Barbara, United States —2021 on 2 papers - [Institute of Computing Technology](https://md.research.elamur.ai/free/en/labs/institute-of-computing-technology/) · Beijing, China —2018–2020 on 2 papers - [Yunnan Key Laboratory of Software Engineering](https://ror.org/03nd4as18) · Kunming, China —2010–2019 on 7 papers - [Zhejiang University of Technology](https://ror.org/02djqfd08) · Hangzhou, China —2011–2013 on 2 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 18 more institutions on single bylines are not listed. ## Topics [Machine translation 1](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Text generation 1](https://md.research.elamur.ai/free/en/topics/text-generation/) ## Works by year ### 2020s [**2021** 1 paper](https://md.research.elamur.ai/free/en/papers/qian-2021-glancing-transformer-non-autoregressive-neural/) ### 2010s [**2018** 1 paper](https://md.research.elamur.ai/free/en/papers/zhu-2018-texygen-benchmarking-platform-text-generation/) ## Papers The most cited first (OpenAlex and our library). 1. **[Texygen: A Benchmarking Platform for Text Generation Models](https://md.research.elamur.ai/free/en/papers/zhu-2018-texygen-benchmarking-platform-text-generation/)** *(2018 · 486 citations)* Comparing models for open-domain text generation, especially GAN-based ones, is unreliable for three reasons: no single metric captures model quality, many authors don't release code, and gains in output quality often just come from giving up diversity. 2. **[Glancing Transformer for Non-Autoregressive Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/qian-2021-glancing-transformer-non-autoregressive-neural/)** *(2021 · 180 citations)* Non-autoregressive translation (NAT) models emit all target tokens at once, which makes them fast. However, they assume target words are independent given the source, so they translate noticeably worse than the autoregressive Transformer. Iterative fixes such as Mask-Predict recover quality but need several decoding… ## Also in our library 7 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 4 co-authors with a page, the most papers together first. - [Weinan Zhang](https://md.research.elamur.ai/free/en/authors/weinan-zhang/) ×2 - [Hao Zhou](https://md.research.elamur.ai/free/en/authors/hao-zhou/) - [Lei Li](https://md.research.elamur.ai/free/en/authors/lei-li/) - [Mingxuan Wang](https://md.research.elamur.ai/free/en/authors/mingxuan-wang/) ## Cited by Papers of our library cite their works 583 times (of the 140 884 papers whose bibliographies we read); [26 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/yong-yu/cited-by/).