--- title: "Zhewei Yao — author profile and papers" description: "Zhewei Yao, Snowflake Inc. (United States): 3 papers on Elamur Research (2021–2022), h-index 26 — affiliations, topics, co-authors and who cites them in…" canonical: "https://research.elamur.ai/free/en/authors/zhewei-yao/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/zhewei-yao/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Zhewei Yao # Zhewei Yao Zhewei Yao has 3 papers in our library, in 2021–2022, most of them on [Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/); often with [Conglong Li](https://md.research.elamur.ai/free/en/authors/conglong-li/), [Minjia Zhang](https://md.research.elamur.ai/free/en/authors/minjia-zhang/), [Reza Yazdani Aminabadi](https://md.research.elamur.ai/free/en/authors/reza-yazdani-aminabadi/). 3 papers in our library · 2021–2022 current affiliation [Snowflake Inc. (United States)](https://ror.org/04vrpfw15), Bozeman [OpenAlex](https://openalex.org/A5102915910) · [ORCID](https://orcid.org/0000-0001-7678-4321) · [**h-index 26**](https://openalex.org/authors/A5102915910) · [92 works](https://openalex.org/works?filter=author.id:A5102915910) · [4 756 citations](https://openalex.org/works?filter=author.id:A5102915910&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [3 works in our library](https://md.research.elamur.ai/free/en/authors/zhewei-yao/#papers) · [512 citations in our library](https://md.research.elamur.ai/free/en/authors/zhewei-yao/cited-by/) · 1 more work in our library · [⭐ Paper Star rank #2537](https://md.research.elamur.ai/free/en/paper-stars/page/26/#star-2537) 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=Zhewei+Yao) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Zhewei+Yao) · [dblp](https://dblp.org/search?q=Zhewei+Yao) · [ACL Anthology](https://aclanthology.org/search/?q=Zhewei+Yao) ## Affiliations - [Snowflake Inc. (United States)](https://ror.org/04vrpfw15) · Bozeman —current · 2024–2026 on 8 papers - [Seoul National University](https://md.research.elamur.ai/free/en/universities/seoul-national-university/) · Seoul, South Korea —2024–2025 on 6 papers - [University of California, Berkeley](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) · Berkeley, United States —2018–2024 on 34 papers - [Microsoft (United States)](https://md.research.elamur.ai/free/en/companies/microsoft/) · Redmond, United States —2021–2024 on 7 papers - [Shanghai Jiao Tong University](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) · Shanghai, China —2003–2018 on 8 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed. ## Topics [Efficient models & compression 2](https://md.research.elamur.ai/free/en/topics/efficient-models/) ## Works by year ### 2020s [**2022** 2 papers](https://md.research.elamur.ai/free/en/authors/zhewei-yao/year/2022/) · [**2021** 1 paper](https://md.research.elamur.ai/free/en/papers/kim-2021-i-bert-integer-only-bert/) ## Papers The most cited first (OpenAlex and our library). 1. **[ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers](https://md.research.elamur.ai/free/en/papers/yao-2022-zeroquant-efficient-affordable-post-training/)** *(2022 · 301 citations)* Serving very large Transformer language models takes a lot of memory and compute. Quantization-aware training needs the original data and a full training run, which is often impractical. ZeroQuant, from Microsoft's DeepSpeed team, is a post-training quantization pipeline for BERT and GPT-3-style models. It has three… 2. **[DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale](https://md.research.elamur.ai/free/en/papers/rajbhandari-2022-deepspeed-moe-advancing-mixture-experts/)** *(2022 · 254 citations)* Mixture-of-Experts (MoE) models can reach a given quality with far less training compute than dense networks. 3. **[I-BERT: Integer-only BERT Quantization](https://md.research.elamur.ai/free/en/papers/kim-2021-i-bert-integer-only-bert/)** *(2021 · 118 citations)* Large Transformer encoders such as BERT and RoBERTa are costly to run, especially on edge hardware. Earlier quantization work for these models was only partly integer: it still converted values back to floating point for GELU, Softmax and LayerNorm. That prevents deployment on integer-only processors (e.g., ARM… ## Also in our library 1 more work of theirs is in our library without a page here yet; it will appear as we publish them. ## Co-authors here 10 co-authors with a page, the most papers together first. - [Conglong Li](https://md.research.elamur.ai/free/en/authors/conglong-li/) ×2 - [Minjia Zhang](https://md.research.elamur.ai/free/en/authors/minjia-zhang/) ×2 - [Reza Yazdani Aminabadi](https://md.research.elamur.ai/free/en/authors/reza-yazdani-aminabadi/) ×2 - [Yuxiong He](https://md.research.elamur.ai/free/en/authors/yuxiong-he/) ×2 - [Amir Gholami](https://md.research.elamur.ai/free/en/authors/amir-gholami/) - [Ammar Ahmad Awan](https://md.research.elamur.ai/free/en/authors/ammar-ahmad-awan/) - [Kurt Keutzer](https://md.research.elamur.ai/free/en/authors/kurt-keutzer/) - [Michael W. Mahoney](https://md.research.elamur.ai/free/en/authors/michael-w-mahoney/) - [Samyam Rajbhandari](https://md.research.elamur.ai/free/en/authors/samyam-rajbhandari/) - [Sehoon Kim](https://md.research.elamur.ai/free/en/authors/sehoon-kim/) ## Cited by Papers of our library cite their works 512 times (of the 140 884 papers whose bibliographies we read); [14 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/zhewei-yao/cited-by/).