--- title: "Zhengyan Zhang — author profile and papers" description: "Zhengyan Zhang, Jiangsu University of Science and Technology: 3 papers on Elamur Research (2021–2025), h-index 21 — affiliations, topics, co-authors and…" canonical: "https://research.elamur.ai/free/en/authors/zhengyan-zhang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/zhengyan-zhang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Zhengyan Zhang # Zhengyan Zhang Zhengyan Zhang has 3 papers in our library, in 2021–2025, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [GPU & parallel computing](https://md.research.elamur.ai/free/en/topics/gpu-parallel-computing/), [Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/); often with [Maosong Sun](https://md.research.elamur.ai/free/en/authors/maosong-sun/), [Zhiyuan Liu](https://md.research.elamur.ai/free/en/authors/zhiyuan-liu/), [Chaojun Xiao](https://md.research.elamur.ai/free/en/authors/chaojun-xiao/). 3 papers in our library · 2021–2025 current affiliation [Jiangsu University of Science and Technology](https://ror.org/00tyjp878), Zhenjiang, China; [Tsinghua University](https://md.research.elamur.ai/free/en/universities/tsinghua-university/), Beijing, China [OpenAlex](https://openalex.org/A5101584823) · [ORCID](https://orcid.org/0000-0003-2988-0083) · [**h-index 21**](https://openalex.org/authors/A5101584823) · [70 works](https://openalex.org/works?filter=author.id:A5101584823) · [11 223 citations](https://openalex.org/works?filter=author.id:A5101584823&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [3 works in our library](https://md.research.elamur.ai/free/en/authors/zhengyan-zhang/#papers) · [535 citations in our library](https://md.research.elamur.ai/free/en/authors/zhengyan-zhang/cited-by/) · 5 more works in our library · [⭐ Paper Star rank #2964](https://md.research.elamur.ai/free/en/paper-stars/page/30/#star-2964) 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=Zhengyan+Zhang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Zhengyan+Zhang) · [dblp](https://dblp.org/search?q=Zhengyan+Zhang) · [ACL Anthology](https://aclanthology.org/search/?q=Zhengyan+Zhang) ## Affiliations - [Tsinghua University](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) · Beijing, China —current · 2017–2026 on 50 papers - [Jiangsu University of Science and Technology](https://ror.org/00tyjp878) · Zhenjiang, China —current · 2011–2026 on 3 papers - [Hong Kong Polytechnic University](https://md.research.elamur.ai/free/en/universities/hong-kong-polytechnic-university/) · Hong Kong, Hong Kong —2024–2025 on 2 papers - [Beijing National Research Center for Information Science and Technology](https://md.research.elamur.ai/free/en/labs/beijing-national-research-center-for-information-science-and-technology/) · Beijing, China —2020–2024 on 12 papers - [Quan Cheng Laboratory](https://ror.org/03drypn60) · Jinan, China —2023 on 2 papers - [State Key Laboratory of Intelligent Technology and Systems](https://md.research.elamur.ai/free/en/labs/state-key-laboratory-of-intelligent-technology-and-systems/) · Beijing —2017–2020 on 3 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 [Language models & pretraining 1](https://md.research.elamur.ai/free/en/topics/language-models/) · [GPU & parallel computing 1](https://md.research.elamur.ai/free/en/topics/gpu-parallel-computing/) · [Efficient models & compression 1](https://md.research.elamur.ai/free/en/topics/efficient-models/) ## Works by year ### 2020s [**2025** 1 paper](https://md.research.elamur.ai/free/en/papers/yuan-2025-native-sparse-attention-hardware/) · [**2024** 1 paper](https://md.research.elamur.ai/free/en/papers/xiao-2024-infllm-training-free-long-context/) · [**2021** 1 paper](https://md.research.elamur.ai/free/en/papers/qi-2021-hidden-killer-invisible-textual-backdoor/) ## Papers The most cited first (OpenAlex and our library). 1. **[Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger](https://md.research.elamur.ai/free/en/papers/qi-2021-hidden-killer-invisible-textual-backdoor/)** *(2021 · 238 citations)* The paper addresses backdoor attacks on NLP models. A model trained on poisoned data behaves normally on ordinary inputs but returns an attacker-chosen label whenever a hidden trigger is present. Earlier textual attacks inserted fixed rare words or sentences as triggers. These insertions damage fluency and are easily… 2. **[Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention](https://md.research.elamur.ai/free/en/papers/yuan-2025-native-sparse-attention-hardware/)** *(2025 · 135 citations)* Standard softmax attention becomes the main cost in long-context language models. The authors estimate it takes 70–80% of decoding latency at 64k tokens. Earlier sparse attention methods often save compute on paper but not in wall-clock time. Many speed up only prefilling or only decoding, clash with GQA/MQA memory… 3. **[InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory](https://md.research.elamur.ai/free/en/papers/xiao-2024-infllm-training-free-long-context/)** *(2024 · 125 citations)* LLMs pre-trained on windows of only a few thousand tokens break down on much longer inputs. Unseen positions push them out of distribution, and large amounts of irrelevant context distract attention. The usual fix, continued pre-training on long sequences, is expensive and can hurt short-context skills. InfLLM avoids… ## Also in our library 5 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 12 of 16 co-authors with a page, the most papers together first. - [Maosong Sun](https://md.research.elamur.ai/free/en/authors/maosong-sun/) ×2 - [Zhiyuan Liu](https://md.research.elamur.ai/free/en/authors/zhiyuan-liu/) ×2 - [Chaojun Xiao](https://md.research.elamur.ai/free/en/authors/chaojun-xiao/) - [Chong Ruan](https://md.research.elamur.ai/free/en/authors/chong-ruan/) - [Damai Dai](https://md.research.elamur.ai/free/en/authors/damai-dai/) - [Fanchao Qi](https://md.research.elamur.ai/free/en/authors/fanchao-qi/) - [Guangxuan Xiao](https://md.research.elamur.ai/free/en/authors/guangxuan-xiao/) - [Huazuo Gao](https://md.research.elamur.ai/free/en/authors/huazuo-gao/) - [Lean Wang](https://md.research.elamur.ai/free/en/authors/lean-wang/) - [Liang Zhao](https://md.research.elamur.ai/free/en/authors/liang-zhao/) - [Mukai Li](https://md.research.elamur.ai/free/en/authors/mukai-li/) - [Xu Han](https://md.research.elamur.ai/free/en/authors/xu-han/) ## Cited by Papers of our library cite their works 535 times (of the 140 884 papers whose bibliographies we read); [20 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/zhengyan-zhang/cited-by/).