--- title: "Richong Zhang — author profile and papers" description: "Richong Zhang, Beihang University: 3 papers on Elamur Research (2019–2024), h-index 29 — affiliations, topics, co-authors and who cites them in our…" canonical: "https://research.elamur.ai/free/en/authors/richong-zhang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/richong-zhang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Richong Zhang # Richong Zhang Richong Zhang works in natural language processing with neural networks. Their papers here follow three threads: classifying the opinions expressed in text, building shared tooling for adapting large language models, and multimodal models that connect language to images. Two concerns recur. One is how linguistic or visual structure can be given to a model. The other is how existing models can be adapted to new tasks with less effort. The work sits mainly within [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) and [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/), with further papers on sentiment and dialogue. The most cited of Zhang's papers here is [LlamaFactory](https://md.research.elamur.ai/free/en/papers/zheng-2024-llamafactory-unified-efficient-fine-tuning/) (2024). It is an open-source framework that brings parameter-efficient tuning methods such as LoRA and QLoRA together in one toolkit covering more than a hundred open language models. Separate modules load models, convert datasets into a common format and run training, and a web interface sits on top. An earlier paper, [Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree](https://md.research.elamur.ai/free/en/papers/sun-2019-aspect-level-sentiment-analysis-convolution/) (2019), decides whether a sentence is positive, negative or neutral toward one particular aspect term. Its model, CDT, refines Bi-LSTM word vectors with a graph convolutional network run over the dependency parse. The reasoning is that syntax brings aspects close to the words that express opinions about them. The newer papers shift from single-task text classifiers toward general-purpose large models. [Shikra](https://md.research.elamur.ai/free/en/papers/chen-2023-shikra-unleashing-multimodal-llm-s/) (2023) addresses what its authors call referential dialogue. In this setting, a multimodal LLM lets a user point to a region of an image and can itself indicate where the objects it mentions are located. Together with LlamaFactory, it points to an interest in making large models easier to adapt and better grounded in what they see. Zhang is based at [Beihang University](https://md.research.elamur.ai/free/en/universities/beihang-university/) in Beijing, with bylines there from 2012 onward. Earlier and overlapping papers list the [University of Ottawa](https://md.research.elamur.ai/free/en/universities/university-of-ottawa/) and the [State Key Laboratory of Software Development Environment](https://md.research.elamur.ai/free/en/labs/state-key-laboratory-of-software-development-environment/) in Beijing. Co-authors on the papers here include [Kai Sun](https://md.research.elamur.ai/free/en/authors/kai-sun/), [Keqin Chen](https://md.research.elamur.ai/free/en/authors/keqin-chen/) and [Rui Zhao](https://md.research.elamur.ai/free/en/authors/rui-zhao/). Richong Zhang has 3 papers in our library, in 2019–2024, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/), [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/); often with [Kai Sun](https://md.research.elamur.ai/free/en/authors/kai-sun/), [Keqin Chen](https://md.research.elamur.ai/free/en/authors/keqin-chen/), [Rui Zhao](https://md.research.elamur.ai/free/en/authors/rui-zhao/). 3 papers in our library · 2019–2024 current affiliation [Beihang University](https://md.research.elamur.ai/free/en/universities/beihang-university/) · Beijing China [OpenAlex](https://openalex.org/A5027015677) · [ORCID](https://orcid.org/0000-0002-1207-0300) · [Wikidata](https://www.wikidata.org/wiki/Q130879253) · [**h-index 29**](https://openalex.org/authors/A5027015677) · [218 works](https://openalex.org/works?filter=author.id:A5027015677) · [3,556 citations](https://openalex.org/works?filter=author.id:A5027015677&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [3 works in our library](https://md.research.elamur.ai/free/en/authors/richong-zhang/#papers) · [807 citations in our library](https://md.research.elamur.ai/free/en/authors/richong-zhang/cited-by/) · 3 more works in our library · [⭐ Paper Star rank #1339](https://md.research.elamur.ai/free/en/paper-stars/page/14/#star-1339) 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=Richong+Zhang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Richong+Zhang) · [dblp](https://dblp.org/search?q=Richong+Zhang) · [ACL Anthology](https://aclanthology.org/search/?q=Richong+Zhang) ## Affiliations [🎓**Beihang University** Beijing · China 2012–2026 · 190 papers*current*](https://md.research.elamur.ai/free/en/universities/beihang-university/) · [🎓**University of Ottawa** Ottawa · Canada 2008–2021 · 18 papers](https://md.research.elamur.ai/free/en/universities/university-of-ottawa/) · [🔬**State Key Laboratory of Software Development Environment** Beijing 2014–2020 · 14 papers](https://md.research.elamur.ai/free/en/labs/state-key-laboratory-of-software-development-environment/) · [🎓**University of Leeds** Leeds · United Kingdom 2019–2020 · 3 papers](https://md.research.elamur.ai/free/en/universities/university-of-leeds/) 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 2](https://md.research.elamur.ai/free/en/topics/language-models/) · [Sentiment & emotion 1](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [Dialogue systems 1](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · [Vision & language 1](https://md.research.elamur.ai/free/en/topics/multimodal/) ## Works by year ### 2020s [**2024** 1 paper](https://md.research.elamur.ai/free/en/papers/zheng-2024-llamafactory-unified-efficient-fine-tuning/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/papers/chen-2023-shikra-unleashing-multimodal-llm-s/) ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/papers/sun-2019-aspect-level-sentiment-analysis-convolution/) ## Papers The most cited first (OpenAlex and our library). 1. **[LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://md.research.elamur.ai/free/en/papers/zheng-2024-llamafactory-unified-efficient-fine-tuning/)** *(2024 · 1,035 citations)* Many open LLMs and many parameter-efficient tuning methods now exist, but each method usually has to be wired into each model by hand. 2. **[Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree](https://md.research.elamur.ai/free/en/papers/sun-2019-aspect-level-sentiment-analysis-convolution/)** *(2019 · 497 citations)* The paper addresses aspect-based sentiment classification: deciding whether a sentence conveys a positive, negative or neutral opinion toward one aspect term. 3. **[Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://md.research.elamur.ai/free/en/papers/chen-2023-shikra-unleashing-multimodal-llm-s/)** *(2023 · 194 citations)* Current multimodal LLMs can describe what an image contains, but they cannot handle where things are. A user cannot point to a region, and the model cannot point back to the objects it mentions. The authors call this missing ability Referential Dialogue (RD) and present Shikra, a generalist MLLM designed for it. ## Also in our library 3 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 3 co-authors with a page, the most papers together first. - [Kai Sun](https://md.research.elamur.ai/free/en/authors/kai-sun/) - [Keqin Chen](https://md.research.elamur.ai/free/en/authors/keqin-chen/) - [Rui Zhao](https://md.research.elamur.ai/free/en/authors/rui-zhao/) ## Cited by Papers of our library cite their works 807 times (of the 140,884 papers whose bibliographies we read); [38 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/richong-zhang/cited-by/).