--- title: "Xiaofeng Zhang — author profile and papers · Reasoning" description: "Xiaofeng Zhang, Shanghai Jiao Tong University: 6 papers on Elamur Research (2023–2026), h-index 1 — affiliations, topics, co-authors and…" canonical: "https://research.elamur.ai/free/en/authors/xiaofeng-zhang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/xiaofeng-zhang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Xiaofeng Zhang # Xiaofeng Zhang Xiaofeng Zhang has 6 papers in our library, in 2023–2026, most of them on [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/), [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/); often with [Xiaosong Yuan](https://md.research.elamur.ai/free/en/authors/xiaosong-yuan/), [Chen Shen](https://md.research.elamur.ai/free/en/authors/chen-shen/), [Yihao Quan](https://md.research.elamur.ai/free/en/authors/yihao-quan/). 6 papers in our library · 2023–2026 [OpenAlex](https://openalex.org/A5139763499) · [**h-index 1**](https://openalex.org/authors/A5139763499) · [19 works](https://openalex.org/works?filter=author.id:A5139763499) · [3 citations](https://openalex.org/works?filter=author.id:A5139763499&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 6 works in our library](https://md.research.elamur.ai/free/en/authors/xiaofeng-zhang/#papers) · [🔗 Cited 128 times in our library](https://md.research.elamur.ai/free/en/authors/xiaofeng-zhang/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #6159](https://md.research.elamur.ai/free/en/paper-stars/page/62/#star-6159) 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=Xiaofeng+Zhang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Xiaofeng+Zhang) · [dblp](https://dblp.org/search?q=Xiaofeng+Zhang) · [ACL Anthology](https://aclanthology.org/search/?q=Xiaofeng+Zhang) ## Affiliations [🎓**Shanghai Jiao Tong University** Shanghai · China 2026 · 11 papers*current*](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) · [🎓**Harbin Institute of Technology** Harbin · China 2026 · 3 papers*current*](https://md.research.elamur.ai/free/en/universities/harbin-institute-of-technology/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 5 The field of science this work belongs to (OpenAlex fields).[Computer Science · 6 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Arts and Humanities · 4 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Artificial Intelligence · 5 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Language and Linguistics · 4 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Computer Vision and Pattern Recognition · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) 🧭 Topics 2 Research subjects and languages the work is about.[Reasoning · 2 works](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Language models & pretraining · 1 work](https://md.research.elamur.ai/free/en/topics/language-models/) ## Works by year ### 2020s [**2026** 3 papers](https://md.research.elamur.ai/free/en/authors/xiaofeng-zhang/year/2026/) · [**2025** 2 papers](https://md.research.elamur.ai/free/en/authors/xiaofeng-zhang/year/2025/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/xiaofeng-zhang/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[Transformer-Patcher: One Mistake worth One Neuron](https://md.research.elamur.ai/free/en/papers/huang-2023-transformer-patcher-one-mistake-worth/)** *(2023 · 123 citations)* Deployed language models keep producing new errors, yet most Model Editing (ME) research fixes only a single mistake at a time. 2. **[Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs](https://md.research.elamur.ai/free/en/papers/zhang-2025-shallow-focus-deep-fixes-enhancing/)** *(2025 · 14 citations)* The paper investigates why large vision-language models (LVLMs) hallucinate, focusing on attention over image tokens, which make up most of the input. 3. **[From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks](https://md.research.elamur.ai/free/en/papers/zhang-2025-redundancy-relevance-information-flow-lvlms/)** *(2025 · 12 citations)* Large vision-language models (LVLMs) turn each image into hundreds of tokens before passing it to an LLM. How those visual tokens actually shape the generated answer has been unclear. The authors study this "information flow", meaning how strongly system, image and user-prompt tokens influence answer tokens, layer by… 4. **[ART: Attention Replacement Technique to Improve Factuality in LLMs](https://md.research.elamur.ai/free/en/papers/luo-2026-art-attention-replacement-technique-improve/)** *(2026 · 1 citation)* This paper links hallucination in LLMs to the way attention is distributed in the earliest layers. Inspecting attention maps of shallow layers (e.g., Layer 0 of Qwen2.5-7B-Instruct on a GSM8K sample), the authors group heads into three types. Uniform heads spread weight evenly over the context, local heads look… 5. **[Diffusion-CAM: Faithful Visual Explanations for dMLLMs](https://md.research.elamur.ai/free/en/papers/zuo-2026-diffusion-cam-faithful-visual-explanations/)** *(2026 · 1 citation)* Diffusion-based multimodal LLMs (dMLLMs) such as LaViDa, LLaDA-V, MMaDA and Dream-VL produce answers by denoising all masked response tokens in parallel. 6. **[Reasoning Fails Where Step Flow Breaks](https://md.research.elamur.ai/free/en/papers/xu-2026-reasoning-fails-where-step-flow/)** *(2026 · 1 citation)* Large reasoning models (LRMs) produce long question–thinking–summary traces, but their mistakes are hard to trace back to specific parts of the reasoning. ## All works 7 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them. 1. [**Transformer-Patcher: One Mistake worth One Neuron arXiv:2301.09785**Zeyu Huang, Yikang Shen, Xiaofeng Zhang, et al.*2023 · 123 citations*](https://md.research.elamur.ai/free/en/papers/huang-2023-transformer-patcher-one-mistake-worth/) 2. **[Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs](https://md.research.elamur.ai/free/en/papers/zhang-2025-shallow-focus-deep-fixes-enhancing/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Xiaofeng Zhang, Yihao Quan, Chen Shen, et al.*2025 · 14 citations* 3. **[From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks](https://md.research.elamur.ai/free/en/papers/zhang-2025-redundancy-relevance-information-flow-lvlms/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Xiaofeng Zhang, Yihao Quan, Chen Shen, et al.*2025 · 12 citations* 4. **[ART: Attention Replacement Technique to Improve Factuality in LLMs](https://md.research.elamur.ai/free/en/papers/luo-2026-art-attention-replacement-technique-improve/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Ziqin Luo, Yihao Quan, Xiaofeng Zhang, et al.*2026 · 1 citation* 5. **[Diffusion-CAM: Faithful Visual Explanations for dMLLMs](https://md.research.elamur.ai/free/en/papers/zuo-2026-diffusion-cam-faithful-visual-explanations/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Haomin Zuo, Yidi Li, Luoxiao Yang, et al.*2026 · 1 citation* 6. **[Reasoning Fails Where Step Flow Breaks](https://md.research.elamur.ai/free/en/papers/xu-2026-reasoning-fails-where-step-flow/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Xiaoyu Xu, Yulan Pan, Xiaosong Yuan, et al.*2026 · 1 citation* 7. **[Fixing Semantic Blind Spots in Anchor Tokens of dMLLMs ↗](https://aclanthology.org/2026.findings-acl.966/) Findings of the Association for Computational Linguistics: ACL 2026 · no summary yet**Ruixuan Xu et al.*2026* ## Co-authors here 12 co-authors with a page, the most papers together first. - [Xiaosong Yuan](https://md.research.elamur.ai/free/en/authors/xiaosong-yuan/) ×4 - [Chen Shen](https://md.research.elamur.ai/free/en/authors/chen-shen/) ×3 - [Yihao Quan](https://md.research.elamur.ai/free/en/authors/yihao-quan/) ×3 - [Chaochen Gu](https://md.research.elamur.ai/free/en/authors/chaochen-gu/) ×2 - [Jieping Ye](https://md.research.elamur.ai/free/en/authors/jieping-ye/) ×2 - [Shaotian Yan](https://md.research.elamur.ai/free/en/authors/shaotian-yan/) ×2 - [Hao Cheng](https://md.research.elamur.ai/free/en/authors/hao-cheng/) - [Hao Tang](https://md.research.elamur.ai/free/en/authors/hao-tang/) - [Jie Zhou](https://md.research.elamur.ai/free/en/authors/jie-zhou/) - [Wenxiao Wang](https://md.research.elamur.ai/free/en/authors/wenxiao-wang/) - [Yikang Shen](https://md.research.elamur.ai/free/en/authors/yikang-shen/) - [Zeyu Huang](https://md.research.elamur.ai/free/en/authors/zeyu-huang/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/) ×3: [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/) ×3 - [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/): [EMNLP 2025](https://md.research.elamur.ai/free/en/venues/emnlp/2025/) - [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/): [NAACL 2025](https://md.research.elamur.ai/free/en/venues/naacl/2025/) - Findings of the Association for Computational Linguistics: ACL 2026 ## Cited by Papers of our library cite their works 128 times (of the 149,439 papers whose bibliographies we read); [24 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/xiaofeng-zhang/cited-by/). Updated 1 November 2026