Hello, I am Keyan Zhou(ε¨ζ―θ¨), a second year master student at the Artificial Intelligence Research Institute of Soochow University, under the supervision of Prof. Juntao Li and Prof. Min Zhang.
Before this, I received my Bachelorβs degree (2019-2023, computer science) from Soochow University.
At present, I am working as a Multi-modal LLM R&D Intern at ByteDance, focusing on enhancing domain-specific reasoning capabilities of LVLMs.
π€ My research interests center on the concept of knowledge in LLMs/LVLMs, particularly within Long Contexts and Long Generation. Specifically, I focus on the following aspects:
- Knowledge Dynamics: Exploring mechanisms for LLMs/LVLMs to dynamically integrate internal knowledge with external information. Resolving knowledge conflicts, mitigating outdated information, and addressing safety risks to improve model trustworthiness.
- Reliable Reasoning: Focusing on how LLMs/LVLMs can iteratively refine their reasoning by cross-verifying and self-correct knowledge from multi-sources to reduce hallucinations and improve reliability.
π€ Iβm looking for a PhD position in 2026 Fall. Please email me at jonaszhou01@gmail.com if there is a potential opportunity!
π Publications
* denotes equal contribution.
L-CiteEval: A Suite for Evaluating Fidelity of Long-context Models
Zecheng Tang*, Keyan Zhou*, Juntao Li, Baibei Ji, Jianye Hou, Min Zhang
- This work proposes a long-context benchmark L-CiteEval, which evaluates the citation quality of LCMs and highlights the tendency of current open-source LCMs to rely on intrinsic knowledge rather than the provided context for generating responses.
CMD: a framework for Context-aware Model self-Detoxification
Zecheng Tang*, Keyan Zhou*, Juntao Li, Yuyang Ding, Pinzheng Wang, Yan Bowen, Renjie Hua, Min Zhang
- This work proposes a context-aware detoxification framework, balancing detoxification and generation quality.
Revealing and Mitigating Over-attention in Knowledge Editing
Pinzheng Wang, Zecheng Tang, Keyan Zhou, Juntao Li, Qiaoming Zhu, Min Zhang
- This work reveals the over-attention issue in knowledge eiditing.
LOOM-Scope: a comprehensive and efficient LOng-cOntext Model evaluation framework
Zecheng Tang, Haitian Wang, Quantong Qiu, Baibei Ji, Ruoxi Sun, Keyan Zhou, Juntao Li, Min Zhang
- This work standardizes long-context evaluation across 22 benchmarks, integrates inference acceleration techniques, and introduces a lightweight comprehensive long-context benchmark called LOOMBench.
-
Zecheng Tang, Pinzheng Wang, Keyan Zhou, Juntao Li, Ziqiang Cao, Min Zhang
π Honors and Awards
- National Scholarship, Ministry of Education
- Soochow University Outstanding Graduate
- Huawei Scholarship
- Mathematical Contest in Modeling(MCM) Finalist Winner
π Educations
- 2023.09 - current, Master, Artificial Intelligence Research Institute, Soochow University, Suzhou.
- 2019.09 - 2023.06, Bachelor, Institute of Computer Science and Technology, Soochow University, Suzhou.
π¬ Invited Talks
π» Internships
- 2025.06 - current, Multi-modal LLM R&D Intern, ByteDance, Shanghai, China.
- 2025.03 - 2025.05, Long-Context LLM Research Intern, MiraclePlus, Shanghai, China.