Zhen Xiong
Zhen Xiong

Zhen Xiong

Computer Science Graduate Student @ USC | NLP Researcher

I am a graduate student from the Dept. of CS @ University of Southern California. I am currently researching on Large Language Model (LLM) and its application.

Large Language ModelsNatural Language ProcessingDeep Learning

Publications

Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM
Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM

Empirical Methods in Natural Language Processing (EMNLP) 2025.

Zhen Xiong, Yujun Cai, Zhecheng Li, Yiwei Wang

PDF Code
Texture or Semantics? Vision-Language Models Get Lost in Font Recognition
Texture or Semantics? Vision-Language Models Get Lost in Font Recognition

Conference of Language Modeling (COLM) 2025.

Zhecheng Li, Guoxian Song, Yujun Cai, Zhen Xiong, Junsong Yuan, Yiwei Wang

PDF
Vulnerability of LLMs to Vertically Aligned Text Manipulations
Vulnerability of LLMs to Vertically Aligned Text Manipulations

Association for Computational Linguistics (ACL) 2025.

Zhecheng Li, Yiwei Wang, Bryan Hooi, Yujun Cai, Zhen Xiong, Nanyun Peng, Kai-wei Chang

PDF
TAGExplainer: Narrating Graph Explanations for Text-Attributed Graph Learning Models
TAGExplainer: Narrating Graph Explanations for Text-Attributed Graph Learning Models

Association for Computational Linguistics (ACL) 2025.

Bo Pan*, Zhen Xiong*, Guanchen Wu*, Zheng Zhang, Yifei Zhang, Liang Zhao (*equal contribution)

PDF
Enhancing Image Generation Fidelity via Progressive Prompts
Enhancing Image Generation Fidelity via Progressive Prompts

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2025.

Zhen Xiong, Yuqi Li, Chuanguang Yang, Tiao Tan, Zhihong Zhu, Siyuan Li, Yue Ma

PDF

Preprints

Unveiling the Potential of Diffusion Large Language Model in Controllable Generation
Unveiling the Potential of Diffusion Large Language Model in Controllable Generation

arXiv preprint arXiv:2507.04504.

Zhen Xiong, Yujun Cai, Zhecheng Li, Yiwei Wang

PDF
Enhancing LLM Character-Level Manipulation via Divide and Conquer
Enhancing LLM Character-Level Manipulation via Divide and Conquer

arXiv preprint arXiv:2502.08180.

Zhen Xiong, Yujun Cai, Bryan Hooi, Nanyun Peng, Zhecheng Li, Yiwei Wang

PDF