Scholar
Zhen Xiong
Google Scholar ID: jRhm61IAAAAJ
University of Southern California
Multimodal Language Models
Natural Language Processing
Computer Vision
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
28
H-index
4
i10-index
0
Publications
11
Co-authors
6
list available
Contact
Email
xiongzhe@usc.edu
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
14 items
The LLM Data Auditor: A Metric-oriented Survey on Quality and Trustworthiness in Evaluating Synthetic Data
2026
Cited
0
Not in Sync: Unveiling Temporal Bias in Audio Chat Models
2025
Cited
0
Generalist Scanner Meets Specialist Locator: A Synergistic Coarse-to-Fine Framework for Robust GUI Grounding
2025
Cited
0
Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models
2025
Cited
0
Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction
2025
Cited
0
$A^2R^2$: Advancing Img2LaTeX Conversion via Visual Reasoning with Attention-Guided Refinement
2025
Cited
0
Unveiling the Potential of Diffusion Large Language Model in Controllable Generation
2025
Cited
0
Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM
2025
Cited
0
Load more
Resume (English only)
Academic Achievements
- Publications:
* "Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM", EMNLP 2025
* "Enhancing Image Generation Fidelity via Progressive Prompts", ICASSP 2025
* "TAGExplainer: Narrating Graph Explanations for Text-Attributed Graph Learning Models", ACL 2025
* "Texture or Semantics? Vision-Language Models Get Lost in Font Recognition", COLM 2025
* "Vulnerability of LLMs to Vertically Aligned Text Manipulations", ACL 2025
- Preprints:
* "Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models", arXiv:2509.21749
* "Unveiling the Potential of Diffusion Large Language Model in Controllable Generation", arXiv:2507.04504
* "Advancing Img2LaTeX Conversion via Visual Reasoning with Attention-Guided Refinement", arXiv:2507.20890
* "Generalist Scanner Meets Specialist Locator: A Synergistic Coarse-to-Fine Framework for Robust GUI Grounding", arXiv:2509.24133
* "Enhancing LLM Character-Level Manipulation via Divide and Conquer", arXiv:2502.08180
- Awards & Honors:
* National Scholarship, 2021
* Renming Scholarship (Top University Scholarship), 2021, 2022, 2023
* 1st Prize, Mathematics Competition of Chinese College Students, 2022
* 1st Prize, University Competitive Programming Contest, 2022
* 2nd Prize, Beijing College Student Mathematical Modeling Competition, 2022
* University Outstanding Academic Achievement Award, 2021, 2022, 2023
Research Experience
- Currently conducting research on Large Language Models at the University of Southern California
Education
- University of Southern California, Master of Science in Computer Science, Jan. 2025 – Present, GPA: 3.92/4.00
- University of California, Irvine, Joint Undergraduate Education Program, Sept. 2023 – Jun. 2024, GPA: 4.00/4.00
- Beijing University of Chemical Technology, Bachelor of Engineering in Computer Science, Sept. 2020 – Jul. 2023, GPA: 93.86/100, Ranked: 1/161
Background
- Research Interests: Large Language Models (LLMs) and their interpretability, controllability, and applications
- Professional Fields: Multimodal Large Language Models, Natural Language Processing, Computer Vision
- Brief Introduction: Second-year graduate student at the University of Southern California, planning to apply for Fall 2026 PhD programs
Co-authors
6 total
Yujun Cai
NTU → Meta → Lecturer(Assistant Professor) @UQ
Zhecheng Li
University of California San Diego
Yiwei Wang
University of California at Merced
Nanyun (Violet) Peng
Associate Professor, UCLA
Bryan Hooi
National University of Singapore
Yue Ma (马跃)
HKUST | Tsinghua | Tencent | Meta
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up