Xiaoye Zhu
Logo Logo Master

I am a master's student majoring in Electronic Information (Artificial Intelligence) at South China University of Technology. Previously, I participated in a non-degree research program at the NUS (Chongqing) Research Institute, where I focused on reinforcement learning and multimodal large models.

My research interests center on Large Language Models and Agents. I have been fortunate to work on cutting-edge research projects, including AI-generated content detection and representation for multimodal generative tasks, with related work published in top-tier conferences such as AAAI and CVPR.


Education
  • South China University of Technology
    South China University of Technology
    Future Technology Institute
    Master in Electronic Information (Artificial Intelligence)
    Sep. 2025 - present
  • NUS (Chongqing) Research Institute
    NUS (Chongqing) Research Institute
    Research Student in ECE (Non-degree)
    Sep. 2024 - Jun. 2025
  • South China University of Technology
    South China University of Technology
    Future Technology Institute
    Bachelor in Artificial Intelligence
    Sep. 2021 - Jun. 2025
Experience
  • TENCENT - LIGHTSPEED STUDIOS
    TENCENT - LIGHTSPEED STUDIOS
    NLP Research Intern
    May. 2025 - August. 2025
Honors & Awards
  • First Prize in the "Greater Bay Area Cup" Guangdong-Hong Kong-Macao Financial Mathematics Modeling Competition
    2023
  • Second Prize in the Asia and Pacific Mathematical Contest in Modeling
    2023
  • University Third-Class Scholarships
    2022 - 2024
  • Excellence Group Third Class Scholarship
    2022
  • EVE Energy Third Class Scholarship
    2023
  • Hongping Evergreen Scholarship
    2024
News
2025
Our paper 'Imitate Before Detect' has been selected for oral presentation at the AAAI 25! Learn more
Feb 15
2024
Our paper homepage for "Imitate Before Detect" is now published. Learn more
Dec 07
Selected Publications
Symbolic Representation for Any-to-Any Generative Tasks
Symbolic Representation for Any-to-Any Generative Tasks

Jiaqi Chen*, Xiaoye Zhu*, Yue Wang*, Tianyang Liu, Xinhui Chen, Ying Chen, Chak Tou Leong, Yifei Ke, Joseph Liu, Yiwen Yuan, Julian McAuley, Li-jia Li (* equal contribution)

IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2025

We propose a symbolic generative task description language and inference engine, capable of representing arbitrary multimodal tasks as symbolic flows.

Symbolic Representation for Any-to-Any Generative Tasks

Jiaqi Chen*, Xiaoye Zhu*, Yue Wang*, Tianyang Liu, Xinhui Chen, Ying Chen, Chak Tou Leong, Yifei Ke, Joseph Liu, Yiwen Yuan, Julian McAuley, Li-jia Li (* equal contribution)

IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2025

We propose a symbolic generative task description language and inference engine, capable of representing arbitrary multimodal tasks as symbolic flows.

Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection
Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection

Jiaqi Chen*, Xiaoye Zhu*, Tianyang Liu*, Ying Chen, Xinhui Chen, Yiwen Yuan, Chak Tou Leong, Zuchao Li, Tang Long, Lei Zhang, Chenyu Yan, Guanghao Mei, Jie Zhang, Lefei Zhang (* equal contribution)

Association for the Advancement of Artificial Intelligence (AAAI) 2025 Oral

Large Language Models (LLMs) have revolutionized text generation, making detecting machine-generated text increasingly challenging. Learn more

Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection

Jiaqi Chen*, Xiaoye Zhu*, Tianyang Liu*, Ying Chen, Xinhui Chen, Yiwen Yuan, Chak Tou Leong, Zuchao Li, Tang Long, Lei Zhang, Chenyu Yan, Guanghao Mei, Jie Zhang, Lefei Zhang (* equal contribution)

Association for the Advancement of Artificial Intelligence (AAAI) 2025 Oral

Large Language Models (LLMs) have revolutionized text generation, making detecting machine-generated text increasingly challenging. Learn more

All publications