I am currently a Ph.D. student at the College of Future Information Technology, Fudan University, under the supervision of Professor Xiaodong Gu. I earned my Bachelor’s degree from the same institution in 2023.
My research interests lie at the Vision-Language Models (VLMs), encompassing transfer learning, few-shot learning, and domain generalization. Currently, my work focuses on AI-generated image detection, text-to-image generation, and VLA-style game agents.
I am currently a Tencent Qingyun Program research intern.
🔥 News
- 2026.05: 🎉 OmniAID was accepted by ICML 2026!
- 2025.12: 🎉 MMRL++ was accepted by IJCV 2026!
- 2025.02: 🎉 MMRL was accepted by CVPR 2025!
- 2024.03: 🎉 JoAPR was accepted by CVPR 2024!
📝 Publications
OmniAID: Decoupling Semantic and Artifacts for Universal AI-Generated Image Detection in the Wild
Yuncheng Guo, Junyan Ye, Chenjue Zhang, Hengrui Kang, Haohuan Fu, Conghui He, Weijia Li
MMRL: Multi-Modal Representation Learning for Vision-Language Models
Yuncheng Guo, Xiaodong Gu
JoAPR: Cleaning the Lens of Prompt Learning for Vision-Language Models
Yuncheng Guo, Xiaodong Gu
💻 Internships
- 2026.03 - present, Research Intern (Qingyun Program), Lightspeed Studios, Tencent.
- 2025.07 - 2026.02, Multimodal Algorithm Intern, OpenDataLab, Shanghai AI Lab.
- 2024.03 - 2024.06, LLM Application Algorithm Intern, Feishu, Bytedance.
🎖 Honors and Awards
- 2025-2026, National Scholarship, Fudan University Opple Lighting Scholarship
- 2024-2025, Fudan University Yang Longhu & Li Shaosi Scholarship, Fudan University Xiaomi Scholarship
- 2023-2024, Fudan University Chen Xiaoming & He Peixin Scholarship
- 2019-2023, Shanghai Outstanding Graduate, Fudan University Outstanding Student, National Endeavor Scholarship
📖 Educations
- 2023.09 - present, Ph.D. in Electronic Science and Technology, College of Future Information Technology, Fudan University
- 2019.09 - 2023.06, B.S. in Electronic Information Science and Technology, School of Information Science and Technology, Fudan University