Xiao Guo

I am a final-year Ph.D. student in the CVLab of Michigan State University, advised by Prof. Xiaoming Liu. Before that, I spent years as a research programmer at USC/ISI, advised by Prof. Iacopo Masi and Prof. Wael AbdAlmageed. I obtain my master and bachelor at the University of Southern California and Wuhan University of Technology, respectively.

I have been a main contributor to several major U.S. government-sponsored projects, including MediFor, ODIN, and RED. In addition, I spent two wonderful summer as an intern at Amazon in 2023 and 2024, working with Dr. Yue Rex Wu and Dr. Hongcheng Wang, respectively.

My research interests include:

• Multi-modal Learning and Vision-Language Model: M2F2-Det (CVPR25-oral), DDVQA-BLIP (ECCV24), and MM-Det (NeurIPS24).
• Image Generative Model: DenseFace (ArXiv24).
• Responsible AI, e.g., Deepfake/Anti-spoofing: HiFi-Net (CVPR23), HiFi-Net++ (IJCV24), and FAS-Wrapper (ECCV22-oral).

Email  /  CV  /  Scholar  /  Github

code

A personalized face generation T2I diffusion model via dense landmarks prediction.

code

An image forgery detection and localization method for both digital manipulation and image editing domains.

code

A new model for multi-domain face anti-spoofing, which addresses the forgetting issue when learning new domain data.

code

Image Forgery Detection and Localization; An extension work of HiFi-Net (CVPR23).

code

A forgery video detection method based the LLama-2.

code

Fine-tuning BLIP for deepfake detection VQA.

Introduce a learnable graph pooling network for the model parsing.