Scholar
Yao Xiao
Google Scholar ID: NKKwkGsAAAAJ
Sun Yat-sen University
Citations & Impact
Citations
41
H-index
3
i10-index
1
Publications
4
Co-authors
2
list available
Contact
Publications
Resume (English only)
Academic Achievements
- - Publications:
- - 'Are High-Quality AI-Generated Images More Difficult for Models to Detect?' accepted to ICML 2025
- - 'Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective' accepted to ICLR 2025
- - 'Decoder-Only LLMs are Better Controllers for Diffusion Models' accepted to ACMMM 2024
- - 'Adversarially Robust Source-free Domain Adaptation with Relaxed Adversarial Training' accepted to ICME 2023 (oral)
- - 'Masked Images Are Counterfactual Samples for Robust Fine-tuning' accepted to CVPR 2023
- - Served as a conference reviewer for ICML, ICLR, NeurIPS, AAAI, ACMMM, and journal reviewer for IEEE TNNLS, IEEE TIP
Research Experience
- - Member of HCP Lab, currently a visiting student at LV-Lab, NUS
Education
- - EngD Student, Sun Yat-sen University, supervised by Prof. Liang Lin
- - Visiting Student, National University of Singapore, supervised by Prof. Shuicheng Yan
- - MEng and BEng in Computer Science and Technology, Sun Yat-sen University, graduated in 2023 and 2020 respectively, advised by Prof. Liang Lin, Prof. Cong Liu, and Prof. Pengxu Wei
Background
- - Research Interests: Building trustworthy and evolving deep learning systems for computer vision and beyond, including AI Generated Content (AIGC) detection/evaluation, controllable and efficient image/video generation; Machine Learning: adversarial robustness, domain adaptation, causality in deep learning.
- - Affiliated Labs: HCP Lab (Human-Cyber-Physical Intelligence Integration Lab), LV-Lab (National University of Singapore)
- - Supervisors: Prof. Liang Lin, Prof. Shuicheng Yan
