3 papers
stat.ML2026
MTSSL: Meta-Thresholding Semi-Supervised Learning
Shuyang Liu, Ziang Zeng, Ruiqiu Zheng +4
A large body of Semi-supervised Learning~(SSL) algorithms encounter the threshold to select pseudo-labels. The value of across different SSL algorithms can vary depending…
cs.CV2026
DF-LLaVA: Unlocking MLLMs for Synthetic Image Detection via Knowledge Injection and Conflict-Driven Self-Reflection
Zhuokang Shen, Kaisen Zhang, Bohan Jia +4
With the increasing prevalence of synthetic images, evaluating image authenticity and locating forgeries accurately while maintaining human interpretability remains a challenging t…
stat.ML2025
Probability-density-aware Semi-supervised Learning
Shuyang Liu, Ruiqiu Zheng, Yunhang Shen +4
Semi-supervised learning (SSL) assumes that neighbor points lie in the same category (neighbor assumption), and points in different clusters belong to various categories (cluster a…