Tat-Seng Chua
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces PARL, a framework that learns personalized evaluation rubrics directly from raw user interaction histories to accurately assess how well LLM outputs align with subjective, user-specific preferences.
The paper proposes the Shortcut Subspace Suppression (S^3) framework to improve deepfake detection generalization by explicitly identifying and suppressing method-specific shortcuts in learned feature representations.
Papers
Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection
Yihui Wang, Yonghui Yang, Jilong Liu, Fengbin Zhu +2 more
The paper proposes the Shortcut Subspace Suppression (S^3) framework to improve deepfake detection generalization by explicitly identifying and suppressing method-specific shortcuts in learned feature…