#artificial intelligence
May 2026
FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness
FragileFlow is introduced, a plug-in regularizer that uses a calibrated margin buffer to identify correct-but-fragile predictions and organize their off-class probability mass into a class-wise vulnerable-risk matrix and provides the first PAC-Bayes upper bound for this margin-aware error-flow object.
Zhuo-Yun Li, Bo-Xuan Wang, Jinwei Hu et al.
· arXiv.org · 4 citations