4 papers
$\textbf{AGT$^{AO}$}$: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality
Pengyu Li, Lingling Zhang, Zhitao Gao +5
While Large Language Models (LLMs) have achieved remarkable capabilities, they unintentionally memorize sensitive data, posing critical privacy and security risks. Machine unlearni…
Rank-Aware Agglomeration of Foundation Models for Immunohistochemistry Image Cell Counting
Zuqi Huang, Mengxin Tian, Huan Liu +6
Accurate cell counting in immunohistochemistry (IHC) images is critical for quantifying protein expression and aiding cancer diagnosis. However, the task remains challenging due to…
Beyond ImageNet: Understanding Cross-Dataset Robustness of Lightweight Vision Models
Weidong Zhang, Pak Lun Kevin Ding, Huan Liu
Lightweight vision classification models such as MobileNet, ShuffleNet, and EfficientNet are increasingly deployed in mobile and embedded systems, yet their performance has been pr…
Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations
Zhen Tan, Song Wang, Yifan Li +4
Post-hoc explanation methods provide interpretation by attributing predictions to input features. Natural explanations are expected to interpret how the inputs lead to the predicti…