1

Spectral Principal Paths: A Spectral Perspective on Linear Representation Formation in LLMs
High-level representations have become a central focus in enhancing AI transparency and control, shifting attention from individual …
Bowei Tian, Xuntao Lyu, Meng Liu, Hongyi Wang, Ang Li
PDF Cite
SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence
Deep learning models exhibit fairness concerns when predictions are inadvertently influenced by sensitive attributes. However, existing …
Bowei Tian, Yexiao He, Ziyao Wang, Meng Liu, Yongkai Wu, Ang Li
PDF Cite Code
Towards counterfactual fairness through auxiliary variables
The challenge of balancing fairness and predictive accuracy in machine learning models, especially when sensitive attributes such as …
Bowei Tian, Ziyao Wang, Shwai He, Wanghao Ye, Guoheng Sun, Yucong Dai, Yongkai Wu, Ang Li
PDF Cite Code
Towards counterfactual fairness through auxiliary variables
FairViT: Fair Vision Transformer via Adaptive Masking
Vision Transformer (ViT) has achieved excellent performance and demonstrated its promising potential on various computer vision tasks. …
Bowei Tian, Ruijie Du, Yanning Shen
PDF Cite Code
FairViT: Fair Vision Transformer via Adaptive Masking