"representation interpretability" Papers

Advancing Interpretability of CLIP Representations with Concept Surrogate Model

Nhat Hoang-Xuan, Xiyuan Wei, Wanli Xing et al.

Enhancing Pre-trained Representation Classifiability can Boost its Interpretability

Sparse Fine-Tuning of Transformers for Generative Tasks

Wei Chen, Jingxi Yu, Zichen Miao et al.