Edge-based circuits in vision transformers can be automatically recovered to explain and steer model computations for classification and adversarial behaviors.
arXiv preprint arXiv:2206.01627 (2022) 3
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A concept-based pruning method for DNNs guided by interpretable concepts and system requirements produces smaller, computationally efficient models that maintain effectiveness on image classification tasks.
citing papers explorer
-
Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers
Edge-based circuits in vision transformers can be automatically recovered to explain and steer model computations for classification and adversarial behaviors.
-
Engineering Resource-constrained Software Systems with DNN Components: a Concept-based Pruning Approach
A concept-based pruning method for DNNs guided by interpretable concepts and system requirements produces smaller, computationally efficient models that maintain effectiveness on image classification tasks.