← Search

Dilyara Bareeva

2 accepted papers

2025

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers

NeurIPS 2025poster

Measuring the alignment between representations lets us understand similarities between the feature spaces of different models, such as Vision Transformers trained under diverse paradigms. However, traditional measures for representational alignment yield only scalar values that obscure how these sp…

Cited by 0SourcecodeScholar
2025

Manipulating Feature Visualizations with Gradient Slingshots

NeurIPS 2025poster

Feature Visualization (FV) is a widely used technique for interpreting concepts learned by Deep Neural Networks (DNNs), which synthesizes input patterns that maximally activate a given feature. Despite its popularity, the trustworthiness of FV explanations has received limited attention. We introduc…

Cited by 0SourcecodeScholar