works on
ai-generated text detection 1contrastive learning 1dynamic modeling 1latent trajectories 1text embeddings 1

From the 1 of 4 linked papers with an AI index.

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

Gradient-Skipping Relevance Propagation for Efficient Explainability of Vision Transformers

Christopher Buratti, Michele Marchetti, Federica Parlapiano +3

Vision Transformers (ViTs) are difficult to interpret because current methods of relevance propagation and attention flow do not fully consider some key architectural features, suc…