Cassio F. Dantas

Identifiers

• name variant Cassio F. Dantas 0.60 · backfill

Papers (2)

1. Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations cs.CV · 2026 · author #2
2. Metonymy in vision models undermines attention-based interpretability cs.CV · 2026 · author #2

Mentions

• 2606.24716 #2 · arxiv_oai · confidence 0.70 Cassio F. Dantas

Frequent Coauthors

• Diego Marcos 2 shared papers
• Ananthu Aniraj 1 shared papers
• Beg\"um Demir 1 shared papers
• Dino Ienco 1 shared papers
• Jonas Klotz 1 shared papers
• Massimiliano Mancini 1 shared papers
• Pallavi Jain 1 shared papers