today local_bar

Johanna Vielhaben

PhD student, Fraunhofer HHI

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers

#1016 · Johanna Vielhaben, Dilyara Bareeva, Jim Berend, Wojciech Samek, Nils Strodthoff

Representational alignment based on concept discovery across ViTs trained on different tasks.