logo
today local_bar
Inherent interpretability

1 paper across 1 session

Poster Session 4

1 paper
Thursday, December 4, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
FaCT: Faithful Concept Traces for Explaining Neural Network Decisions
#1000 · Amin Parchami-Araghi, Sukrut Rao, Jonas Fischer, Bernt Schiele

A new model with inherent mechanistic and concept-based explanations and a new concept consistency evaluation framework