2 papers
cs.LG2026
Concept Flow Models: Anchoring Concept-Based Reasoning with Hierarchical Bottlenecks
Ya Wang, Adrian Paschke
Concept Bottleneck Models (CBMs) enhance interpretability by projecting learned features into a human-understandable concept space. Recent approaches leverage vision-language model…
cs.LG2025
Neural Network-Powered Finger-Drawn Biometric Authentication
Maan Al Balkhi, Kordian Gontarska, Marko Harasic +1
This paper investigates neural network-based biometric authentication using finger-drawn digits on touchscreen devices. We evaluated CNN and autoencoder architectures for user auth…