16 citations · 16 across the 5 of their papers we have counts for
Showing 2025Show all
3 papers · 1 filter
cs.AI2025
Cultural Alien Sampler: Open-ended art generation balancing originality and coherence
Alejandro H. Artiles, Hiromu Yakura, Levin Brinkmann +6
In open-ended domains like art, autonomous agents must generate ideas that are both original and internally coherent, yet current Large Language Models (LLMs) either default to fam…
cs.CV2025
Discovering Intersectional Bias via Directional Alignment in Face Recognition Embeddings
Ignacio Serna
Modern face recognition models embed identities on a unit hypersphere, where identity variation forms tight clusters. Conversely, shared semantic attributes can often be effectivel…
cs.CV2025
A Rapid Test for Accuracy and Bias of Face Recognition Technology
Manuel Knott, Ignacio Serna, Ethan Mann +1
Measuring the accuracy of face recognition (FR) systems is essential for improving performance and ensuring responsible use. Accuracy is typically estimated using large annotated d…