FAccT 2025 in Athens
I presented my work at FAccT 2025 in Athens in the session “Papers: Images and Faces,” which brought together cutting-edge research on fairness, bias, and social perception in facial and vision-based AI systems.
The session took place on June 25, 2025, in Arts Lounge B, and featured a rich set of interdisciplinary contributions:
-
Gone With the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Images
Tian Qiu, Arjun Nichani, Rasta Tadayontahmasebi, Haewon Jeong -
Performance Differentials in Deployed Biometric Systems Caused by Open-Source Face Detectors
Cynthia M. Cook et al. -
Social Bias in Vision Transformers: A Comparative Study Across Architectures and Learning Paradigms
Takehiro Tsurumi, Elena Beretta -
Social Perception of Faces in a Vision-Language Model
Carina I. Hausladen, Manuel Knott, Colin F. Camerer, Pietro Perona -
What TikTok Claims, What Bold Glamour Does: A Filter’s Paradox
Miriam Doh, Corinna Canali, Nuria Oliver -
Component-Based Fairness in Face Attribute Classification with Bayesian Network-informed Meta Learning
Yifan Liu et al. (online)
