@everyone 📣 **New Research Digest **👀

Can AI learn from how humans feel rather than just what they see?

Online sexism continues to affect millions of people, yet detecting it remains surprisingly difficult. Harmful content is often disguised through humor, ambiguity, or context that traditional AI systems struggle to interpret.

In our latest Research Digest, researchers from PRHLT and ValgrAI used Neon eye tracking, EEG, and physiological sensing to investigate how people process sexist memes.

The results suggest that subtle signals such as fixation behavior, blink patterns, and pupil responses may reveal information that images and text alone cannot.

The study offers a fascinating glimpse into a future where AI learns not only from content, but also from human perception.

📰 Read the full Research Digest here

Video: A participant viewing sexist and non-sexist memes from the EXIST 2025 dataset while wearing Neon eye tracking glasses. Courtesy of Iván Arcos.