@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.
@everyone New Alpha Lab is live.
This one shows how to synchronize Neon eye tracking with EEG data from the Mentalab Explore Pro system in a mobile, real-world setup.
We walk through how to capture visual attention and brain activity from a participant in motion, with synchronized data streams ready for analysis.
Follow the tutorial and start building your own EEG + eye tracking experiments: https://docs.pupil-labs.com/alpha-lab/mentalab
@everyone 📣 📣 Another New Research Digest 👀
Can robots communicate their intentions with a simple glance?
To find out, Lara Naendrup-Poell and Linda Onnasch from Technische Universität Berlin investigated whether gaze-like visual cues can help people anticipate a robot's next action.
Using Neon, they measured how participants responded to a collaborative robot displaying eyes, arrows, or no visual cues at all.
The findings showed robotic eyes guided attention more effectively than arrows, helping participants predict the robot's movements faster and more consistently. But they also revealed when the robot's cues became unreliable, people quickly changed their visual strategy and stopped relying on them.
The study highlights how attention and trust are closely linked in human-robot collaboration, offering valuable insights for the design of future collaborative systems.
📰 Read the full Research Digest here.
Video: A participant wearing Neon eye tracking glasses during a collaborative task with the CoBot (source)