5 papers
Now You See the Hate: Adaptive View Retrieval for Hidden Hateful Illusions
Qianpu Chen, Derya Soydaner
Hateful optical illusions expose a serious gap in current multimodal safety systems. On original-view hateful illusions, previous work shows that six moderation classifiers achieve…
In Trust We Survive: Emergent Trust Learning
Qianpu Chen, Giulio Barbero, Mike Preuss +1
We introduce Emergent Trust Learning (ETL), a lightweight, trust-based control algorithm that can be plugged into existing AI agents. It enables these to reach cooperation in compe…
When Visual Evidence is Ambiguous: Pareidolia as a Diagnostic Probe for Vision Models
Qianpu Chen, Derya Soydaner, Rob Saunders
When visual evidence is ambiguous, vision models must decide how to interpret face-like patterns. Face pareidolia, the perception of faces in non-face objects, provides a controlle…
Have Large Vision-Language Models Mastered Art History?
Ombretta Strafforello, Derya Soydaner, Michiel Willems +2
The emergence of large Vision-Language Models (VLMs) has established new baselines in image classification across multiple domains. We examine whether their multimodal reasoning ca…
Investigating the Gestalt Principle of Closure in Deep Convolutional Neural Networks
Yuyan Zhang, Derya Soydaner, Fatemeh Behrad +2
Deep neural networks perform well in object recognition, but do they perceive objects like humans? This study investigates the Gestalt principle of closure in convolutional neural…