Human and generative AI integrate visual cues differently in a shape completion task
Jonathan Adams, Luca Serriere, Maximilian Jonathan Kothen, Maria Barbara Smorczewska, Filipp Schmidt, Yaniv Morgenstern
This paper compares how humans and generative AI models integrate visual cues in shape completion tasks, finding that humans use both low- and high-level cues while AI models rely primarily on low-level pattern continuation.
bioRxiv · Dec 22, 2025 · PreprintNeuroscience