From Static Images to Dynamic Interactions: Generative AI Exhibits Robust Social-Cognitive Capabilities across Modalities and Cultural Boundaries

Posters

Keyword: Digital Media

Abstract: We systematically evaluated the social-cognitive capabilities of state-of-the-art Generative AI models using a suite of textual, static image, and dynamic video assessments. Across all modalities, advanced models consistently met or exceeded average human performance, demonstrating robust, cross-ethnic abilities, suggesting their potential as objective clinical assessment tools.

• Elad Refoua (Presenting Author)
• Dorit Hadar-Shoval (Author)
• Gunther Meinlschmidt (Author)
• David Piterman (Author)
• Alon Geller (Author)
• Iftach Tsafrir (Author)
• Kfir Asraf (Author)
• Maya Lvovsky (Author)
• Yoav Shimoni (Author)
• Renata Wacker (Author)
• Isabel Dziobek (Author)
• Inbar Feinstein (Author)
• Zohar Elyoseph (Author)