← Search

Leyla Isik

2 accepted papers

2025

Modeling dynamic social vision highlights gaps between deep learning and humans

ICLR 2025poster

Deep learning models trained on computer vision tasks are widely considered the most successful models of human vision to date. The majority of work that supports this idea evaluates how accurately these models predict behavior and brain responses to static images of objects and scenes. Real-world v…

Cited by 12SourcePDFScholar
2025

MuMA-ToM: Multi-modal Multi-Agent Theory of Mind

AAAI 2025technical

Understanding people's social interactions in complex real-world scenarios often relies on intricate mental reasoning. To truly understand how and why people interact with one another, we must infer the underlying mental states that give rise to the social interactions, i.e., Theory of Mind reasonin…