Do Multimodal Large Language Models Truly See What We Point At? Investigating Indexical, Iconic, and Symbolic Gesture Comprehension

Noriki Nishida | Koji Inoue | Hideki Nakayama | Mayumi Bono | Katsuya Takanashi |

Paper Details:

Month: July
Year: 2025
Location: Vienna, Austria
Venue: ACL |

Citations

URL

No Citations Yet

Field Of Study