most citedCultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries

2 citations · 2 across the 1 of their papers we have counts for

collaborators

1 paper

cs.AI2025★ 2 cited

CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries

Shudong Liu, Yiqiao Jin, Cheng Li +6

Vision-language models (VLMs) have advanced human-AI interaction but struggle with cultural understanding, often misinterpreting symbols, gestures, and artifacts due to biases in p…