Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting

Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting

6 October 2025

ArXiv (abs)PDF HTML

Papers citing "Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting"

0 / 0 papers shown

Title
No papers found