Skip to content
#

cka

Here are 210 public repositories matching this topic...

This research project investigates whether Vision-Language Models (VLMs) like CLIP/BLIP truly "understand" compositions or simply memorize patterns. It features a sophisticated diagnostic suite—including CKA, Concept Probing, and Negation Consistency—to quantify generalization gaps and visualize model attention via Grad-CAM.

  • Updated Mar 31, 2026
  • Python

Improve this page

Add a description, image, and links to the cka topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the cka topic, visit your repo's landing page and select "manage topics."

Learn more