Skip to content
Live
Trending storyDeveloping

MC-Lens explores the consciousness mechanism of VLMs

1 reports1 outlets15 hours agoUpdate

The story so far

AI overview

Hugging Face introduced the Multimodal Concept Lens (MC-Lens) to explore the 'consciousness' mechanism of Visual Language Models (VLMs). By mapping the intermediate states of visual and language encoders to a shared semantic space, it reveals the accessibility and selective access mechanisms of concepts. Experiments show that the information of accessed concepts participates in downstream computation and reasoning, and it was found that there are differences in the development of cross-modal alignment and selective access.

AI-written from the reports · Updated 2 hours ago

Coverage timeline

Follow the coverage to see every side of the story.

20 Nov
  1. Hugging Face Daily Papers
    Probing the "Conscious" Mind: Selective Access and Global Workspace in Vision-Language Models

    Multimodal Concept Lens (MC-Lens) reveals the accessibility and selective access mechanisms of VLM concepts by mapping the intermediate states of visual and language encoders to a shared semantic space. Experiments show that the accessed conceptual information participates in downstream computation and reasoning, and it is found that there are differences in the development of cross-modal alignment and selective access.

Heat over time

Not enough data yet to draw a trend.