English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Vision-Language Models (VLMs) are trained on vast amounts of data captured byhumans emulating our understanding of the world. However, known as visualillusions, human's perception of reality isn't always faithful to the physicalworld. This raises a key question: do VLMs have the similar kind of illusionsas humans do, or do they faithfully learn to represent reality? To investigatethis question, we build a dataset containing five types of visual illusions andformulate four tasks to examine visual illusions in state-of-the-art VLMs. Ourfindings have shown that although the overall alignment is low, larger modelsare closer to human perception and more susceptible to visual illusions. Ourdataset and initial findings will promote a better understanding of visualillusions in humans and machines and provide a stepping stone for futurecomputational models that can better align humans and machines in perceivingand communicating about the shared visual world. The code and data areavailable at https://github.com/vl-illusion/dataset.

Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?