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

Key to tasks that require reasoning about natural language in visual contextsis grounding words and phrases to image regions. However, observing thisgrounding in contemporary models is complex, even if it is generally expectedto take place if the task is addressed in a way that is conductive togeneralization. We propose a framework to jointly study task performance andphrase grounding, and propose three benchmarks to study the relation betweenthe two. Our results show that contemporary models demonstrate inconsistencybetween their ability to ground phrases and solve tasks. We show how this canbe addressed through brute-force training on ground phrasing annotations, andanalyze the dynamics it creates. Code and at available athttps://github.com/lil-lab/phrase_grounding.

A Joint Study of Phrase Grounding and Task Performance in Vision and Language Models