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

Large language models have demonstrated robust performance on variouslanguage tasks using zero-shot or few-shot learning paradigms. While beingactively researched, multimodal models that can additionally handle images asinput have yet to catch up in size and generality with language-only models. Inthis work, we ask whether language-only models can be utilised for tasks thatrequire visual input -- but also, as we argue, often require a strong reasoningcomponent. Similar to some recent related work, we make visual informationaccessible to the language model using separate verbalisation models.Specifically, we investigate the performance of open-source, open-accesslanguage models against GPT-3 on five vision-language tasks when giventextually-encoded visual information. Our results suggest that language modelsare effective for solving vision-language tasks even with limited samples. Thisapproach also enhances the interpretability of a model's output by providing ameans of tracing the output back through the verbalised image content.

Images in Language Space: Exploring the Suitability of Large Language Models for Vision & Language Tasks