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

Instruction tuning has significantly advanced large language models (LLMs)such as ChatGPT, enabling them to align with human instructions across diversetasks. However, progress in open vision-language models (VLMs) has been limiteddue to the scarcity of high-quality instruction datasets. To tackle thischallenge and promote research in the vision-language field, we introduce theMulti-Modal, Multilingual Instruction Tuning (M$^3$IT) dataset, designed tooptimize VLM alignment with human instructions. Our M$^3$IT dataset comprises40 carefully curated datasets, including 2.4 million instances and 400 manuallywritten task instructions, reformatted into a vision-to-text structure. Keytasks are translated into 80 languages with an advanced translation system,ensuring broader accessibility. M$^3$IT surpasses previous datasets regardingtask coverage, instruction number and instance scale. Moreover, we developYing-VLM, a VLM model trained on our M$^3$IT dataset, showcasing its potentialto answer complex questions requiring world knowledge, generalize to unseenvideo tasks, and comprehend unseen instructions in Chinese. We haveopen-sourced the dataset to encourage further research.

M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning