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

Recent advances such as LLaVA and Mini-GPT4 have successfully integratedvisual information into LLMs, yielding inspiring outcomes and giving rise to anew generation of multi-modal LLMs, or MLLMs. Nevertheless, these methodsstruggle with hallucinations and the mutual interference between tasks. Totackle these problems, we propose an efficient and accurate approach to adaptto downstream tasks by utilizing LLM as a bridge to connect multiple expertmodels, namely u-LLaVA. Firstly, we incorporate the modality alignment moduleand multi-task modules into LLM. Then, we reorganize or rebuild multi-typepublic datasets to enable efficient modality alignment and instructionfollowing. Finally, task-specific information is extracted from the trained LLMand provided to different modules for solving downstream tasks. The overallframework is simple, effective, and achieves state-of-the-art performanceacross multiple benchmarks. We also release our model, the generated data, andthe code base publicly available at https://github.com/OPPOMKLab/u-LLaVA.

u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model