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

The increasing demand for intelligent systems capable of interpreting andreasoning about visual content requires the development of Large Multi-ModalModels (LMMs) that are not only accurate but also have explicit reasoningcapabilities. This paper presents a novel approach to imbue an LMM with theability to conduct explicit reasoning based on visual content and textualinstructions. We introduce a system that can ask a question to acquirenecessary knowledge, thereby enhancing the robustness and explicability of thereasoning process. Our method comprises the development of a novel datasetgenerated by a Large Language Model (LLM), designed to promote chain-of-thoughtreasoning combined with a question-asking mechanism. We designed an LMM, whichhas high capabilities on region awareness to address the intricate requirementsof image-text alignment. The model undergoes a three-stage training phase,starting with large-scale image-text alignment using a large-scale datasets,followed by instruction tuning, and fine-tuning with a focus onchain-of-thought reasoning. The results demonstrate a stride toward a morerobust, accurate, and interpretable LMM, capable of reasoning explicitly andseeking information proactively when confronted with ambiguous visual input.

Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generation