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/

Zendy Plus

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

Zendy Tools

Zendy Open

Natural language image-caption datasets, widely used for training LargeMultimodal Models, mainly focus on natural scenarios and overlook the intricatedetails of mathematical figures that are critical for problem-solving,hindering the advancement of current LMMs in multimodal mathematical reasoning.To this end, we propose leveraging code as supervision for cross-modalalignment, since code inherently encodes all information needed to generatecorresponding figures, establishing a precise connection between the twomodalities. Specifically, we co-develop our image-to-code model and datasetwith model-in-the-loop approach, resulting in an image-to-code model,FigCodifier and ImgCode-8.6M dataset, the largest image-code dataset to date.Furthermore, we utilize FigCodifier to synthesize novel mathematical figuresand then construct MM-MathInstruct-3M, a high-quality multimodal mathinstruction fine-tuning dataset. Finally, we present MathCoder-VL, trained withImgCode-8.6M for cross-modal alignment and subsequently fine-tuned onMM-MathInstruct-3M for multimodal math problem solving. Our model achieves anew open-source SOTA across all six metrics. Notably, it surpasses GPT-4o andClaude 3.5 Sonnet in the geometry problem-solving subset of MathVista,achieving improvements of 8.9% and 9.2%. The dataset and models will bereleased at https://github.com/mathllm/MathCoder.

MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning