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 (LLMs) have showcased impressive capabilities inhandling straightforward programming tasks. However, their performance tends tofalter when confronted with more challenging programming problems. We observethat conventional models often generate solutions as monolithic code blocks,restricting their effectiveness in tackling intricate questions. To overcomethis limitation, we present Modular-of-Thought Coder (MoTCoder). We introduce apioneering framework for MoT instruction tuning, designed to promote thedecomposition of tasks into logical sub-tasks and sub-modules. Ourinvestigations reveal that, through the cultivation and utilization ofsub-modules, MoTCoder significantly improves both the modularity andcorrectness of the generated solutions, leading to substantial relative pass@1improvements of 12.9% on APPS and 9.43% on CodeContests. Our codes areavailable at https://github.com/dvlab-research/MoTCoder.

MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks