DesignBench: A Multi-framework Multi-task Benchmark for Front-end Code Generation
Code and dataset for the paper.
May 31, 2025
DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation
We introduce DesignBench, the first comprehensive multi-framework multi-task benchmark for front-end code generation, encompassing React, Vue, and Angular frameworks. Beyond traditional design generation, we pioneer design edit and repair tasks. Through extensive experiments across task complexity, framework compatibility, difficulty levels, contextual factors and in-depth code-level analysis, we reveal primary limitations in current MLLMs for framework-based development and elicit several actionable advice for researchers and developers.
May 30, 2025
How Large Language Model Empowers the Analysis of Online Public Engagement for Mega Infrastructure Projects: cases in Hong Kong
This study proposes an NPRM (Networking, Parsing, Retrieval, Mapping) approach to uncover the interactions related to online public engagement in MIPs by observing the distribution of user identities involved, identifying individuals with considerable influence, and evaluating the influencer-public interactions during various project events. Observations are used to guide project decision-makers to understand public opinion of mega projects on social networks.
Sep 25, 2024
Large Language Model-based data-driven framework for digital transformation in construction industry
This research proposes a data-driven framework paradigm, amalgamating 'Large Language Models (LLMs) + construction knowledge databases', modelled on a question-answering system. It leverages domain-specific knowledge to enhance the output produced by LLMs.
Jul 30, 2024