Summary of Web2code: a Large-scale Webpage-to-code Dataset and Evaluation Framework For Multimodal Llms, by Sukmin Yun and Haokun Lin and Rusiru Thushara and Mohammad Qazim Bhat and Yongxin Wang and Zutao Jiang and Mingkai Deng and Jinhong Wang and Tianhua Tao and Junbo Li and Haonan Li and Preslav Nakov and Timothy Baldwin and Zhengzhong Liu and Eric P. Xing and Xiaodan Liang and Zhiqiang Shen
Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
by Sukmin Yun, Haokun Lin, Rusiru Thushara, Mohammad Qazim Bhat, Yongxin Wang, Zutao Jiang, Mingkai Deng, Jinhong Wang, Tianhua Tao, Junbo Li, Haonan Li, Preslav Nakov, Timothy Baldwin, Zhengzhong Liu, Eric P. Xing, Xiaodan Liang, Zhiqiang Shen
First submitted to arxiv on: 28 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a new benchmark for multimodal large language models (MLLMs) called Web2Code, which aims to improve their ability to understand webpage screenshots and generate corresponding HTML code. The authors create a large-scale dataset of webpage-to-code pairs using pre-trained LLMs and leverage this data to evaluate the performance of MLLMs in webpage understanding and web-to-code generation tasks. The paper shows that the proposed Web2Code benchmark is beneficial not only for these specific tasks but also for general visual domain applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a new way to test how well computer programs can understand pictures of websites and turn them into the code that makes up those sites. They made a big collection of pictures and corresponding code, then used this data to see how good different computer models are at doing this task. The results show that their approach is useful not just for understanding website pictures but also for other tasks that involve recognizing what’s in images. |
