Yuxuan Wan

Yuxuan Wan

Auto-generated profile, based on publicly available information

Yuxuan Wan

Chinese University of Hong Kong, Hong Kong, Hong Kong

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 November 2023
Verified
Conference Paper
Open access
YWYuxuan Wan
Yuxuan Wan
WWWenxuan Wang
Wenxuan Wang
PHPinjia He
Pinjia He
JGJiazhen Gu
Jiazhen Gu
HBHaonan Bai
Haonan Bai
MLMichael R. Lyu
Michael R. Lyu
Powered by advanced Artificial Intelligence (AI) techniques, conversational AI systems, such as ChatGPT, and digital assistants like Siri, have been widely deployed in daily life. However, such systems may still produce content containing biases and stereotypes, causing potential social problems. Due to modern AI techniques’ data-driven, black-box nature, comprehensively identifying and measuring biases in conversational systems remains challenging. Particularly, it is hard to generate inputs that can comprehensively trigger potential bias due to the lack of data containing both social groups and biased properties. In addition, modern conversational systems can produce diverse responses (e.g., chatting and explanation), which makes existing bias detection methods based solely on sentiment and toxicity hardly being adopted. In this paper, we propose BiasAsker, an automated framework to identify and measure social bias in conversational AI systems. To obtain social groups and biased properties, we construct a comprehensive social bias dataset containing a total of 841 groups and 5,021 biased properties. Given the dataset, BiasAsker automatically generates questions and adopts a novel method based on existence measurement to identify two types of biases (i.e., absolute bias and related bias) in conversational systems. Extensive experiments on eight commercial systems and two famous research models, such as ChatGPT and GPT-3, show that 32.83% of the questions generated by BiasAsker can trigger biased behaviors in these widely deployed conversational systems. All the code, data, and experimental results have been released to facilitate future research.

19 June 2025 in Proceedings of the ACM on Software Engineering
Verified
Journal Article
Open access
YWYuxuan Wan
Yuxuan Wan
CWChaozheng Wang
Chaozheng Wang
YDYi Dong
Yi Dong
WWWenxuan Wang
Wenxuan Wang
SLShuqing Li
Shuqing Li
MLMichael Lyu
Michael Lyu
Websites are critical in today’s digital world, with over 1.11 billion currently active and approximately 252,000 new sites launched daily. Converting website layout design into functional UI code is a time-consuming yet indispensable step of website development. Manual methods of converting visual designs into functional code present significant challenges, especially for non-experts. To explore automatic design-to-code solutions, we first conduct a motivating study on GPT-4o and identify three types of issues in generating UI code: element omission, element distortion, and element misarrangement. We further reveal that a focus on smaller visual segments can help multimodal large language models (MLLMs) mitigate these failures in the generation process. In this paper, we propose DCGen, a divide-and-conquer-based approach to automate the translation of webpage design to UI code. DCGen starts by dividing screenshots into manageable segments, generating code for each segment, and then reassembling them into complete UI code for the entire screenshot. We conduct extensive testing with a dataset comprised of real-world websites and various MLLMs and demonstrate that DCGen achieves up to a 15% improvement in visual similarity and 8% in code similarity for large input images. Human evaluations show that DCGen can help developers implement webpages significantly faster and more similar to the UI designs. To the best of our knowledge, DCGen is the first segment-aware MLLM-based approach for generating UI code directly from screenshots.

28 October 2024
Verified
Conference Paper
Open access
WWWenxuan Wang
Wenxuan Wang
HBHaonan Bai
Haonan Bai
JHJen-Tse Huang
Jen-Tse Huang
YWYuxuan Wan
Yuxuan Wan
YYYouliang Yuan
Youliang Yuan
MLMichael Lyu
Michael Lyu


30 June 2026 in Proceedings of the ACM on Software Engineering
Verified
Journal Article
Open access
JXJingyu Xiao
Jingyu Xiao
ZZZhongyi Zhang
Zhongyi Zhang
YWYuxuan Wan
Yuxuan Wan
YHYintong Huo
Yintong Huo
YLYang Liu
Yang Liu
MLMichael R. Lyu
Michael R. Lyu
Multimodal Large Language Models (MLLMs) have demonstrated exceptional performance in UI2Code tasks (i.e., generating code from UI mockups), significantly enhancing website development efficiency. However, UI2Code tasks incur substantially higher computational overhead compared to traditional code generation tasks. This overhead is primarily driven by the large number of input image tokens required to represent complex visual designs and the extensive volume of output code tokens needed to describe complete webpage structures. In this paper, we conduct a comprehensive preliminary study on popular MLLMs for UI2Code tasks, identifying significant redundancies in both image and code tokens. We observe that these redundancies not only exacerbate computational complexity but also hinder the model’s ability to focus on key UI elements, leading to excessively lengthy and often invalid HTML files. To address these challenges, we propose EfficientUICoder, a bidirectional compression framework designed for efficient UI code generation. First, we introduce an Element and Layout-aware Token Compression method, which preserves essential UI element and layout information by detecting element regions and constructing a UI element tree for efficient representation. Second, we design a Region-aware Token Refinement strategy that refines selected tokens by leveraging attention scores to evaluate semantic importance, discarding low-attention tokens from selected regions while integrating high-attention tokens from unselected regions. Third, we develop an Adaptive Duplicate Token Suppression mechanism, which dynamically modulates token probabilities during decoding by tracking HTML/CSS code structure frequencies and applying exponential penalty strategies to minimize repetitive generation. Extensive experiments demonstrate that EfficientUICoder achieves a 55%-60% compression ratio without compromising the quality of the generated webpages, effectively reducing output code redundancy. In terms of efficiency, EfficientUICoder achieves superior improvements, reducing computational cost by up to 44.9%, generated tokens by up to 41.4%, prefill time by up to 46.6%, and inference time by up to 48.8% on 34B-level MLLMs. Code is available at https://github.com/WebPAI/EfficientUICoder.

5 July 2026
Verified
Conference Paper
Open access
RYRunxin Yang
Runxin Yang
YWYuxuan Wan
Yuxuan Wan
SLShuqing Li
Shuqing Li
MLMichael R. Lyu
Michael R. Lyu