Lun Yiu Nie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Lun Yiu Nie has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Chao Zhang
Cornell University, Ithaca, New York, USA
2 shared publications - Cuiyun Gao
The Chinese University of Hong Kong, Hong Kong, China
1 shared publication - Jeffrey M. Rzeszotarski
Department of Computer Science, Loyola University Maryland, Baltimore, Maryland, USA
1 shared publication - Jichuan Zeng
The Chinese University of Hong Kong
1 shared publication - Michael R. Lyu
The Chinese University of Hong Kong
1 shared publication - Qi Xin
Tsinghua University, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
From Words to Widgets for Controllable LLM Generation
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Open AccessFrom Words to Widgets for Controllable LLM Generation
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-19
BrickSmart: Leveraging Generative AI to Support Children's Spatial Language Learning in Family Block Play
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Open AccessBrickSmart: Leveraging Generative AI to Support Children's Spatial Language Learning in Family Block Play
- Top Cited PapersOpen Access
- 31 January 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 32 (1) , 1-32
Code Structure–Guided Transformer for Source Code Summarization
Code summaries help developers comprehend programs and reduce their time to infer the program functionalities during software maintenance. Recent efforts resort to deep learning techniques such as sequence-to-sequence models for generating accurate code summaries, among which Transformer-based approaches have achieved promising performance. However, effectively integrating the code structure information into the Transformer is under-explored in this task domain. In this article, we propose a novel approach named SG-Trans to incorporate code structural properties into Transformer. Specifically, we inject the local symbolic information (e.g., code tokens and statements) and global syntactic structure (e.g., dataflow graph) into the self-attention module of Transformer as inductive bias. To further capture the hierarchical characteristics of code, the local information and global structure are designed to distribute in the attention heads of lower layers and high layers of Transformer. Extensive evaluation shows the superior performance of SG-Trans over the state-of-the-art approaches. Compared with the best-performing baseline, SG-Trans still improves 1.4% and 2.0% on two benchmark datasets, respectively, in terms of METEOR score, a metric widely used for measuring generation quality.
- 31 January 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 32 (1) , 1-32
Top Cited PapersOpen AccessCode Structure–Guided Transformer for Source Code Summarization
Code summaries help developers comprehend programs and reduce their time to infer the program functionalities during software maintenance. Recent efforts resort to deep learning techniques such as sequence-to-sequence models for generating accurate code summaries, among which Transformer-based approaches have achieved promising performance. However, effectively integrating the code structure information into the Transformer is under-explored in this task domain. In this article, we propose a novel approach named SG-Trans to incorporate code structural properties into Transformer. Specifically, we inject the local symbolic information (e.g., code tokens and statements) and global syntactic structure (e.g., dataflow graph) into the self-attention module of Transformer as inductive bias. To further capture the hierarchical characteristics of code, the local information and global structure are designed to distribute in the attention heads of lower layers and high layers of Transformer. Extensive evaluation shows the superior performance of SG-Trans over the state-of-the-art approaches. Compared with the best-performing baseline, SG-Trans still improves 1.4% and 2.0% on two benchmark datasets, respectively, in terms of METEOR score, a metric widely used for measuring generation quality.