TCSE logo 
 Sigsoft logo
Sustainability badge

Software developers frequently use code completion tools to accelerate software development by suggesting the following code elements. Researchers usually employ AutoRegressive (AR) decoders to complete code sequences in a left-to-right, token-by-token fashion. To improve the accuracy and efficiency of code completion, we argue that tokens within a code statement have the potential to be predicted concurrently. In this article, we first conduct an empirical study to analyze the dependency among the target tokens in line-level code completion. The results suggest that it is potentially practical to generate all statement tokens in parallel. To this end, we introduce SANAR, a simple and effective syntax-aware non-autoregressive model for line-level code completion. To further improve the quality of the generated code, we propose an adaptive and syntax-aware sampling strategy to boost the model’s performance. The experimental results obtained from two widely used datasets indicate that our model outperforms state-of-the-art code completion approaches of similar model size by a considerable margin, and is faster than these models with up to 9_ speed-up. Moreover, the extensive results additionally demonstrate that the enhancements achieved by SANAR become even more pronounced with larger model sizes, highlighting their significance.

Wed 30 Apr

Displayed time zone: Eastern Time (US & Canada) change

15:30 - 16:00
15:30
30m
Poster
Non-Autoregressive Line-Level Code Completion
Journal-first Papers
Fang Liu Beihang University, Zhiyi Fu Peking University, Ge Li Peking University, Zhi Jin Peking University, Hui Liu Beijing Institute of Technology, Yiyang Hao Silicon Heart Tech Co., Li Zhang Beihang University
15:30
30m
Poster
FlatD: Protecting Deep Neural Network Program from Reversing Attacks
SE In Practice (SEIP)
Jinquan Zhang The Pennsylvania State University, Zihao Wang Penn State University, Pei Wang Independent Researcher, Rui Zhong Palo Alto Networks, Dinghao Wu Pennsylvania State University
15:30
30m
Talk
Building Domain-Specific Machine Learning Workflows: A Conceptual Framework for the State-of-the-PracticeSE for AI
Journal-first Papers
Bentley Oakes Polytechnique Montréal, Michalis Famelis Université de Montréal, Houari Sahraoui DIRO, Université de Montréal
DOI Pre-print File Attached
15:30
30m
Poster
Predicting the First Response Latency of Maintainers and Contributors in Pull Requests
Journal-first Papers
SayedHassan Khatoonabadi Concordia University, Montreal, Ahmad Abdellatif University of Calgary, Diego Elias Costa Concordia University, Canada, Emad Shihab Concordia University, Montreal
15:30
30m
Talk
LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation
Journal-first Papers
Sarah Fakhoury Microsoft Research, Aaditya Naik University of Pennsylvania, Georgios Sakkas University of California at San Diego, Saikat Chakraborty Microsoft Research, Shuvendu K. Lahiri Microsoft Research
Link to publication
15:30
30m
Poster
RustAssistant: Using LLMs to Fix Compilation Errors in Rust Code
Research Track
Pantazis Deligiannis Microsoft Research, Akash Lal Microsoft Research, Nikita Mehrotra Microsoft Research, Rishi Poddar Microsoft Research, Aseem Rastogi Microsoft Research
15:30
30m
Talk
QuanTest: Entanglement-Guided Testing of Quantum Neural Network SystemsQuantum
Journal-first Papers
Jinjing Shi Central South University, Zimeng Xiao Central South University, Heyuan Shi Central South University, Yu Jiang Tsinghua University, Xuelong LI China Telecom
Link to publication

Thu 1 May

Displayed time zone: Eastern Time (US & Canada) change

13:30 - 14:00
13:30
30m
Poster
Non-Autoregressive Line-Level Code Completion
Journal-first Papers
Fang Liu Beihang University, Zhiyi Fu Peking University, Ge Li Peking University, Zhi Jin Peking University, Hui Liu Beijing Institute of Technology, Yiyang Hao Silicon Heart Tech Co., Li Zhang Beihang University
13:30
30m
Talk
LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation
Journal-first Papers
Sarah Fakhoury Microsoft Research, Aaditya Naik University of Pennsylvania, Georgios Sakkas University of California at San Diego, Saikat Chakraborty Microsoft Research, Shuvendu K. Lahiri Microsoft Research
Link to publication
13:30
30m
Talk
SusDevOps: Promoting Sustainability to a First Principle in Software Delivery
New Ideas and Emerging Results (NIER)
Istvan David McMaster University / McMaster Centre for Software Certification (McSCert)
13:30
30m
Poster
Predicting the First Response Latency of Maintainers and Contributors in Pull Requests
Journal-first Papers
SayedHassan Khatoonabadi Concordia University, Montreal, Ahmad Abdellatif University of Calgary, Diego Elias Costa Concordia University, Canada, Emad Shihab Concordia University, Montreal
13:30
30m
Poster
RustAssistant: Using LLMs to Fix Compilation Errors in Rust Code
Research Track
Pantazis Deligiannis Microsoft Research, Akash Lal Microsoft Research, Nikita Mehrotra Microsoft Research, Rishi Poddar Microsoft Research, Aseem Rastogi Microsoft Research
13:30
30m
Talk
Relevant information in TDD experiment reporting
Journal-first Papers
Fernando Uyaguari Instituto Superior Tecnológico Wissen, Silvia Teresita Acuña Castillo Universidad Autónoma de Madrid, John W. Castro Universidad de Atacama, Davide Fucci Blekinge Institute of Technology, Oscar Dieste Universidad Politécnica de Madrid, Sira Vegas Universidad Politecnica de Madrid
:
:
:
: