Top Researchers in LM4SE

Table of contents

1. Researchers
   1. Hongyu Zhang
   2. David Lo
   3. Xin Xia
   4. Yang Liu
   5. Zhenchang Xing
   6. Gabriele Bavota
   7. Tien Nhut Nguyen
   8. Yi Li
   9. Qing Wang
   10. Chetan Arora
   11. Lionel Briand
   12. Lin Shi
   13. Xiaofei Xie
   14. Ge Li
   15. Zhi Jin
   16. Lingming Zhang
   17. Mehrdad Sabetzadeh
   18. Michael R. Lyu
   19. Neel Sundaresan
   20. Bowen Xu
   21. Lin Tan
   22. Denys Poshyvanyk
   23. Xiaodong Gu
   24. Toufique Ahmed
   25. Cuiyun Gao
   26. Pinjia He
   27. Collin McMillan
   28. Chunyang Chen
   29. Michele Tufano
   30. Beijun Shen
   31. Xing Hu
   32. Haoyu Wang
   33. Prem Devanbu
   34. Shing-Chi Cheung
   35. Chunqiu Steven Xia
   36. Antonio Mastropaolo
   37. Chaozheng Wang
   38. Zeyu Sun
   39. Sallam Abualhaija
   40. Xu Wang
   41. Hailong Sun
   42. Xudong Liu
   43. Luca Pascarella
   44. Vincent Hellendoorn
   45. Yao Wan
   46. Guandong Xu
   47. Tegawendé F. Bissyandé
   48. Shaohua Wang
   49. Jianjun Zhao
   50. Songqiang Chen
   51. Xiaoyuan Xie
   52. Shangqing Liu
   53. Jia Li
   54. Jidong Ge
   55. Pengyu Nie
   56. Junyi Jessy Li
   57. Miloš Gligorić
   58. Shangwen Wang
   59. Junjie Chen
   60. Qihao Zhu
   61. Xiwei Xu
   62. Anh Tuan Nguyen
   63. Xin Peng
   64. Yiling Lou
   65. Simone Scalabrino
   66. Rocco Oliveto
   67. Wenxuan Wang
   68. Kevin Moran
   69. Jian Zhang
   70. Ming Wen
   71. Zhendong Su
   72. Premkumar T. Devanbu
   73. Miltiadis Allamanis
   74. Charles Sutton
   75. Yepang Liu
   76. Dongmei Zhang
   77. Lu Zhang
   78. Sumit Gulwani
   79. Junjie Wang
   80. Lingxiao Jiang
   81. Saad Ezzini
   82. Mark Harman
   83. Thibaud Lutellier
   84. Yanlin Wang

This page tracks the top researchers in language models for software engineering (LM4SE) over the past decade based on their publication record at top SE conferences. We analyzed all papers from ICSE, ASE, FSE, and ISSTA since 2012 to compile a list of prolific authors advancing the state-of-the-art in LM4SE.

Researchers

Hongyu Zhang

• Log-based Anomaly Detection Without Log Parsing, ASE 2021
• Log Parsing: How Far Can ChatGPT Go?, ASE 2023
• Deep API learning, FSE 2016
• Predicting Node failure in cloud service systems, FSE 2018
• Robust log-based anomaly detection on unstable log data, FSE 2019
• No more fine-tuning? an experimental evaluation of prompt tuning in code intelligence, FSE 2022
• Diet code is healthy: simplifying programs for pre-trained models of code, FSE 2022
• You see what I want you to see: poisoning vulnerabilities in neural code search, FSE 2022
• A Novel Neural Source Code Representation Based on Abstract Syntax Tree, ICSE 2019
• Retrieval-based Neural Source Code Summarization, ICSE 2020
• Cross-Domain Deep Code Search with Meta Learning, ICSE 2022
• Improving Fault Localization and Program Repair with Deep Semantic Features and Transferred Knowledge, ICSE 2022
• On the Evaluation of Neural Code Summarization, ICSE 2021
• What Do They Capture? - A Structural Analysis of Pre-Trained Language Models for Source Code, ICSE 2022
• Where is Your App Frustrating Users?, ICSE 2022
• Keeping Pace with Ever-Increasing Data: Towards Continual Learning of Code Intelligence Models, ICSE 2023
• Template-based Neural Program Repair, ICSE 2023
• CoCoSoDa: Effective Contrastive Learning for Code Search, ICSE 2022
• Towards Efficient Fine-Tuning of Pre-trained Code Models: An Experimental Study and Beyond, ISSTA 2023
• Detecting Condition-Related Bugs with Control Flow Graph Neural Network, ISSTA 2023

David Lo

• Answer Summarization for Technical Queries: Benchmark and New Approach, ASE 2022
• Compressing Pre-trained Models of Code into 3 MB, ASE 2022
• Are We Ready to Embrace Generative AI for Software Q&A?, ASE 2023
• AutoPruner: transformer-based call graph pruning, FSE 2022
• How to better utilize code graphs in semantic code search?, FSE 2022
• iTiger: an automatic issue title generation tool, FSE 2022
• On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code, FSE 2023
• Natural Attack for Pre-trained Models of Code, ICSE 2022
• CoLeFunDa: Explainable Silent Vulnerability Fix Identification, ICSE 2023
• Neural-Machine-Translation-Based Commit Message Generation: How Far Are We?, ASE 2018
• Assessing the Generalizability of Code2vec Token Embeddings, ASE 2019
• Automating User Notice Generation for Smart Contract Functions, ASE 2021
• Finding A Needle in a Haystack: Automated Mining of Silent Vulnerability Fixes, ASE 2021
• The Devil is in the Tails: How Long-Tailed Code Distributions Impact Large Language Models, ASE 2023
• DSM: a specification mining tool using recurrent neural network based language model, FSE 2018
• RecipeGen++: an automated trigger action programs generator, FSE 2022
• Deep specification mining, ISSTA 2018

Xin Xia

• Predicting semantically linkable knowledge in developer online forums via convolutional neural network, ASE 2016
• Neural-Machine-Translation-Based Commit Message Generation: How Far Are We?, ASE 2018
• Automating User Notice Generation for Smart Contract Functions, ASE 2021
• EditSum: A Retrieve-and-Edit Framework for Source Code Summarization, ASE 2021
• Finding A Needle in a Haystack: Automated Mining of Silent Vulnerability Fixes, ASE 2021
• Is this Change the Answer to that Problem?: Correlating Descriptions of Bug and Code Changes for Evaluating Patch Correctness, ASE 2022
• Neural SZZ Algorithm, ASE 2023
• Identify and Update Test Cases When Production Code Changes: A Transformer-Based Approach, ASE 2023
• Are we building on the rock? on the importance of data preprocessing for code summarization, FSE 2022
• How to better utilize code graphs in semantic code search?, FSE 2022
• CCT5: A Code-Change-Oriented Pre-trained Model, FSE 2023
• RepresentThemAll: A Universal Learning Representation of Bug Reports, ICSE 2023
• CoLeFunDa: Explainable Silent Vulnerability Fix Identification, ICSE 2023

Yang Liu

• FiB: Squeezing loop invariants by interpolation between forward/backward predicate transformers, ASE 2017
• Tell Them Apart: Distilling Technology Differences from Crowd-Scale Comparison Discussions, ASE 2018
• A Quantitative Analysis Framework for Recurrent Neural Network, ASE 2019
• DeepMutation++: A Mutation Testing Framework for Deep Learning Systems, ASE 2019
• Marble: Model-based Robustness Analysis of Stateful Deep Learning Systems, ASE 2020
• TransRepair: Context-aware Program Repair for Compilation Errors, ASE 2022
• An Empirical Study on Fine-Tuning Large Language Models of Code for Automated Program Repair, ASE 2023
• Generating query-specific class API summaries, FSE 2019
• DeepStellar: model-based quantitative analysis of stateful deep learning systems, FSE 2019
• ReCDroid: Automatically Reproducing Android Application Crashes from Bug Reports, ICSE 2019
• ContraBERT: Enhancing Code Pre-trained Models via Contrastive Learning, ICSE 2023
• Retracted on March 14, 2023: Cross-lingual transfer learning for statistical type inference, ISSTA 2021
• Detecting Condition-Related Bugs with Control Flow Graph Neural Network, ISSTA 2023

Zhenchang Xing

• Predicting semantically linkable knowledge in developer online forums via convolutional neural network, ASE 2016
• Tell Them Apart: Distilling Technology Differences from Crowd-Scale Comparison Discussions, ASE 2018
• Neural-Machine-Translation-Based Commit Message Generation: How Far Are We?, ASE 2018
• PRCBERT: Prompt Learning for Requirement Classification using BERT-based Pretrained Language Models, ASE 2022
• Prompt-tuned Code Language Model as a Neural Knowledge Base for Type Inference in Statically-Typed Partial Code, ASE 2022
• Let’s Chat to Find the APIs: Connecting Human, LLM and Knowledge Graph through AI Chain, ASE 2023
• From Misuse to Mastery: Enhancing Code Generation with Knowledge-Driven AI Chaining, ASE 2023
• Generating query-specific class API summaries, FSE 2019
• Object detection for graphical user interface: old fashioned or deep learning or a combination?, FSE 2020
• Unsupervised Software-Specific Morphological Forms Inference from Informal Discussions, ICSE 2017
• Silent Vulnerable Dependency Alert Prediction with Vulnerability Key Aspect Explanation, ICSE 2023

Gabriele Bavota

• An Empirical Investigation into Learning Bug-Fixing Patches in the Wild via Neural Machine Translation, ASE 2018
• Towards Automatically Addressing Self-Admitted Technical Debt: How Far Are We?, ASE 2023
• On Learning Meaningful Code Changes Via Neural Machine Translation, ICSE 2019
• On Learning Meaningful Assert Statements for Unit Test Cases, ICSE 2020
• Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks, ICSE 2021
• Evaluating SZZ Implementations Through a Developer-Informed Oracle, ICSE 2021
• Using Deep Learning to Generate Complete Log Statements, ICSE 2022
• Using Pre-Trained Models to Boost Code Review Automation, ICSE 2022
• On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot, ICSE 2023
• Automating Code-Related Tasks Through Transformers: The Impact of Pre-training, ICSE 2023

Tien Nhut Nguyen

• Combining Program Analysis and Statistical Language Model for Code Statement Completion, ASE 2019
• Next Syntactic-Unit Code Completion and Applications, ASE 2022
• A statistical semantic language model for source code, FSE 2013
• Lexical statistical machine translation for language migration, FSE 2013
• T2API: synthesizing API code usage templates from English texts with statistical translation, FSE 2016
• DLFix: Context-based Code Transformation Learning for Automated Program Repair, ICSE 2020
• A Context-Based Automated Approach for Method Name Consistency Checking and Suggestion, ICSE 2021
• DEAR: A Novel Deep Learning-based Approach for Automated Program Repair, ICSE 2022

Yi Li

• Combining Program Analysis and Statistical Language Model for Code Statement Completion, ASE 2019
• A Quantitative Analysis Framework for Recurrent Neural Network, ASE 2019
• Marble: Model-based Robustness Analysis of Stateful Deep Learning Systems, ASE 2020
• DeepStellar: model-based quantitative analysis of stateful deep learning systems, FSE 2019
• A Vision on Intentions in Software Engineering, FSE 2023
• DLFix: Context-based Code Transformation Learning for Automated Program Repair, ICSE 2020
• A Context-Based Automated Approach for Method Name Consistency Checking and Suggestion, ICSE 2021
• DEAR: A Novel Deep Learning-based Approach for Automated Program Repair, ICSE 2022
• Retracted on March 14, 2023: Cross-lingual transfer learning for statistical type inference, ISSTA 2021

Qing Wang

• Understanding feature requests by leveraging fuzzy method and linguistic analysis, ASE 2017
• ISPY: Automatic Issue-Solution Pair Extraction from Community Live Chats, ASE 2021
• SCPatcher: Mining Crowd Security Discussions to Enrich Secure Coding Practices, ASE 2023
• Learning to extract transaction function from requirements: an industrial case on financial software, FSE 2020
• Are we building on the rock? on the importance of data preprocessing for code summarization, FSE 2022
• Detection of Hidden Feature Requests from Massive Chat Messages via Deep Siamese Network, ICSE 2020
• Where is Your App Frustrating Users?, ICSE 2022
• Fill in the Blank: Context-aware Automated Text Input Generation for Mobile GUI Testing, ICSE 2022

Chetan Arora

• RUBRIC: a flexible tool for automated checking of conformance to requirement boilerplates, FSE 2013
• NARCIA: an automated tool for change impact analysis in natural language requirements, FSE 2015
• Automated change impact analysis between SysML models of requirements and design, FSE 2016
• TAPHSIR: towards AnaPHoric ambiguity detection and ReSolution in requirements, FSE 2022
• COREQQA - A COmpliance REQuirements Understanding using Question Answering Tool, FSE 2022
• Using Domain-Specific Corpora for Improved Handling of Ambiguity in Requirements, ICSE 2021
• Automated Handling of Anaphoric Ambiguity in Requirements: A Multi-solution Study, ICSE 2022
• AI-based Question Answering Assistance for Analyzing Natural-language Requirements, ICSE 2023

Lionel Briand

• RUBRIC: a flexible tool for automated checking of conformance to requirement boilerplates, FSE 2013
• UMTG: a toolset to automatically generate system test cases from use case specifications, FSE 2015
• NARCIA: an automated tool for change impact analysis in natural language requirements, FSE 2015
• Automated change impact analysis between SysML models of requirements and design, FSE 2016
• COREQQA - A COmpliance REQuirements Understanding using Question Answering Tool, FSE 2022
• Automated Test Suite Generation for Time-Continuous Simulink Models, ICSE 2016
• Using Domain-Specific Corpora for Improved Handling of Ambiguity in Requirements, ICSE 2021
• Automatic generation of system test cases from use case specifications, ISSTA 2015

Lin Shi

• Understanding feature requests by leveraging fuzzy method and linguistic analysis, ASE 2017
• ISPY: Automatic Issue-Solution Pair Extraction from Community Live Chats, ASE 2021
• SCPatcher: Mining Crowd Security Discussions to Enrich Secure Coding Practices, ASE 2023
• Learning to extract transaction function from requirements: an industrial case on financial software, FSE 2020
• Are we building on the rock? on the importance of data preprocessing for code summarization, FSE 2022
• Detection of Hidden Feature Requests from Massive Chat Messages via Deep Siamese Network, ICSE 2020
• Where is Your App Frustrating Users?, ICSE 2022

Xiaofei Xie

• A Quantitative Analysis Framework for Recurrent Neural Network, ASE 2019
• DeepMutation++: A Mutation Testing Framework for Deep Learning Systems, ASE 2019
• Marble: Model-based Robustness Analysis of Stateful Deep Learning Systems, ASE 2020
• TransRepair: Context-aware Program Repair for Compilation Errors, ASE 2022
• DeepStellar: model-based quantitative analysis of stateful deep learning systems, FSE 2019
• ContraBERT: Enhancing Code Pre-trained Models via Contrastive Learning, ICSE 2023
• Retracted on March 14, 2023: Cross-lingual transfer learning for statistical type inference, ISSTA 2021

Ge Li

• Multi-task Learning based Pre-trained Language Model for Code Completion, ASE 2020
• EditSum: A Retrieve-and-Edit Framework for Source Code Summarization, ASE 2021
• ZC3: Zero-Shot Cross-Language Code Clone Detection, ASE 2023
• Incorporating domain knowledge through task augmentation for front-end JavaScript code generation, FSE 2022
• Learning to Recommend Method Names with Global Context, ICSE 2022
• SkCoder: A Sketch-based Approach for Automatic Code Generation, ICSE 2023
• CODEP: Grammatical Seq2Seq Model for General-Purpose Code Generation, ISSTA 2023

Zhi Jin

• Multi-task Learning based Pre-trained Language Model for Code Completion, ASE 2020
• EditSum: A Retrieve-and-Edit Framework for Source Code Summarization, ASE 2021
• ZC3: Zero-Shot Cross-Language Code Clone Detection, ASE 2023
• Multi-perspective representation learning for source code analytics (invited tutorial), FSE 2022
• Learning to Recommend Method Names with Global Context, ICSE 2022
• SkCoder: A Sketch-based Approach for Automatic Code Generation, ICSE 2023
• CODEP: Grammatical Seq2Seq Model for General-Purpose Code Generation, ISSTA 2023

Lingming Zhang

• Learning to Construct Better Mutation Faults, ASE 2022
• The Plastic Surgery Hypothesis in the Era of Large Language Models, ASE 2023
• Less training, more repairing please: revisiting automated program repair via zero-shot learning, FSE 2022
• Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair, FSE 2023
• Automated Program Repair in the Era of Large Pre-trained Language Models, ICSE 2023
• An extensive study on pre-trained models for program understanding and generation, ISSTA 2022
• Large Language Models Are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models, ISSTA 2022

Mehrdad Sabetzadeh

• RUBRIC: a flexible tool for automated checking of conformance to requirement boilerplates, FSE 2013
• NARCIA: an automated tool for change impact analysis in natural language requirements, FSE 2015
• Automated change impact analysis between SysML models of requirements and design, FSE 2016
• TAPHSIR: towards AnaPHoric ambiguity detection and ReSolution in requirements, FSE 2022
• Using Domain-Specific Corpora for Improved Handling of Ambiguity in Requirements, ICSE 2021
• Automated Handling of Anaphoric Ambiguity in Requirements: A Multi-solution Study, ICSE 2022
• AI-based Question Answering Assistance for Analyzing Natural-language Requirements, ICSE 2023

Michael R. Lyu

• What Makes Good In-Context Demonstrations for Code Intelligence Tasks with LLMs?, ASE 2023
• Generative Type Inference for Python, ASE 2023
• REEF: A Framework for Collecting Real-World Vulnerabilities and Fixes, ASE 2023
• No more fine-tuning? an experimental evaluation of prompt tuning in code intelligence, FSE 2022
• BiasAsker: Measuring the Bias in Conversational AI System, FSE 2023
• AEON: a method for automatic evaluation of NLP test cases, ISSTA 2022
• ARCLIN: Automated API Mention Resolution for Unformatted Texts, ICSE 2022

Neel Sundaresan

• IntelliCode compose: code generation using transformer, FSE 2020
• Program merge conflict resolution via neural transformers, FSE 2021
• DeepDev-PERF: a deep learning-based approach for improving software performance, FSE 2022
• Exploring and evaluating personalized models for code generation, FSE 2022
• InferFix: End-to-End Program Repair with LLMs, FSE 2023
• AdaptivePaste: Intelligent Copy-Paste in IDE, FSE 2023
• Learning to Reduce False Positives in Analytic Bug Detectors, ICSE 2022

Bowen Xu

• Predicting semantically linkable knowledge in developer online forums via convolutional neural network, ASE 2016
• Answer Summarization for Technical Queries: Benchmark and New Approach, ASE 2022
• Compressing Pre-trained Models of Code into 3 MB, ASE 2022
• The Devil is in the Tails: How Long-Tailed Code Distributions Impact Large Language Models, ASE 2023
• Are We Ready to Embrace Generative AI for Software Q&A?, ASE 2023
• How to better utilize code graphs in semantic code search?, FSE 2022

Lin Tan

• Bugram: Bug detection with n-gram language models, ASE 2016
• CURE: Code-Aware Neural Machine Translation for Automatic Program Repair, ICSE 2021
• Revisiting Learning-based Commit Message Generation, ICSE 2023
• Impact of Code Language Models on Automated Program Repair, ICSE 2023
• CoCoNuT: combining context-aware neural translation models using ensemble for program repair, ISSTA 2020
• How Effective Are Neural Networks for Fixing Security Vulnerabilities, ISSTA 2023

Denys Poshyvanyk

• An Empirical Investigation into Learning Bug-Fixing Patches in the Wild via Neural Machine Translation, ASE 2018
• Helion: Enabling Natural Testing of Smart Homes, FSE 2023
• On Learning Meaningful Code Changes Via Neural Machine Translation, ICSE 2019
• On Learning Meaningful Assert Statements for Unit Test Cases, ICSE 2020
• Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks, ICSE 2021
• Using Pre-Trained Models to Boost Code Review Automation, ICSE 2022

Xiaodong Gu

• Answering Software Deployment Questions via Neural Machine Reading at Scale, ASE 2022
• InfeRE: Step-by-Step Regex Generation via Chain of Inference, ASE 2023
• Deep API learning, FSE 2016
• Diet code is healthy: simplifying programs for pre-trained models of code, FSE 2022
• Self-Supervised Query Reformulation for Code Search, FSE 2023
• Cross-Domain Deep Code Search with Meta Learning, ICSE 2022

Toufique Ahmed

• Few-shot training LLMs for project-specific code-summarization, ASE 2022
• Better Patching Using LLM Prompting, via Self-Consistency, ASE 2023
• Learning type annotation: is big data enough?, FSE 2021
• NatGen: generative pre-training by “naturalizing” source code, FSE 2022
• Multilingual training for Software Engineering, ICSE 2021
• Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models, ICSE 2023

Cuiyun Gao

• What Makes Good In-Context Demonstrations for Code Intelligence Tasks with LLMs?, ASE 2023
• Generative Type Inference for Python, ASE 2023
• REEF: A Framework for Collecting Real-World Vulnerabilities and Fixes, ASE 2023
• No more fine-tuning? an experimental evaluation of prompt tuning in code intelligence, FSE 2022
• Keeping Pace with Ever-Increasing Data: Towards Continual Learning of Code Intelligence Models, ICSE 2023
• CCTEST: Testing and Repairing Code Completion Systems, ICSE 2022

Pinjia He

• Machine translation testing via pathological invariance, FSE 2020
• Log Parsing with Generalization Ability under New Log Types, FSE 2023
• BiasAsker: Measuring the Bias in Conversational AI System, FSE 2023
• Automated Testing and Improvement of Named Entity Recognition Systems, FSE 2023
• Structure-Invariant Testing for Machine Translation, ICSE 2019
• AEON: a method for automatic evaluation of NLP test cases, ISSTA 2022

Collin McMillan

• Automatically generating commit messages from diffs using neural machine translation, ASE 2017
• Modeling Programmer Attention as Scanpath Prediction, ASE 2023
• A Language Model of Java Methods with Train/Test Deduplication, FSE 2023
• Improving automated source code summarization via an eye-tracking study of programmers, ICSE 2014
• A Neural Model for Generating Natural Language Summaries of Program Subroutines, ICSE 2019

Chunyang Chen

• Tell Them Apart: Distilling Technology Differences from Crowd-Scale Comparison Discussions, ASE 2018
• Object detection for graphical user interface: old fashioned or deep learning or a combination?, FSE 2020
• Unsupervised Software-Specific Morphological Forms Inference from Informal Discussions, ICSE 2017
• Automated Query Reformulation for Efficient Search Based on Query Logs From Stack Overflow, ICSE 2021
• Fill in the Blank: Context-aware Automated Text Input Generation for Mobile GUI Testing, ICSE 2022

Michele Tufano

• An Empirical Investigation into Learning Bug-Fixing Patches in the Wild via Neural Machine Translation, ASE 2018
• Exploring and evaluating personalized models for code generation, FSE 2022
• InferFix: End-to-End Program Repair with LLMs, FSE 2023
• On Learning Meaningful Code Changes Via Neural Machine Translation, ICSE 2019
• On Learning Meaningful Assert Statements for Unit Test Cases, ICSE 2020

Beijun Shen

• Lancer: Your Code Tell Me What You Need, ASE 2019
• Answering Software Deployment Questions via Neural Machine Reading at Scale, ASE 2022
• InfeRE: Step-by-Step Regex Generation via Chain of Inference, ASE 2023
• Diet code is healthy: simplifying programs for pre-trained models of code, FSE 2022
• Cross-Domain Deep Code Search with Meta Learning, ICSE 2022

Xing Hu

• Automating User Notice Generation for Smart Contract Functions, ASE 2021
• EditSum: A Retrieve-and-Edit Framework for Source Code Summarization, ASE 2021
• Identify and Update Test Cases When Production Code Changes: A Transformer-Based Approach, ASE 2023
• SkCoder: A Sketch-based Approach for Automatic Code Generation, ICSE 2023
• CoLeFunDa: Explainable Silent Vulnerability Fix Identification, ICSE 2023

Haoyu Wang

• Are they Toeing the Line? Diagnosing Privacy Compliance Violations among Browser Extensions, ASE 2022
• Natural Test Generation for Precise Testing of Question Answering Software, ASE 2022
• CHAMP: Characterizing Undesired App Behaviors from User Comments Based on Market Policies, ICSE 2021
• DescribeCtx: Context-Aware Description Synthesis for Sensitive Behaviors in Mobile Apps, ICSE 2022
• Demystifying Privacy Policy of Third-Party Libraries in Mobile Apps, ICSE 2023

Prem Devanbu

• Few-shot training LLMs for project-specific code-summarization, ASE 2022
• Better Patching Using LLM Prompting, via Self-Consistency, ASE 2023
• Learning type annotation: is big data enough?, FSE 2021
• NatGen: generative pre-training by “naturalizing” source code, FSE 2022
• Multilingual training for Software Engineering, ICSE 2021

Shing-Chi Cheung

• Nuances are the Key: Unlocking ChatGPT to Find Failure-Inducing Tests with Differential Prompting, ASE 2023
• OASIS: prioritizing static analysis warnings for Android apps based on app user reviews, FSE 2017
• Testing Coreference Resolution Systems without Labeled Test Sets, FSE 2023
• Coverage-Driven Test Code Generation for Concurrent Classes, ICSE 2016
• TransRegex: Multi-modal Regular Expression Synthesis by Generate-and-Repair, ICSE 2020

Chunqiu Steven Xia

• The Plastic Surgery Hypothesis in the Era of Large Language Models, ASE 2023
• Less training, more repairing please: revisiting automated program repair via zero-shot learning, FSE 2022
• Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair, FSE 2023
• Automated Program Repair in the Era of Large Pre-trained Language Models, ICSE 2023
• Large Language Models Are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models, ISSTA 2022

Antonio Mastropaolo

• Towards Automatically Addressing Self-Admitted Technical Debt: How Far Are We?, ASE 2023
• Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks, ICSE 2021
• Using Deep Learning to Generate Complete Log Statements, ICSE 2022
• Using Pre-Trained Models to Boost Code Review Automation, ICSE 2022
• On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot, ICSE 2023

Chaozheng Wang

• Generative Type Inference for Python, ASE 2023
• REEF: A Framework for Collecting Real-World Vulnerabilities and Fixes, ASE 2023
• No more fine-tuning? an experimental evaluation of prompt tuning in code intelligence, FSE 2022
• Keeping Pace with Ever-Increasing Data: Towards Continual Learning of Code Intelligence Models, ICSE 2023
• CCTEST: Testing and Repairing Code Completion Systems, ICSE 2022

Zeyu Sun

• A syntax-guided edit decoder for neural program repair, FSE 2021
• Automatic Testing and Improvement of Machine Translation, ICSE 2019
• FIRA: Fine-Grained Graph-Based Code Change Representation for Automated Commit Message Generation, ICSE 2022
• Improving Machine Translation Systems via Isotopic Replacement, ICSE 2022
• Tare: Type-Aware Neural Program Repair, ICSE 2023

Sallam Abualhaija

• TAPHSIR: towards AnaPHoric ambiguity detection and ReSolution in requirements, FSE 2022
• COREQQA - A COmpliance REQuirements Understanding using Question Answering Tool, FSE 2022
• Using Domain-Specific Corpora for Improved Handling of Ambiguity in Requirements, ICSE 2021
• Automated Handling of Anaphoric Ambiguity in Requirements: A Multi-solution Study, ICSE 2022
• AI-based Question Answering Assistance for Analyzing Natural-language Requirements, ICSE 2023

Xu Wang

• A Novel Neural Source Code Representation Based on Abstract Syntax Tree, ICSE 2019
• Retrieval-based Neural Source Code Summarization, ICSE 2020
• Improving Fault Localization and Program Repair with Deep Semantic Features and Transferred Knowledge, ICSE 2022
• Template-based Neural Program Repair, ICSE 2023
• Detecting Condition-Related Bugs with Control Flow Graph Neural Network, ISSTA 2023

Hailong Sun

• A Novel Neural Source Code Representation Based on Abstract Syntax Tree, ICSE 2019
• Retrieval-based Neural Source Code Summarization, ICSE 2020
• Improving Fault Localization and Program Repair with Deep Semantic Features and Transferred Knowledge, ICSE 2022
• Template-based Neural Program Repair, ICSE 2023
• Detecting Condition-Related Bugs with Control Flow Graph Neural Network, ISSTA 2023

Xudong Liu

• A Novel Neural Source Code Representation Based on Abstract Syntax Tree, ICSE 2019
• Retrieval-based Neural Source Code Summarization, ICSE 2020
• Improving Fault Localization and Program Repair with Deep Semantic Features and Transferred Knowledge, ICSE 2022
• Template-based Neural Program Repair, ICSE 2023
• Detecting Condition-Related Bugs with Control Flow Graph Neural Network, ISSTA 2023

Luca Pascarella

• Evaluating SZZ Implementations Through a Developer-Informed Oracle, ICSE 2021
• Using Deep Learning to Generate Complete Log Statements, ICSE 2022
• Using Pre-Trained Models to Boost Code Review Automation, ICSE 2022
• On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot, ICSE 2023
• Automating Code-Related Tasks Through Transformers: The Impact of Pre-training, ICSE 2023

Vincent Hellendoorn

• Perceived language complexity in GitHub issue discussions and their effect on issue resolution, ASE 2017
• CAT-LM Training Language Models on Aligned Code And Tests, ASE 2023
• Are deep neural networks the best choice for modeling source code?, FSE 2017
• On the naturalness of proofs, FSE 2018

Yao Wan

• Improving Automatic Source Code Summarization via Deep Reinforcement Learning, ASE 2018
• Multi-modal Attention Network Learning for Semantic Source Code Retrieval, ASE 2019
• You see what I want you to see: poisoning vulnerabilities in neural code search, FSE 2022
• What Do They Capture? - A Structural Analysis of Pre-Trained Language Models for Source Code, ICSE 2022

Guandong Xu

• Improving Automatic Source Code Summarization via Deep Reinforcement Learning, ASE 2018
• Multi-modal Attention Network Learning for Semantic Source Code Retrieval, ASE 2019
• You see what I want you to see: poisoning vulnerabilities in neural code search, FSE 2022
• What Do They Capture? - A Structural Analysis of Pre-Trained Language Models for Source Code, ICSE 2022

Tegawendé F. Bissyandé

• Assessing the Generalizability of Code2vec Token Embeddings, ASE 2019
• Evaluating Representation Learning of Code Changes for Predicting Patch Correctness in Program Repair, ASE 2020
• Natural Language to Code: How Far Are We?, FSE 2023
• CodeGrid: A Grid Representation of Code, ISSTA 2023

Shaohua Wang

• Combining Program Analysis and Statistical Language Model for Code Statement Completion, ASE 2019
• DLFix: Context-based Code Transformation Learning for Automated Program Repair, ICSE 2020
• A Context-Based Automated Approach for Method Name Consistency Checking and Suggestion, ICSE 2021
• DEAR: A Novel Deep Learning-based Approach for Automated Program Repair, ICSE 2022

Jianjun Zhao

• A Quantitative Analysis Framework for Recurrent Neural Network, ASE 2019
• DeepMutation++: A Mutation Testing Framework for Deep Learning Systems, ASE 2019
• Marble: Model-based Robustness Analysis of Stateful Deep Learning Systems, ASE 2020
• DeepStellar: model-based quantitative analysis of stateful deep learning systems, FSE 2019

Songqiang Chen

• Stay Professional and Efficient: Automatically Generate Titles for Your Bug Reports, ASE 2020
• Testing Your Question Answering Software via Asking Recursively, ASE 2021
• Property-based Test for Part-of-Speech Tagging Tool, ASE 2021
• Validation on machine reading comprehension software without annotated labels: a property-based method, FSE 2021

Xiaoyuan Xie

• Stay Professional and Efficient: Automatically Generate Titles for Your Bug Reports, ASE 2020
• Testing Your Question Answering Software via Asking Recursively, ASE 2021
• Property-based Test for Part-of-Speech Tagging Tool, ASE 2021
• Validation on machine reading comprehension software without annotated labels: a property-based method, FSE 2021

Shangqing Liu

• A Unified Framework to Learn Program Semantics with Graph Neural Networks, ASE 2020
• TransRepair: Context-aware Program Repair for Compilation Errors, ASE 2022
• Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases, ASE 2023
• ContraBERT: Enhancing Code Pre-trained Models via Contrastive Learning, ICSE 2023

Jia Li

• EditSum: A Retrieve-and-Edit Framework for Source Code Summarization, ASE 2021
• ZC3: Zero-Shot Cross-Language Code Clone Detection, ASE 2023
• SkCoder: A Sketch-based Approach for Automatic Code Generation, ICSE 2023

Jidong Ge

• AST-Transformer: Encoding Abstract Syntax Trees Efficiently for Code Summarization, ASE 2021
• Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases, ASE 2023
• SPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations, ICSE 2022
• AST-Trans: Code Summarization with Efficient Tree-Structured Attention, ICSE 2022

Pengyu Nie

• CoditT5: Pretraining for Source Code and Natural Language Editing, ASE 2022
• On the naturalness of hardware descriptions, FSE 2020
• Multilingual Code Co-evolution using Large Language Models, FSE 2023
• Learning Deep Semantics for Test Completion, ICSE 2023

Junyi Jessy Li

• CoditT5: Pretraining for Source Code and Natural Language Editing, ASE 2022
• On the naturalness of hardware descriptions, FSE 2020
• Multilingual Code Co-evolution using Large Language Models, FSE 2023
• Learning Deep Semantics for Test Completion, ICSE 2023

Miloš Gligorić

• CoditT5: Pretraining for Source Code and Natural Language Editing, ASE 2022
• On the naturalness of hardware descriptions, FSE 2020
• Multilingual Code Co-evolution using Large Language Models, FSE 2023
• Learning Deep Semantics for Test Completion, ICSE 2023

Shangwen Wang

• Is this Change the Answer to that Problem?: Correlating Descriptions of Bug and Code Changes for Evaluating Patch Correctness, ASE 2022
• Natural Language to Code: How Far Are We?, FSE 2023
• An Extensive Study on Adversarial Attack against Pre-trained Models of Code, FSE 2023
• CCT5: A Code-Change-Oriented Pre-trained Model, FSE 2023

Junjie Chen

• Learning to Construct Better Mutation Faults, ASE 2022
• Natural Test Generation for Precise Testing of Question Answering Software, ASE 2022
• Robust log-based anomaly detection on unstable log data, FSE 2019
• On the Evaluation of Neural Code Summarization, ICSE 2021

Qihao Zhu

• Learning to Construct Better Mutation Faults, ASE 2022
• A syntax-guided edit decoder for neural program repair, FSE 2021
• FIRA: Fine-Grained Graph-Based Code Change Representation for Automated Commit Message Generation, ICSE 2022
• Tare: Type-Aware Neural Program Repair, ICSE 2023

Xiwei Xu

• Prompt-tuned Code Language Model as a Neural Knowledge Base for Type Inference in Statically-Typed Partial Code, ASE 2022
• Let’s Chat to Find the APIs: Connecting Human, LLM and Knowledge Graph through AI Chain, ASE 2023
• Object detection for graphical user interface: old fashioned or deep learning or a combination?, FSE 2020
• Silent Vulnerable Dependency Alert Prediction with Vulnerability Key Aspect Explanation, ICSE 2023

Anh Tuan Nguyen

• Next Syntactic-Unit Code Completion and Applications, ASE 2022
• A statistical semantic language model for source code, FSE 2013
• Lexical statistical machine translation for language migration, FSE 2013
• T2API: synthesizing API code usage templates from English texts with statistical translation, FSE 2016

Xin Peng

• An Empirical Study of Parameter-Efficient Fine-Tuning Methods for Pre-Trained Code Models, ASE 2023
• CodeGen4Libs: A Two-Stage Approach for Library-Oriented Code Generation, ASE 2023
• Generating Variable Explanations via Zero-shot Prompt Learning, ASE 2023
• Generating query-specific class API summaries, FSE 2019

Yiling Lou

• CodeGen4Libs: A Two-Stage Approach for Library-Oriented Code Generation, ASE 2023
• Generating Variable Explanations via Zero-shot Prompt Learning, ASE 2023
• FIRA: Fine-Grained Graph-Based Code Change Representation for Automated Commit Message Generation, ICSE 2022
• Revisiting Learning-based Commit Message Generation, ICSE 2023

Simone Scalabrino

• Using Deep Learning to Automatically Improve Code Readability, ASE 2023
• Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks, ICSE 2021
• Evaluating SZZ Implementations Through a Developer-Informed Oracle, ICSE 2021
• On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot, ICSE 2023

Rocco Oliveto

• Using Deep Learning to Automatically Improve Code Readability, ASE 2023
• Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks, ICSE 2021
• Evaluating SZZ Implementations Through a Developer-Informed Oracle, ICSE 2021
• On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot, ICSE 2023

Wenxuan Wang

• What Makes Good In-Context Demonstrations for Code Intelligence Tasks with LLMs?, ASE 2023
• Generative Type Inference for Python, ASE 2023
• BiasAsker: Measuring the Bias in Conversational AI System, FSE 2023
• AEON: a method for automatic evaluation of NLP test cases, ISSTA 2022

Kevin Moran

• A Comparative Study of Transformer-Based Neural Text Representation Techniques on Bug Triaging, ASE 2023
• Helion: Enabling Natural Testing of Smart Homes, FSE 2023
• On Learning Meaningful Assert Statements for Unit Test Cases, ICSE 2020
• AidUI: Toward Automated Recognition of Dark Patterns in User Interfaces, ICSE 2023

Jian Zhang

• An Empirical Study on Fine-Tuning Large Language Models of Code for Automated Program Repair, ASE 2023
• A Novel Neural Source Code Representation Based on Abstract Syntax Tree, ICSE 2019
• Retrieval-based Neural Source Code Summarization, ICSE 2020
• Detecting Condition-Related Bugs with Control Flow Graph Neural Network, ISSTA 2023

Ming Wen

• SMT Solver Validation Empowered by Large Pre-Trained Language Models, ASE 2023
• Testing Coreference Resolution Systems without Labeled Test Sets, FSE 2023
• Natural Language to Code: How Far Are We?, FSE 2023
• An Extensive Study on Adversarial Attack against Pre-trained Models of Code, FSE 2023

Zhendong Su

• On the localness of software, FSE 2014
• Machine translation testing via pathological invariance, FSE 2020
• Stochastic Optimization of Program Obfuscation, ICSE 2017
• Structure-Invariant Testing for Machine Translation, ICSE 2019

Premkumar T. Devanbu

• On the localness of software, FSE 2014
• Are deep neural networks the best choice for modeling source code?, FSE 2017
• On the naturalness of proofs, FSE 2018
• On the naturalness of software, ICSE 2012

Miltiadis Allamanis

• Learning natural coding conventions, FSE 2014
• Mining idioms from source code, FSE 2014
• Suggesting accurate method and class names, FSE 2015
• AdaptivePaste: Intelligent Copy-Paste in IDE, FSE 2023

Charles Sutton

• Learning natural coding conventions, FSE 2014
• Mining idioms from source code, FSE 2014
• Suggesting accurate method and class names, FSE 2015
• Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code, ICSE 2020

Yepang Liu

• OASIS: prioritizing static analysis warnings for Android apps based on app user reviews, FSE 2017
• Natural Language to Code: How Far Are We?, FSE 2023
• CCT5: A Code-Change-Oriented Pre-trained Model, FSE 2023
• Demystifying Privacy Policy of Third-Party Libraries in Mobile Apps, ICSE 2023

Dongmei Zhang

• Robust log-based anomaly detection on unstable log data, FSE 2019
• On the Evaluation of Neural Code Summarization, ICSE 2021
• CoCoSoDa: Effective Contrastive Learning for Code Search, ICSE 2022
• Towards Efficient Fine-Tuning of Pre-trained Code Models: An Experimental Study and Beyond, ISSTA 2023

Lu Zhang

• A syntax-guided edit decoder for neural program repair, FSE 2021
• Automatic Testing and Improvement of Machine Translation, ICSE 2019
• Improving Machine Translation Systems via Isotopic Replacement, ICSE 2022
• Tare: Type-Aware Neural Program Repair, ICSE 2023

Sumit Gulwani

• AI-assisted programming: applications, user experiences, and neuro-symbolic techniques (keynote), FSE 2022
• NL2Viz: natural language to visualization via constrained syntax-guided synthesis, FSE 2022
• Grace: Language Models Meet Code Edits, FSE 2023
• Program Synthesis Using Natural Language, ICSE 2015

Junjie Wang

• Are we building on the rock? on the importance of data preprocessing for code summarization, FSE 2022
• CLEAR: Contrastive Learning for API Recommendation, ICSE 2022
• Where is Your App Frustrating Users?, ICSE 2022
• Fill in the Blank: Context-aware Automated Text Input Generation for Mobile GUI Testing, ICSE 2022

Lingxiao Jiang

• An empirical study of blockchain system vulnerabilities: modules, types, and patterns, FSE 2021
• iTiger: an automatic issue title generation tool, FSE 2022
• RecipeGen++: an automated trigger action programs generator, FSE 2022
• InferCode: Self-Supervised Learning of Code Representations by Predicting Subtrees, ICSE 2020

Saad Ezzini

• TAPHSIR: towards AnaPHoric ambiguity detection and ReSolution in requirements, FSE 2022
• Using Domain-Specific Corpora for Improved Handling of Ambiguity in Requirements, ICSE 2021
• Automated Handling of Anaphoric Ambiguity in Requirements: A Multi-solution Study, ICSE 2022
• AI-based Question Answering Assistance for Analyzing Natural-language Requirements, ICSE 2023

Mark Harman

• A study of equivalent and stubborn mutation operators using human analysis of equivalence, ICSE 2014
• Automatic Testing and Improvement of Machine Translation, ICSE 2019
• Improving Machine Translation Systems via Isotopic Replacement, ICSE 2022
• Who Judges the Judge: An Empirical Study on Online Judge Tests, ISSTA 2023

Thibaud Lutellier

• CURE: Code-Aware Neural Machine Translation for Automatic Program Repair, ICSE 2021
• Impact of Code Language Models on Automated Program Repair, ICSE 2023
• CoCoNuT: combining context-aware neural translation models using ensemble for program repair, ISSTA 2020
• How Effective Are Neural Networks for Fixing Security Vulnerabilities, ISSTA 2023

Yanlin Wang

• On the Evaluation of Neural Code Summarization, ICSE 2021
• CoCoSoDa: Effective Contrastive Learning for Code Search, ICSE 2022
• Towards Efficient Fine-Tuning of Pre-trained Code Models: An Experimental Study and Beyond, ISSTA 2023
• RefBERT: A Two-Stage Pre-trained Framework for Automatic Rename Refactoring, ISSTA 2023