Publications

[J25] Journal Evaluating Incompatible Third-party Library API Usage in LLM-based Code Completion

[C60] Conference SEER: Self-Enhancing Chain-of-Thought Compression for Reasoning Models

[J24] Journal Code Refinement With Repository Context: How Far Are We?

[J23] Journal GUIGroup: Enabling Functional Layout Grouping with Multimodal Large Language Models

[C59] Conference Cracking Query Bottlenecks: Towards Efficiency-Oriented Text-to-SQL Generation

[C58] Conference SmartDecompiler-R1: Enhancing Faithful and Explainable Smart Contract Bytecode Decompilation with Reinforcement Learning

[C57] Conference ExecVerify: White-box RL With Verifiable Stepwise Rewards for Code Execution Reasoning

[C56] Conference Adaptive Mutation Scheduling with Deep Reinforcement Learning for Smart Contract Fuzzing

[J22] Journal Trace: Securing Smart Contract Repository Against Access Control Vulnerability

[J21] Journal Improving Gas Efficiency in Smart Contracts: Data-Driven Insights and LLM-Assisted Remediation

[J20] Journal Fortifying the Seams Between C/C++ and Rust: Characterizing Bugs in Interop Tools

[J19] Journal Delving into History: Retrieve Less but Augment More on Commit Message Generation

[C55] Conference Lost in Blockchain Address Misuse: Hidden Cross-Platform Risks and Their Security Impact

[C54] Conference Can LLMs Keep Up with Library Changes? An Exploratory Study on LLM-Generated Code

[J18] Journal RLV: LLM-Based Vulnerability Detection by Retrieving and Refining Contextual Information

[J17] Journal Enhancing Domain-Specific Code Completion via Collaborative Inference with Large and Small Language Models

[C53] Conference ACTaint: Agent-Based Taint Analysis for Access Control Vulnerabilities in Smart Contracts

[C52] Conference SolContractEval: A Benchmark for Evaluating Contract-level Solidity Code Generation

[C51] Conference FGIT: Fault-guided Fine-tuning for Code Generation

[C50] Conference FIRE: Smart Contract Bytecode Function Identification via Graph-Refined Hybrid Feature Encoding

[C49] Conference Code2API: A Tool for Generating Reusable APIs from Stack Overflow Code Snippets

[C48] Conference Award LLM4SZZ: Enhancing SZZ Algorithm with Context-Enhanced Assessment on Large Language Models

[C47] Conference More Effective JavaScript Breaking Change Detection via Dynamic Object Relation Graph

[C46] Conference Award A Comprehensive Study of Bug Characteristics on Foundation Language Models

[J16] Journal Towards Better Comprehension of Breaking Changes in NPM Ecosystem

[J15] Journal Enhancing Bug-Inducing Commit Identification: A Fine-Grained Semantic Analysis Approach

[J14] Journal Automating Comment Generation for Smart Contract from Bytecode

[C45] Conference Automatic Commit Range Identification of Untagged Version

[C44] Conference Analyzing and Detecting Toxicities in Developer Online Chatrooms: A Fine-Grained Taxonomy and Automated Detection Approach

[C43] Conference Instructive Code Retriever: Learn From Large Language Model’s Feedback for Code Intelligence Tasks

[C42] Conference Unveil the Mystery of Critical Software Vulnerabilities

[C41] Conference Are Human Rules Necessary? Generating Reusable APIs with CoT Reasoning and In-context Learning

[J13] Journal E-PRedictor: An Approach for Early Prediction of Pull Request Acceptance

[J12] Journal Market manipulation of Cryptocurrencies: Evidence from Social Media and Transaction Data

[C40] Conference Award A Large-Scale Empirical Study of Open Source License Usage: Practices and Challenges

[C39] Conference Dual Prompt-Based Few-Shot Learning for Automated Vulnerability Patch Localization

[C38] Conference Sustainability Forecasting for Deep Learning Packages

[C37] Conference Robust Auto-Scaling with Probabilistic Workload Forecasting for Cloud Databases

[C36] Conference Towards More Practical Automation of Vulnerability Assessment

[C35] Conference Neural SZZ Algorithm

[C34] Conference Award The Future Can’t Help Fix The Past: Assessing Program Repair In The Wild

[C33] Conference An Empirical Study of the Apache Voting Process on Open Source Community Governance

[J11] Journal Survey of Open Source Software Vulnerability Awareness

[C32] Conference Patchmatch: A Tool for Locating Patches of Open Source Project Vulnerabilities

[C31] Conference Fine-grained Commit-level Vulnerability Type Prediction By CWE Tree Structure

[C30] Conference Automated Unearthing of Dangerous Issue Reports

[C29] Conference Code Reviewer Recommendation in Tencent: Practice, Challenge, and Direction

[C28] Conference VCMatch: A Ranking-based Approach for Automatic Security Patches Localization for OSS Vulnerabilities

[C27] Conference Recommending Code Reviewers for Proprietary Software Projects: A Large Scale Study

[C26] Conference V-SZZ: Automatic Identification of Version Ranges Affected by CVE Vulnerabilities

[J10] Journal How does Working from Home Affect Developer Productivity? – A Case Study of Baidu During the COVID-19 Pandemic

[C25] Conference Automating Developer Chat Mining

[C24] Conference Enhancing Developer Interactions with Programming Screencasts through Accurate Code Extraction

[J9] Journal psc2code: Denoising Code Extraction from Programming Screencasts

[C23] Conference AppMoD: Helping Older Adults Manage Mobile Security with Online Social Help

[J8] Journal A Large Scale Study of Long-Time Contributor Prediction for GitHub Projects

[C22] Conference Statistical Log Differencing

[C21] Conference On Reliability of Patch Correctness Assessment

[J7] Journal VT-Revolution: Interactive Programming Video Tutorial Authoring and Watching System

[J6] Conference APIReal: An API Recognition and Linking Approach for Online Developer Forums

[C20] Conference Categorizing and Predicting Invalid Vulnerabilities on Common Vulnerabilities and Exposures

[C19] Conference Award A Smart Context-aware Program Assistant based on Dynamic Programming Event Modeling

[C18] Conference Towards Mining Comprehensive Android Sandboxes

[C17] Demo DSM: A Specification Mining Tool using Recurrent Neural Network Based Language Model

[C16] Demo VT-Revolution: Interactive Programming Tutorials Made Possible

[C15] Conference Using Finite-State Models for Log Differencing

[C14] Conference Characterizing Common and Domain-Specific Package Bugs: A Case Study on Ubuntu

[C13] Conference Mining Sandboxes: Are We There Yet?

[J5] Conference Inference of Development Activities from Interaction with Uninstrumented Applications

[J4] Journal Measuring Program Comprehension: A Large-Scale Field Study with Professionals

[J3] Conference What Do Developers Search For on the Web?

[J2] Journal Automated Android App Permission Recommendation

[C12] Conference Personality and Project Success: Insights from a Large-Scale Study with Professionals

[C11] Conference Who Will Leave the Company? - A Large-Scale Industry Study of Developer Turnover by Mining Monthly Work Report

[J1] Conference Extracting and Analyzing Time-Series HCI Data from Screen-Captured Task Videos

[C10] Conference What Permissions Should This App Request?

[C9] Conference Combining Word Embedding with Information Retrieval to Recommend Similar Bug Reports

[C8] Conference Automated Debugging Considered Harmful Considered Harmful -- A User Study Revisiting the Usefulness of Spectra-Based Fault Localization Techniques with Professionals using Real Bugs from Large Systems

[C7] Conference How Android App Developers Manage Power Consumption? – An Empirical Study by Mining Power Management Commits

[C6] Conference BPMiner: Mining Developers’ Behavior Patterns from Screen-Captured Task Videos

[C5] Conference Tracking and Analyzing Cross-Cutting Activities in Developers’ Daily Work

[C4] Demo ActivitySpace: An Interapplication Remembrance Agent for Integrated Knowledge Work

[C3] Demo scvRipper: Video Scraping Tool for Modeling Developers’ Behavior Using Interaction Data

[C2] Conference Reverse Engineering Time-Series Interaction Data from Screen-Captured Videos

[C1] Conference amAssist: In-IDE Ambient Search of Online Programming Resources