arXiv 2026
Teaching Code Agents to Ask Without Leaking Private Code.
arXiv 2026
Teaching Code Agents to Ask Without Leaking Private Code.
arXiv 2026
Runnable Commit Untangling for Coding Agents.
EMNLP 2026
ManimAgent: Self-Evolving Multimodal Agents for Visual Education.
ISSTA 2026
Hidden Licensing Risks in the LLMware Ecosystem.
TOSEM 2026
Ecosystem of Large Language Models for Code.
TSE 2026
Automated TEE Adaptation with LLMs: Identifying, Transforming, and Porting Sensitive Functions in Programs.
ICML 2026
PrivCode++: Latent-Conditioned Differentially Private Code Generation for Comprehensive Guarantees.
ICML 2026
Watermarking LLM Agent Trajectories.
ISSTA 2026
Learning from the Test: Self-Referential Differential Testing for Deep RL Agents.
ISSTA 2026
Insecure Coding Preferences in Long-Term Memory: Security Risks for LLM-based Code Generation.
ASE 2026
Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering.
ASE 2026
How Reasoning Shapes Social Bias in LLM-Generated Code?
ICSE 2026
Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning.
ICSE 2026
Training on Clean Data but Getting Backdoored Models! A Poisoning Attack on Code Encoders.
EASE 2026
Quality Assurance for Artificial Intelligence: A Study of Industrial Concerns, Challenges and Best Practices.
FSE 2026
Towards Efficient Code LLM Inference with Quantization and Compilation-Time Optimization.
FSE 2026 Doctoral Symposium
Automated Diagnosis and Testing of Game Compatibility Layers.
ACSAC 2026
Finding Memory Leaks in C/C++ Programs via Neuro-Symbolic Augmented Static Analysis.
ACL 2026
MultiCodeAttack: Iterative Jailbreak Attacking on LLMs with Multi-Code Prompt Injection.
PhD Thesis 2025 SMU
Towards Robust, Secure, and Privacy-Aware Large Language Models of Code.
π ACM SIGSOFT Outstanding Doctoral Dissertation Award
TOSEM 2025
Efficient and Green Large Language Models for Software Engineering: Literature Review, Vision, and the Road Ahead.
TOSEM 2025
Prioritizing Speech Test Cases.
TOSEM 2025
Finding Safety Violations of AI-Enabled Control Systems through the Lens of Synthesized Proxy Programs.
arXiv 2025
Mut4All: Fuzzing Compilers via LLM-Synthesized Mutators Learned from Bug Reports.
TOSEM 2025
YourCoLo: Leveraging One-to-Many Relationships and Inter-Code Connections for User Review-Based Code Localization.
EMSE 2025
PTM4Tag+: Tag Recommendation of Stack Overflow Posts with Pre-trained Models.
ASE 2025
"My productivity is boosted, but ..." Demystifying Users' Perception on AI Coding Assistants.
π ACM SIGSOFT Distinguished Paper Award
ASE 2025
Backdoors in Code Summarizers: How Bad Is It?
ASE 2025
Token Sugar: Making Source Code Sweeter for LLMs through Token-Efficient Shorthand.
ACM MM 2025
Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?
AIware 2025
How Does Quantization Impact Privacy Risk on LLMs for Code?
arXiv 2025
SLICEMATE: Accurate and Scalable Static Program Slicing via LLM-Powered Agents.
ICSME 2025 Registered Reports
Learning From the Best: What Makes Popular Hugging Face Models? A Registered Report.
TOSEM 2025
Synthesizing Efficient and Permissive Programmatic Runtime Shields for Neural Policies.
ICSE 2024 SRC
Classifying Source Code: How Far Can Compressor-based Classifiers Go?
π ACM Student Research Competition Gold Medal
arXiv 2024
Robustness, Security, Privacy, Explainability, Efficiency, and Usability of Large Language Models for Code.
ICSE 2024
Unveiling Memorization in Code Models.
TSE 2024
Gotcha! This Model Uses My Code! Evaluating Membership Leakage Risks in Code Models.
ISSTA 2024
AI Coders Are among Us: Rethinking Programming Language Grammar towards Efficient Code Generation.
π ACM SIGSOFT Distinguished Paper Award
ICSE 2024
Curiosity-Driven Testing for Sequential Decision-Making Process.
ICSE-SEIS 2024
Greening Large Language Models of Code.
arXiv 2024
Hotfixing Large Language Models for Code: How Far Can Parameter-Efficient Fine-Tuning Go?
TOSEM 2024
Large Language Models for Software Engineering: A Systematic Literature Review.
π ACM TOSEM 2024 Most Cited Paper
S&P 2024
BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets.
SEET@ICSE 2024
Assessing AI Detectors in Identifying AI-Generated Code: Implications for Education.
TOSEM 2024
Representation Learning for Stack Overflow Posts: How Far Are We?
TSE 2024
Stealthy Backdoor Attack for Code Models.
π IEEE Computer Society Best Paper Award
arXiv 2023
Data Augmentation Approaches for Source Code Models: A Survey.
ICSME 2023
CCBERT: Self-Supervised Code Change Representation Learning.
ISSTA 2023
Synthesizing Speech Test Cases with Text-to-Speech? An Empirical Study on the False Alarms in Automated Speech Recognition Testing.
ICST 2023
ASDF: A Differential Testing Framework for Automatic Speech Recognition Systems.
MSR 2023
What Do Users Ask in Open-Source AI Repositories? An Empirical Study of GitHub Issues.
MSR 2023
NICHE: A Curated Dataset of Engineered Machine Learning Projects in Python.
SANER 2023
Towards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinking.
SANER 2023
Exploring and Repairing Gender Fairness Violations in Word Embedding-based Sentiment Analysis Model through Adversarial Patches.
arXiv 2023
Adversarial Attacks on Code Models with Discriminative Graph Patterns.
Book Chapter 2023
Supporting Collateral Evolution in Software Ecosystems.
Software Ecosystems: Tooling and Analytics Β· Chapter 7
TSE 2022
BiasFinder: Metamorphic Test Generation to Uncover Bias for Sentiment Analysis Systems.
ICSE 2022
Natural Attack for Pre-trained Models of Code.
ASE 2022
Compressing Pre-trained Models of Code into 3 MB.
π ACM SIGSOFT Distinguished Paper Award Nomination
ICPC 2022
PTM4Tag: Sharpening Tag Recommendation of Stack Overflow Posts with Pre-trained Models.
ASE 2022
Answer Summarization for Technical Queries: Benchmark and New Approach.
SANER 2022
Aspect-Based API Review Classification: How Far Can Pre-Trained Transformer Model Go?
ACSAC 2022
Curiosity-Driven and Victim-Aware Adversarial Policies.
π Honorable Mention Award
SANER 2022
Revisiting Neuron Coverage Metrics and Quality of Deep Neural Networks.
SANER 2022
Can Identifier Splitting Improve Open-Vocabulary Language Model of Code?
ESEC/FSE 2021
BiasRV: Uncovering Biased Sentiment Predictions at Runtime.
ESEC/FSE 2021
CrossASR++: A Modular Differential Testing Framework for Automatic Speech Recognition.
ICSME 2021
BiasHeal: On-the-Fly Black-Box Healing of Bias in Sentiment Analysis Systems.
ICSME 2021
Can Differential Testing Improve Automatic Speech Recognition Systems?
ASE 2021
IncBL: Incremental Bug Localization.