SPENCER: Self-Adaptive Model Distillation for Efficient Code RetrievalACM Transactions on Software Engineering and Methodology (TOSEM), 2025 |
LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation GroundingInternational Conference on Learning Representations (ICLR), 2025 |
Speculative Decoding for Verilog: Speed and Quality, All in OneDesign Automation Conference (DAC), 2025 |
Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?Annual Meeting of the Association for Computational Linguistics (ACL), 2025 |
Code LLMs: A Taxonomy-based SurveyBigData Congress [Services Society] (BSS), 2024 |
GALLa: Graph Aligned Large Language Models for Improved Source Code UnderstandingAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
Analyzing the Performance of Large Language Models on Code SummarizationInternational Conference on Language Resources and Evaluation (LREC), 2024 |
CSEPrompts: A Benchmark of Introductory Computer Science PromptsInternational Syposium on Methodologies for Intelligent Systems (ISMIS), 2024 |
Investigating the Efficacy of Large Language Models for Code Clone
DetectionIEEE International Conference on Program Comprehension (ICPC), 2024 |
Deep Learning for Code Intelligence: Survey, Benchmark and ToolkitACM Computing Surveys (ACM Comput. Surv.), 2023 |
Language Agnostic Code EmbeddingsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2023 |
Rethinking Negative Pairs in Code SearchConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
Large Language Models for Software Engineering: A Systematic Literature
ReviewACM Transactions on Software Engineering and Methodology (TOSEM), 2023 |
Contrastive Learning for API Aspect AnalysisInternational Conference on Automated Software Engineering (ASE), 2023 |
Multi-target Backdoor Attacks for Code Pre-trained ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
Understanding Programs by Exploiting (Fuzzing) Test CasesAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
CCT-Code: Cross-Consistency Training for Multilingual Clone Detection
and Code SearchNorth American Chapter of the Association for Computational Linguistics (NAACL), 2023 |
Searching by Code: a New SearchBySnippet Dataset and SnippeR Retrieval
Model for Searching by Code SnippetsInternational Conference on Language Resources and Evaluation (LREC), 2023 |
CodeT5+: Open Code Large Language Models for Code Understanding and
GenerationConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
Code Execution with Pre-trained Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
An Unbiased Transformer Source Code Learning with Semantic Vulnerability
GraphEuropean Symposium on Security and Privacy (Euro S&P), 2023 |
An Empirical Study of Deep Learning Models for Vulnerability DetectionInternational Conference on Software Engineering (ICSE), 2022 |
CLAWSAT: Towards Both Robust and Accurate Code ModelsIEEE International Conference on Software Analysis, Evolution, and Reengineering (SANER), 2022 |
Exploring Representation-Level Augmentation for Code SearchConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
Soft-Labeled Contrastive Pre-training for Function-level Code
RepresentationConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models
for Programming Language Attend Code StructureConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
Semantic-Preserving Adversarial Code ComprehensionInternational Conference on Computational Linguistics (COLING), 2022 |
Finding Reusable Machine Learning Components to Build Programming
Language Processing PipelinesEuropean Conference on Software Architecture (ECSA), 2022 |
CoditT5: Pretraining for Source Code and Natural Language EditingInternational Conference on Automated Software Engineering (ASE), 2022 |
Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models
of Source CodeInternational Joint Conference on Artificial Intelligence (IJCAI), 2022 |