← authors · overview

• NatGen: Generative pre-training by "Naturalizing" source code
  2022 · 99 citations
• CYCLE: Learning to Self-Refine the Code Generation
  2024 · 29 citations
• Vulnerability Detection with Code Language Models: How Far Are We?
  2024 · 13 citations
• Patching as Translation: the Data and the Metaphor
  2020 · 11 citations
• CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion
  2023 · 11 citations
• CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context
  2022 · 10 citations
• CONCORD: Clone-aware Contrastive Learning for Source Code
  2023 · 6 citations
• SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning
  2024 · 6 citations
• TraceFixer: Execution Trace-Driven Program Repair
  2023 · 2 citations
• TRACED: Execution-aware Pre-training for Source Code
  2023 · 1 citations
• DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
  2026
• Towards Learning (Dis)-Similarity of Source Code from Program Contrasts
  2021
• VELVET: a noVel Ensemble Learning approach to automatically locate VulnErable sTatements
  2021
• Automated Code Editing with Search-Generate-Modify
  2023
• Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain
  2023