← authors · overview

• UniXcoder: Unified Cross-Modal Pre-training for Code Representation
  2022 · 542 citations
• CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
  2021 · 415 citations
• CodeBLEU: a Method for Automatic Evaluation of Code Synthesis
  2020 · 187 citations
• GraphCodeBERT: Pre-training Code Representations with Data Flow
  2020 · 155 citations
• Automating Code Review Activities by Large-Scale Pre-training
  2022 · 155 citations
• InferFix: End-to-End Program Repair with LLMs
  2023 · 140 citations
• Learning to Recommend Method Names with Global Context
  2022 · 32 citations
• Code Execution with Pre-trained Language Models
  2023 · 19 citations
• Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy
  2021 · 11 citations
• TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs
  2023 · 9 citations
• Competition-Level Problems are Effective LLM Evaluators
  2023 · 4 citations
• Contextualized Data-Wrangling Code Generation in Computational Notebooks
  2024 · 4 citations
• Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency
  2023 · 2 citations
• AutoVerus: Automated Proof Generation for Rust Code
  2024 · 1 citations
• Reducing the Costs of Proof Synthesis on Rust Systems by Scaling Up a Seed Training Set
  2026