← authors · overview

• StarCoder: may the source be with you!
  2023 · 197 citations
• InCoder: A Generative Model for Code Infilling and Synthesis
  2022 · 142 citations
• SantaCoder: don't reach for the stars!
  2023 · 54 citations
• Natural Language to Code Translation with Execution
  2022 · 38 citations
• DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
  2022 · 33 citations
• Coder Reviewer Reranking for Code Generation
  2022 · 7 citations
• CodeRAG-Bench: Can Retrieval Augment Code Generation?
  2024 · 3 citations
• Data Augmentation for Code Translation with Comparable Corpora and Multiple References
  2023 · 3 citations
• ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?
  2024 · 3 citations
• SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
  2025 · 2 citations
• SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
  2025 · 2 citations
• Execution-Based Evaluation for Open-Domain Code Generation
  2022 · 2 citations
• CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks
  2024 · 1 citations
• Toward Training Superintelligent Software Agents through Self-Play SWE-RL
  2025
• Generating Pragmatic Examples to Train Neural Program Synthesizers
  2023