Code Generation & Program Synthesis

Program synthesis, code generation, code understanding.

A topic in the Science corpus, drawn from 289 papers.

Trusted voices in Code Generation & Program Synthesis

Ordered by the trust Code Generation & Program Synthesis's own network concentrates on each researcher, most first.

  1. Premkumar T. Devanbu — trusted by 188 researchers here
  2. Martin T. Vechev — trusted by 153 researchers here
  3. Veselin Raychev — trusted by 153 researchers here
  4. Eran Yahav — trusted by 83 researchers here
  5. Charles Sutton — trusted by 65 researchers here
  6. Earl T. Barr — trusted by 62 researchers here
  7. Miltiadis Allamanis — trusted by 60 researchers here
  8. Pavol Bielik — trusted by 62 researchers here
  9. Vincent J. Hellendoorn — trusted by 49 researchers here
  10. Sumit Gulwani — trusted by 52 researchers here
  11. Eibe Frank — trusted by 52 researchers here
  12. Ian H. Witten — trusted by 52 researchers here

Most-cited papers in Code Generation & Program Synthesis

Ordered by the recorded citation count from the source corpus; a citation is not an endorsement.

  1. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? (2023) — 3,028 citations
  2. Competition-level code generation with AlphaCode (2022) — 2,356 citations
  3. Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation (2023) — 1,966 citations
  4. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code (2024) — 1,848 citations
  5. DeepSeek-Coder: When the Large Language Model Meets Programming - The Rise of Code Intelligence (2024) — 1,786 citations
  6. Code as Policies: Language Model Programs for Embodied Control (2022) — 1,688 citations
  7. StarCoder: may the source be with you! (2023, Trans. Mach. Learn. Res.) — 1,263 citations
  8. Teaching Large Language Models to Self-Debug (2023) — 1,232 citations
  9. Measuring Coding Challenge Competence With APPS (2021) — 1,191 citations
  10. On the naturalness of software (2012) — 1,021 citations
  11. WizardCoder: Empowering Code Large Language Models with Evol-Instruct (2023) — 1,012 citations
  12. Unified Pre-training for Program Understanding and Generation (2021) — 938 citations
  13. Syntax-guided synthesis (2013) — 909 citations
  14. Combinatorial sketching for finite programs (2006) — 889 citations
  15. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines (2023) — 867 citations
  16. Convolutional Neural Networks over Tree Structures for Programming Language Processing (2014) — 843 citations
  17. ViperGPT: Visual Inference via Python Execution for Reasoning (2023) — 823 citations
  18. Deep Code Comment Generation (2018) — 791 citations
  19. Expectation vs. Experience: Evaluating the Usability of Code Generation Tools Powered by Large Language Models (2022) — 744 citations
  20. CodeT5+: Open Code Large Language Models for Code Understanding and Generation (2023) — 742 citations
  21. Code completion with statistical language models (2014) — 722 citations
  22. Visual Programming: Compositional visual reasoning without training (2022) — 718 citations
  23. A Novel Neural Source Code Representation Based on Abstract Syntax Tree (2019) — 715 citations
  24. The Impact of AI on Developer Productivity: Evidence from GitHub Copilot (2023) — 697 citations
  25. Program Synthesis (2017) — 695 citations
  26. Deep learning code fragments for code clone detection (2016) — 690 citations
  27. Deep Code Search (2018) — 687 citations
  28. SourcererCC: Scaling Code Clone Detection to Big-Code (2015) — 641 citations
  29. DeepCoder: Learning to Write Programs (2016) — 625 citations
  30. BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions (2024) — 597 citations
  31. Oracle-guided component-based program synthesis (2010) — 591 citations
  32. CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X (2023) — 573 citations
  33. Unsupervised Translation of Programming Languages (2020) — 573 citations
  34. DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation (2022) — 563 citations
  35. CodeT: Code Generation with Generated Tests (2022) — 560 citations
  36. An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation (2023) — 557 citations
  37. Language Models can Solve Computer Tasks (2023) — 522 citations
  38. RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation (2023) — 516 citations
  39. The Robots Are Coming: Exploring the Implications of OpenAI Codex on Introductory Programming (2022) — 509 citations
  40. GitHub Copilot AI pair programmer: Asset or Liability? (2022) — 509 citations
  41. Automatic Generation of Programming Exercises and Code Explanations Using Large Language Models (2022) — 502 citations
  42. Programming Is Hard - Or at Least It Used to Be: Educational Opportunities and Challenges of AI Code Generation (2022) — 464 citations
  43. A Transformer-based Approach for Source Code Summarization (2020) — 456 citations
  44. Special Issue on Program Generation, Optimization, and Platform Adaptation (2005) — 443 citations
  45. CoCoNuT: combining context-aware neural translation models using ensemble for program repair (2020) — 436 citations
  46. Suggesting accurate method and class names (2015) — 434 citations
  47. Improving Automatic Source Code Summarization via Deep Reinforcement Learning (2018) — 433 citations
  48. Parseweb: a programmer assistant for reusing open source code on the web (2007) — 432 citations
  49. CURE: Code-Aware Neural Machine Translation for Automatic Program Repair (2021) — 415 citations
  50. Learning natural coding conventions (2014) — 406 citations

Most active researchers

By papers in this topic: a volume measure, not trust.