Yinlin Deng

I am a fourth-year Ph.D. candidate in Computer Science at University of Illinois at Urbana-Champaign. As a member of the PL/FM/SE Group, I am being advised by Prof. Lingming Zhang. I'm generously supported by a Two Sigma PhD Fellowship.
Previously, I obtained my B.S. in Computer Science from Turing Class, Peking University.

Email / CV / Github

Publications

Agentless: Demystifying LLM-based Software Engineering Agents
Chunqiu Steven Xia*, Yinlin Deng*, Soren Dunn, Lingming Zhang
FSE, 2025 | paper | code |

Can LLMs Implicitly Learn Numeric Parameter Constraints in Data Science APIs?
Yinlin Deng, Chunqiu Steven Xia, Zhezhen Cao, Meiziniu Li, Lingming Zhang
NeurIPS, 2024 | paper |

Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM
Chunqiu Steven Xia*, Yinlin Deng*, Lingming Zhang
COLM, 2024 Oral spotlights | paper | webpage | code |

NExT: Teaching Large Language Models to Reason about Code Execution The Forty-first International Conference on Machine Learning
Ansong Ni, Miltiadis Allamanis, Arman Cohan, Yinlin Deng, Kensen Shi, Charles Sutton, Pengcheng Yin
ICML, 2024 | paper |

ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis In The Twelfth International Conference on Learning Representations
Kensen Shi, Joey Hong, Yinlin Deng, Pengcheng Yin, Manzil Zaheer, Charles Sutton
ICLR, 2024 Oral | paper |

White-box Compiler Fuzzing Empowered by Large Language Models
Chenyuan Yang, Yinlin Deng, Runyu Lu, Jiayi Yao, Jiawei Liu, Reyhaneh Jabbarvand, Lingming Zhang
arXiv, 2023 | paper |

Large Language Models are Edge-Case Generators: Crafting Unusual Programs for Fuzzing Deep Learning Libraries In 46th International Conference on Software Engineering
Yinlin Deng, Chunqiu Steven Xia, Chenyuan Yang, Shizhuo Dylan Zhang, Shujing Yang, Lingming Zhang
ICSE, 2024 | paper |

Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models In 32nd International Symposium on Software Testing and Analysis
Yinlin Deng, Chunqiu Steven Xia, Haoran Peng, Chenyuan Yang, Lingming Zhang
ISSTA, 2023 | paper | code |

Fuzzing Automatic Differentiation in Deep-Learning Libraries In 45th International Conference on Software Engineering
Chenyuan Yang, Yinlin Deng, Jiayi Yao, Yuxing Tu, Hanchi Li, Lingming Zhang
ICSE, 2023 | paper | code |

Fuzzing Deep-Learning Libraries via Automated Relational API Inference In 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering
Yinlin Deng*, Chenyuan Yang*, Anjiang Wei, Lingming Zhang
ESEC/FSE, 2022 | paper | code |

Free Lunch for Testing: Fuzzing Deep-Learning Libraries from Open Source In 44th International Conference on Software Engineering
Anjiang Wei, Yinlin Deng, Chenyuan Yang, Lingming Zhang
ICSE, 2022 | paper | code |

Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation In Proceedings of the ACM on Programming Languages 6
Jiawei Liu, Yuxiang Wei, Sen Yang, Yinlin Deng, Lingming Zhang
OOPSLA, 2022 | paper | code | artifact |

Template taken from Jon Barron.
Last updated: April 12, 2023