Maliheh Izadi
Assistant Professor, Delft University of Technology, The Netherlands.

TU Delft, The Netherlands
m.izadi[AT]tudelft[DOT]nl
I am an assistant professor in the Faculty of Electrical Engineering, Mathematics, and Computer Science (EEMCS) at Delft University of Technology (TU Delft), the Netherlands.
At TU Delft, I direct the AI-enabled Software Engineering (AISE) research lab, where I supervise various PhD, MSc, and BSc students. I am also the academic manager for TU Delft’s tenth ICAI lab, AI4SE, consisted of 10 PhDs and various MSc/BSc students. Lastly, I am also part of the Software Engineering Research Group (SERG) at TU Delft.
My research is at the intersection of deep learning and source code analysis. I study, design, and develop learning-based models, specifically Large Language Models (#LLM) for source code, to automate software engineering and developer-related tasks such as understanding, generating, and documenting source code. My work has been published by several top venues in the software engineering community such as IEEE/ACM ICSE, FSE, TOSEM, EMSE, MSR, ICSME, SANER, and JSS.
I hold a PhD in Software Engineering from Sharif University of Technology (SUT). My PhD research focused on mining information from version control systems to facilitate software production-related tasks by automatically generating reports (such as release notes) for developers and software teams. I have a master’s degree in IT Engineering from SUT. My MSc research focused on improving evaluation methods of recommender systems which resulted in various publications.
If you are a researcher working on the intersection of NLP/ML and software engineering and you are interested in my work, feel free to reach out to propose/discuss possible collaborations. I have a postdoc position available on improving development tools and software engineering processes using #LLMs4code. Please apply through the portal for PhD vacancies or reach out to me through my email for the postdoc position. Make sure to introduce yourself, describe your research interests, and enclose a copy of your CV.
NOTE for prospective BSc and MSc students: If you are a TU Delft student who would like to work on the intersection of LLMs and SE in my lab, I have opportunities for a thesis, internships with industrial partners, and research projects. Feel free to contact me through my email to schedule a meeting and discuss potential opportunities.
Research Interests
- Language models for source code
- Evaluations and benchmarking
- Autonmous agents
- Intelligent development tools
- Developer productivity
News
Apr 02, 2025 | New paper on Benchmarking Harmfulness in LLM4Code accepted at the ACM FSE 2025 (Main Track). |
---|---|
Mar 14, 2025 | New paper on Predictive Sequencing of States accepted at FSE 2025 (New Ideas and Vision Track). |
Mar 10, 2025 | New paper on Multi-agent Onboarding Assistant accepted at FSE 2025 (Demo Track). |
Selected publications
- Code Red! On the Harmfulness of Applying Off-the-shelf Large Language Models to Programming TasksIn ACM International Conference on the Foundations of Software Engineering (FSE), main track, 2025
- Leveraging large language models for enhancing the understandability of generated unit testsIn IEEE/ACM 47th International Conference on Software Engineering (ICSE), main track, 2025
- HyperSeq: A Hyper-Adaptive Representation for Predictive Sequencing of StatesIn ACM International Conference on the Foundations of Software Engineering (FSE), 2025
-
-
-
- A Transformer-based Approach for Smart Invocation of Automatic Code CompletionIn The 1st ACM International Conference on AI-powered Software (AIware), 2024
- Language models for code completion: A practical evaluationIn IEEE/ACM 46th International Conference on Software Engineering (ICSE), 2024
- Traces of Memorisation in Large Language Models for CodeIn IEEE/ACM 46th International Conference on Software Engineering (ICSE), 2024
-