I am a PhD student in the Software Technology Group. My research interests include Geometric Deep Learning, Reinforcement Learning and developing efficient and robust AI for real world applications. Currently, I am working on developing code synthesis models that can generate secure and bug-free code.
Publications
2025
Integrating symbolic execution into the fine-tuning of code-generating LLMs.
Sakharova, Anand, Mezini,
NAACL.
10.18653/v1/2025.naacl-srw.27
2024
A critical study of what code-LLMs (do not) learn.
Anand, Verma, Narasimhan, Mezini,
ACL.
10.18653/v1/2024.findings-acl.939