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

CodeSSM: Towards state space models for code understanding.
Verma, Anand, Mezini, EMNLP. 10.18653/v1/2025.emnlp-main.1735

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