I am a doctoral researcher in the Software Technology Group. My research interests include Reinforcement Learning, Multi-agent Systems, Robust and explainable AI, and State Space based models. Within my work, I plan to improve code intelligence models (code-LLMs) by designing robust and explainable architectures for code models which can help in handling short as well as long range dependencies.

Shweta Verma
Doctoral Researcher
| shweta.verma@tu-... | |
| Phone | +49 6151 16-21363 |
| Office | S2|02 A222 Hochschulstr. 10 64289 Darmstadt |
2025
CodeSSM: Towards state space models for code understanding.
Verma, Anand, Mezini,
EMNLP.
10.18653/v1/2025.emnlp-main.1735
2024
A critical study of what code-LLMs (do not) learn.
Anand, Verma, Narasimhan, Mezini,
ACL.
10.18653/v1/2024.findings-acl.939