About
I am a PhD student in Computer Science at Heidelberg University, affiliated with the Institute of Computer Science. I am supervised by Prof. Dr. Artur Andrzejak .
My research lies at the intersection of Software Engineering and Artificial Intelligence, with a focus on trustworthy AI, interpretable machine learning, and large language models for code. Previously, I worked on efficient distributed deep learning and DNN offloading strategies for local–edge–cloud collaborative environments.
Research
My research focuses on developing efficient, reliable, and interpretable intelligent systems that bridge artificial intelligence and software engineering.
Research Interests:
- Trustworthy and Interpretable Large Language Models – Mechanistic interpretability, knowledge editing, and reliability of LLMs for code.
- AI for Software Engineering – Code generation, code translation, automated debugging, and intelligent developer tools.
- Explainable Artificial Intelligence (XAI) – Transparent and interpretable machine learning models.
- Distributed and Edge AI Systems – Efficient DNN offloading and collaborative intelligence across local–edge–cloud environments.
- Green and Efficient Machine Learning – Energy-aware AI systems for IoT and resource-constrained environments.
My work has been published in leading venues such as ICML, ICLR, IEEE Transactions on Services Computing, IEEE Transactions on Green Communications and Networking, and IEEE Consumer Electronics Magazine.
News
- 2026: Our paper on using SVD as an efficient interpretability method for transformers was accepted to ICML 2026 (Spotlight).
- 2026: Paper on precise and interpretable editing of code knowledge in large language models accepted to ICLR 2026.
- 2026: Paper on explainable AI based feature selection for energy-harvesting IoT networks accepted to International Symposium on Communication Systems, Networks and Digital Signal Processing.
- 2025: Work on identifying decisive code snippets for LLM-based code inference released as a preprint.
- 2024: Paper on interpretable error correction for code-to-code translation accepted to ICLR 2024.
- 2023: Survey on DNN migration in IoT systems published in IEEE Consumer Electronics Magazine.
- 2022: Two papers on DNN offloading and inference acceleration in local–edge–cloud collaborative environments published in IEEE Transactions on Services Computing and IEEE Transactions on Green Communications and Networking. One of the papers (IEEE TSC) was listed among the Top 50 Most Popular Articles.
Selected Publications
Miscellaneous
Outside of research, I enjoy reading, traveling, and exploring advances in artificial intelligence and technology.