José Antonio Hernández López

Department of Computer Science and Systems
University of Murcia
Murcia, Spain
I am José Antonio Hernández López, Assistant Professor in the Department of Computer Science and Systems at the University of Murcia. Previously, I was a WASP postdoctoral researcher at Linköping University (Sweden), under the supervision of Dániel Varró. During my PhD, I held an FPU scholarship funded by the University of Murcia, under the supervision of Jesús Sánchez Cuadrado. My research focuses on the use of artificial intelligence and natural language processing techniques (specially large language models, LLMs) to improve software engineering processes (e.g., code generation, bug detection, testing, etc.).
Throughout my research career, I have published in the top conferences and journals in software engineering: ICSE, FSE, ASE, IEEE TSE, MODELS, among others. I have also received best paper awards in several editions of the MODELS conference.
Finally, it is worth mentioning that I have actively collaborated with industry throughout my career. During my PhD, I completed an internship at InQuery Labs (a company recently acquired by PTC), where I worked on the development of a transpiler. While working in Sweden, I was affiliated with and participated in several projects at Software Center, a consortium of companies (e.g., Volvo, Bosch, Saab, etc.) and public institutions in the context of Generative AI in Simulation-Based Test Environments. During that period, I also collaborated with Ericsson on the use of LLMs to generate unit tests. Currently, I have a technology transfer contract with the company accessmedia to make media content more accessible through the use of LLMs.
selected publications
- SoSyMModelSet: a dataset for machine learning in model-driven engineeringSoftware and Systems Modeling, 2022
- TSEGenerating structurally realistic models with deep autoregressive networksIEEE Transactions on Software Engineering, 2022
- ASEAST-Probe: Recovering abstract syntax trees from hidden representations of pre-trained language modelsIn Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering, 2022
- TSEOn inter-dataset code duplication and data leakage in large language modelsIEEE Transactions on Software Engineering, 2024
- FSEAn Adaptive Language-Agnostic Pruning Method for Greener Language Models for CodeProceedings of the ACM on Software Engineering, 2025
- ICSEThe Power of Types: Exploring the Impact of Type Checking on Neural Bug Detection in Dynamically Typed Languages2024