Pablo Miralles
Hi, I’m Pablo! I’m a PhD student in Artificial Intelligence supervised by Alejandro Martín and Javier Huertas-Tato. Before this, I completed an MSc in Machine Learning and Big Data at the Technical University of Madrid, and a double BSc in Mathematics and Computer Science at the University of Murcia.
My research focuses on applying deep learning to natural language processing (NLP), with work spanning AI-generated text detection, authorship attribution, natural language inference (NLI), and efficient Transformer architectures. The overarching theme is the study of inductive biases in models, the capabilities adquired from pre-training, and how to apply or post-train these models for downstream tasks in a way that generalizes robustly especially when data are scarce or affected by spurious correlations.
Feel free to check out my publications, occasional posts, or reach out if you’re interested in collaborating!
News
- 🧠 Our paper On the locality bias and results in the Long Range Arena got accepted at IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI)! 🎉
- 🇬🇧 Started my research visit at Queen Mary University of London (QMUL), working with Arkaitz Zubiaga! 🎓
- 📄 Our paper Evaluating the scalability and adversarial generalization of GRPO-trained NLI models got accepted at Knowledge-Based Systems! 🥳
- 🎉 Our paper One-shot Style Transfer LLM log-probabilities for Authorship Attribution and Verification got accepted at Findings of EMNLP 2026! 🚀