AI4SE

From Logic to Learning: Rethinking Programming for the AI Era featured image

From Logic to Learning: Rethinking Programming for the AI Era

In this talk, I will present approaches that leverage the precision of formal logic and the adaptability of learning-based models to enable intelligent code generation, automated …

avatar
Pedro Orvalho
Read more
Artificial Intelligence for Reliable Code featured image

Artificial Intelligence for Reliable Code

Understanding the reasoning and robustness of AI systems, such as Large Language Models (LLMs), is critical for ensuring their reliable use in programming tasks. While recent …

avatar
Pedro Orvalho
Read more
Counterexample Guided Program Repair Using Large Language Models and MaxSAT-based Fault Localization featured image

Counterexample Guided Program Repair Using Large Language Models and MaxSAT-based Fault Localization

In this talk I will present a hybrid method to automated repair of C code, using Maximum Satisfiability (MaxSAT)-based fault localization, CFaults, to localize bugs and LLMs to …

avatar
Pedro Orvalho
Read more
Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations? featured image

Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations?

In this talk, I will present our evaluation on whether state-of-the-art LLMs with up to 8B parameters can reason about Python programs or are simply guessing.

avatar
Pedro Orvalho
Read more
MENTOR: Automated Feedback for Introductory Programming Exercises featured image

MENTOR: Automated Feedback for Introductory Programming Exercises

In my talk, I will present MENTOR, a semantic automated program repair (APR) framework designed to provide Automated Feedback for Introductory Programming Exercises.

avatar
Pedro Orvalho
Read more
MENTOR: Feedback Automático para Exercícios Introdutórios de Programação (Portuguese) featured image

MENTOR: Feedback Automático para Exercícios Introdutórios de Programação (Portuguese)

Nesta palestra, irei apresentar o sistema MENTOR, uma ferramenta de reparação automática de programas orientada para fornecer feedback automatizado para exercícios introdutórios de …

avatar
Pedro Orvalho
Read more
🏆 Honored to Receive the Vencer o Adamastor (VoA) Award 2025!! 🏆 featured image

🏆 Honored to Receive the Vencer o Adamastor (VoA) Award 2025!! 🏆

I am thrilled to share that I was the recipient of the Vencer o Adamastor 2025 prize, which acknowledges innovative contributions by young scientists in Portugal. 🎉 🎉

avatar
Pedro Orvalho
Read more
Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization featured image

Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization

In this talk I will present our novel approach that combines the strengths of both FM-based fault localization and LLMs, via zero-shot learning, to enhance Automated Program …

avatar
Pedro Orvalho
Read more
LLM-Driven Automated Program Repair Using MaxSAT-based Fault Localization featured image

LLM-Driven Automated Program Repair Using MaxSAT-based Fault Localization

In this talk I will present a hybrid method to automated repair of C code, using Maximum Satisfiability (MaxSAT)-based fault localization, CFaults, to localize bugs and LLMs to …

avatar
Pedro Orvalho
Read more