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 …
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 …
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.
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.
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 …
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 …
GitSEED: A Git-backed Automated Assessment Tool for Software Engineering and Programming Education
In this talk I will present GitSEED, a language-agnostic automated assessment tool designed for Programming Education and Software Engineering (SE) and backed by GitLab.
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 …
CFaults: Model-Based Diagnosis for Fault Localization in C with Multiple Test Cases
In this talk I will introduce a novel fault localization approach for C programs with multiple faults. CFaults leverages Model-Based Diagnosis (MBD) with multiple observations and …
C-Pack of IPAs: A C90 Program Benchmark of Introductory Programming Assignments
In this talk I will present C-Pack-IPAs, a publicly available benchmark comprising student-program submissions for 25 distinct introductory programming assignments (IPAs).
UpMax: User partitioning for MaxSAT
In this talk I will present a new framework called UpMax that decouples the partitioning procedure from the MaxSAT solving algorithms.
Learning Variable Mappings to Repair and Verify Programs
In this talk I will propose using graph neural networks (GNNs) to map the set of variables between two programs based on both programs' abstract syntax trees (ASTs).
MultIPAs: Applying Program Transformations to Introductory Programming Assignments for Data Augmentation
In this talk I will present MultIPAs, a program transformation tool that can augment IPAs benchmarks by (1) applying six syntactic mutations that conserve the program's semantics …
Project Proposal: Learning Variable Mappings to Repair Programs
In this talk I propose to learn how to map the set of variables between different small imperative programs based on both programs' abstract syntax trees (ASTs) using graph neural …
Anonymized Abstract Syntax Trees and Invariant-Based Program Clustering
In this talk I propose a novel approach for program clustering that uses dynamically generated program invariants to cluster semantically equivalent programming assignments.