📄 Paper accepted @ AAAI 2025!! 🎉
I am very happy to share that our paper that combines the strengths of both MaxSAT-based fault localisation and Large Language Models, via zero-shot learning, to enhance automated …
LLM-Driven Automated Program Repair Using MaxSAT-based Fault Localization @ Oxford
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 …
Automated Feedback for Introductory Programming Exercises
Delivering valuable and personalised feedback to students remains one of the greatest challenges in programming education, particularly in courses with large enrollments. Providing …
C-Pack of IPAs: A C90 Program Benchmark of Introductory Programming Assignments @ APR@ICSE 2024
In this talk I will present C-Pack-IPAs, a publicly available benchmark comprising student-program submissions for 25 distinct introductory programming assignments (IPAs).
C-Pack of IPAs: A C90 Program Benchmark of Introductory Programming Assignments
A C90 Program Benchmark of Introductory Programming Assignments (IPAs), that contains semantically correct, semantically incorrect, and syntactically incorrect programs and a test …
Graph Neural Networks For Mapping Variables Between Programs
In this work, we propose using graph neural networks (GNNs) to map the set of variables between two programs based on both programs' abstract syntax trees (ASTs). To demonstrate …
Learning Variable Mappings to Repair and Verify Programs @ CIIRC 2023
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
This paper presents MultIPAs, a program transformation tool that can augment IPAs benchmarks by (1) applying six syntactic mutations that conserve the program's semantics and (2) …
Project Proposal: Learning Variable Mappings to Repair Programs @ AITP 2022
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 …
Project Proposal: Learning Variable Mappings to Repair Programs
In this position paper, we propose to learn how to map the set of variables between different small imperative programs based on both programs' abstract syntax trees (ASTs) using …
Anonymized Abstract Syntax Trees and Invariant-Based Program Clustering @ CIIRC 2022
In this talk I propose a novel approach for program clustering that uses dynamically generated program invariants to cluster semantically equivalent programming assignments.