7 citations · 8 across the 7 of their papers we have counts for
5 papers · 1 filter
Smaller Models, Unexpected Costs: Trade-offs in LLM Quantization for Automated Program Repair
Fernando Vallecillos-Ruiz, Giordano d'Aloisio, Max Hort +3
Large Language Models (LLMs) are powerful tools and have been increasingly adopted for complex software engineering tasks. As the number of parameters increases, results can often…
How Do Generative Models Draw a Software Engineer? A Case Study on Stable Diffusion Bias
Tosin Fadahunsi, Giordano d'Aloisio, Antinisca Di Marco +1
Generative models are nowadays widely used to generate graphical content used for multiple purposes, e.g. web, art, advertisement. However, it has been shown that the images genera…
On the Compression of Language Models for Code: An Empirical Study on CodeBERT
Giordano d'Aloisio, Luca Traini, Federica Sarro +1
Language models have proven successful across a wide range of software engineering tasks, but their significant computational costs often hinder their practical adoption. To addres…
Architectural Support for Software Performance in Continuous Software Engineering: A Systematic Mapping Study
Romina Eramo, Michele Tucci, Daniele Di Pompeo +3
The continuous software engineering paradigm is gaining popularity in modern development practices, where the interleaving of design and runtime activities is induced by the contin…
Architecture Design for Human-Driven Systems
Mahyar T. Moghaddam, Moamin B. Abughazala, Vittorio Cortellessa +4
This paper highlights humans' social and mobility behaviors' role in the continuous engineering of sustainable socio-technical systems. Our approach relates the humans' characteris…