Victor Lamas

Victor Lamas

Auto-generated profile, based on publicly available information

Victor Lamas

Universidade da Coruña

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 September 2024
Verified
Conference Paper
Open access
VLVictor Lamas
Victor Lamas
MLMiguel R. Luaces
Miguel R. Luaces
DGDaniel García González
Daniel García González
Nowadays, large language models (LLMs) are an extremely useful and fast tool to complement and help in many jobs and current problems. However, there are cases where a pretty specific vocabulary is used in which these models were not previously trained, leading to less satisfactory results. More specifically, these models are less effective when dealing with less-known or unpublished domain-specific languages (DSLs). Within this field, the automatic generation of code based on such languages, starting from natural language, would speed up the development times of any related project, as well as the understanding of such DSLs. Therefore, this paper presents a tool in which developers can perform what is known as semantic parsing. In other words, the developer can ask a pre-trained LLM to translate a natural language instruction into the vocabulary of the established DSL. Thus, by setting the DSL grammar as context (grammar prompting) and providing usage examples (few-shot learning), the LLM can quickly generate reliable domain-specific code, significantly improving the quality of life of the developers. A video demonstration of the tool is shown in the following link: https://zenodo.org/records/12610506.

4 February 2025
Verified
Conference Paper
Open access
VLVictor Lamas
Victor Lamas
MLMaría Isabel Limaylla Lunarejo
María Isabel Limaylla Lunarejo
MLMiguel R. Luaces
Miguel R. Luaces
DRDavid Romero-Organvidez
David Romero-Organvidez
JDJosé Ángel Galindo Duarte
José Ángel Galindo Duarte
DBDavid Benavides
David Benavides

15 July 2025 in Computers & Geosciences
Verified
Journal Article
Open access
VLVictor Lamas
Victor Lamas
ACAlejandro Cortiñas
Alejandro Cortiñas
MLMiguel R. Luaces
Miguel R. Luaces

31 October 2025 in Information and Software Technology
Verified
Journal Article
Open access
VLVictor Lamas
Victor Lamas
DGDaniel García González
Daniel García González
LSLuca Sala
Luca Sala
MLMiguel R. Luaces
Miguel R. Luaces

2 September 2024
Verified
Conference Paper
Open access
ACAlejandro Cortiñas
Alejandro Cortiñas
VLVictor Lamas
Victor Lamas
MLMiguel R. Luaces
Miguel R. Luaces
Geosciences have witnessed a revolution in data collection thanks to the Internet of Things (IoT), which has made it possible to monitor complex phenomena using sensor networks. However, developing web-centric, sensor-based, data warehousing information systems presents challenges because of their complexity and cost. This paper presents an intuitive low-code development system (called SensorPublisher), based on a software product line (SPL) and a domain-specific language (DSL), that speeds up the creation of data warehousing applications for geographic sensor data. SensorPublisher allows the geoscientist to define the sensor network, to generate a software product, and to deploy the product to a local or a remote server. Our tool seeks to encourage scientists to share the outcomes of their sensor data analysis projects with their communities by means of a simple, user-friendly and cost-effective approach. We showcase the system in different geoscientific domains, such as meteorological monitoring services, traffic data and air quality monitoring in urban areas, and marine area monitoring systems.

28 August 2023
Verified
Conference Paper
Open access
ACAlejandro Cortiñas
Alejandro Cortiñas
JKJacob Krüger
Jacob Krüger
VLVictor Lamas
Victor Lamas
MLMiguel R. Luaces
Miguel R. Luaces
OPOscar Pedreira
Oscar Pedreira