CV Lattes
ORCID
Google Scholar Citations
Universidade Estadual de Campinas (UNICAMP). Instituto de Computação (IC) (Institutional affiliation from the last research proposal) Birthplace: Brazil
Gabriel Santos is a Ph.D. candidate in Computer Science at the Institute of Computing, University of Campinas (Unicamp), where he earned his bachelor's degree, graduating as an outstanding student in Computer Science in 2021. In 2020, he received the Scientific Merit Award at the XXVIII UNICAMP Scientific Initiation Congress for his #PraCegoVer project. He is a member of the Natural Language Processing research group at the Artificial Intelligence and Cognitive Architectures Hub (H.IAAC). His research focuses on natural language processing and multimodal learning. In his doctoral work, he investigates efficient approaches to specialize vision-language models (VLMs) for the Brazilian context, which includes developing low-cost strategies for training VLMs in Portuguese and addressing cultural challenges in NLP. (Source: Lattes Curriculum)
| News published in Agência FAPESP Newsletter about the researcher |
| More itemsLess items |
| TITULO |
| Articles published in other media outlets ( ): |
| More itemsLess items |
| VEICULO: TITULO (DATA) |
| VEICULO: TITULO (DATA) |
The Natural Language Processing (NLP) field has undergone significant transformations, primarily marked by Large Language Models (LLMs). However, an inherent limitation of these models is the incapacity of processing data modalities beyond text. To tackle this, in recent years, different Multimodal Large Language Models (MLLMs) have been proposed to extend the LLMs to other modalities fur…
The Internet has become increasingly accessible, reaching a wide range of audiences. However, little progress has been made in the inclusion of people with disabilities, and the scenery is even worse when it comes specifically to visual impairment, as much of the published content is purely visual (e.g., photos, advertising images). Every day, the visually impaired suffer from the violati…
Ontologies formally represent domain concepts and their relationships to express data semantics. Ontology mappings are relevant to integrate heterogeneous data sources and to facilitate data exchange between systems. The automatic creation of mappings requires a matching procedure to identify related semantic concepts. The automated cross-lingual matching is still an open research challen…
Natural Language Processing (NLP) has undergone significant transformations, primarily marked by Large Language Models (LLMs). However, an inherent limitation of these models is the incapacity of processing data modalities beyond text. To tackle this, in recent years, different Multimodal LLMs have been proposed to extend the LLMs to other modalities. Despite the advances, existing litera…
| 3 / 3 | Completed scholarships in Brazil |
| 1 / 1 | Ongoing scholarships abroad |
| 4 / 4 | All Scholarships |
| Associated processes | |