4 papers
Hands-off Image Editing: Language-guided Editing without any Task-specific Labeling, Masking or even Training
Rodrigo Santos, António Branco, João Silva +1
Instruction-guided image editing consists in taking an image and an instruction and deliverring that image altered according to that instruction. State-of-the-art approaches to thi…
Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family
LuÃs Gomes, António Branco, João Silva +2
Sentence encoder encode the semantics of their input, enabling key downstream applications such as classification, clustering, or retrieval. In this paper, we present Serafim PT*,…
Meta-prompting Optimized Retrieval-augmented Generation
João Rodrigues, António Branco
Retrieval-augmented generation resorts to content retrieved from external sources in order to leverage the performance of large language models in downstream tasks. The excessive v…
PORTULAN ExtraGLUE Datasets and Models: Kick-starting a Benchmark for the Neural Processing of Portuguese
Tomás Osório, Bernardo Leite, Henrique Lopes Cardoso +4
Leveraging research on the neural modelling of Portuguese, we contribute a collection of datasets for an array of language processing tasks and a corresponding collection of fine-t…