Authors:Diogo Glória-Silva, João Cardeira, Manuel Letras da Luz, Afonso Simplício, Gonçalo Vinagre, Diogo Tavares, Rafael Ferreira, Inês Calvo, Inês Vieira, David Semedo, João Magalhães
Abstract:Large Vision and Language Models (LVLMs) have advanced rapidly, yet European Portuguese (pt-PT) remains systematically underserved by existing open-source multimodal models, which either conflate it with Brazilian Portuguese or severely under-represent it in their training data mixes. We introduce AMALIA-VL, the first open-source instruction-tuned LVLM built natively for pt-PT, pairing a high-resolution vision encoder with dynamic image tiling and a fully open pt-PT-optimized language model via a learned connector. We contribute with a purposefully designed three-stage training process - vision-language alignment, general visual instruction tuning, and preference optimization - together with a pt-PT-centric multimodal data mix combining curated and translated public datasets with novel datasets that address the near-total absence of European Portuguese multimodal resources. Our evaluation shows that AMALIA-VL establishes a strong baseline for open-source pt-PT this http URL will release model weights, training data, and construction pipelines along with machine-translated pt-PT evaluation benchmarks to help democratize pt-PT LVLM development.
From: Diogo Glória-Silva [view email]
[v1]
Wed, 17 Jun 2026 14:11:41 UTC (3,562 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。