Models and dataset for "Parameter-Efficient Multimodal Instruction Tuning for Romanian Vision–Language Models"
AI & ML interests
Natural Language Processing, Multimodal AI, Information Retrieval, Legal AI, Romanian, Large Language Models
Recent Activity
View all activity
Models and dataset for "Parameter-Efficient Multimodal Instruction Tuning for Romanian Vision–Language Models"
We introduce a novel multimodal dataset comprising Romanian driving test questions, text-based and image-based, alongside annotated legal references
We introduce the first sentence-level dataset for Romanian satire detection for news articles, called SeLeRoSa.
This collection provides the fine-tuned models used in "Investigating LLMs for Complex Word Identification in Multilingual and Multidomain Setups"