-
SOLVE-Med: Specialized Orchestration for Leading Vertical Experts across Medical Specialties
Paper • 2511.03542 • Published -
IMB: An Italian Medical Benchmark for Question Answering
Paper • 2510.18468 • Published -
praiselab-picuslab/Llama-3.2-1B-Instruct-Cardiologia
Question Answering • 1B • Updated -
praiselab-picuslab/Llama-3.2-1B-Instruct-Dermatologia
Question Answering • 1B • Updated
PRAISELab@PICUSLab
AI & ML interests
Artificial Intelligence, Generative AI, Large Language Models, Biomedical NLP, Medical Question Answering, Generative Agent-based Modeling, Recommender System, Social Networks
Recent Activity
Hi 👋, we are the PRAISE Research Group
Predictive Analytics for Understanding Big Multimedia Data @ University of Naples Federico II
🧠 About Us
The PRAISE (PRedictive AnalytIcs for underStanding big multimEdia data) research group is part of the PICUS Lab at the Department of Electrical Engineering and Information Technologies (DIETI), University of Naples Federico II, Italy.
We are a team of researchers with a strong background in AI, multimodal data understanding, and predictive analytics across multiple domains including eHealth, Social Network Analysis, and Multimedia Data Analysis.
Our goal is to develop intelligent systems that can understand, predict, and interact with complex multimedia information—especially focusing on language, vision, and their integration.
🔬 Research Topics
Multimodal AI for Healthcare
- Multilingual and multimodal language models
- Diagnostic and therapeutic AI assistance
- Automatic EHR generation from speech and unstructured text (Italian)
- Medical image understanding (CT, MRI, X-ray, etc.)
Social Network Modeling & Simulation
- Generative Agent-Based Frameworks
- LLM-driven simulation of social phenomena: stance change, information diffusion
- Tools for crowd fact-checking, fake news and harmful content detection
Lie Detection from Multimedia Streams
- AI for behavioral analysis and deception detection
- Collaborative project with US-based Courtscribes Company
Big Scholarly Data Analytics
- Automated knowledge extraction and semantic enrichment
- Development of analytics platforms for scientific literature
🤖 Models
We are currently developing fine-tuned multimodal language models for the Italian medical domain, in collaboration with national (e.g., Accenture, Almaviva) and international partners (e.g., King’s College London).
Our models integrate textual and visual medical data to support clinical tasks in real-world applications.
📄 View our papers
📫 Contact Us
- 🌐 GitHub Page: PRAISELab@PICUSLab
Connect with us:
⭐ Members
|
Gian Marco Orlando |
Diego Russo |
Marco Perillo |
Giuseppe Riccio |
Antonio Romano |
Mariano Barone |
Francesco Di Serio |
-
SOLVE-Med: Specialized Orchestration for Leading Vertical Experts across Medical Specialties
Paper • 2511.03542 • Published -
IMB: An Italian Medical Benchmark for Question Answering
Paper • 2510.18468 • Published -
praiselab-picuslab/Llama-3.2-1B-Instruct-Cardiologia
Question Answering • 1B • Updated -
praiselab-picuslab/Llama-3.2-1B-Instruct-Dermatologia
Question Answering • 1B • Updated