Doctoral Consortium
Date: 19 June 2026
Room: CB30A
Chairs: Valerio Guarrasi (Università Campus Bio-Medico di Roma)
Description
The Doctoral Consortium is dedicated to PhD students conducting research in Artificial Intelligence and provides a setting for presenting and discussing ongoing work. It is part of the Italian National PhD Programme in AI and supports interaction among students working on emerging research topics. The Consortium represents a moment for scientific exchange and community building within Ital-IA 2026.
Detailed Programme
Times show each contribution's presentation slot. An asterisk marks the presenting author when provided in the programme data.
| Time | ID | Contribution |
|---|---|---|
| 11:30-13:30 | - | NVIDIA workshop on Rapid Application Development with LLMs and a Medical Use-case |
| 13:30-14:30 | Lunch | |
| 14:30-14:40 | #46 | Machine Unlearning in Large Language Models: Challenges and Research Directions |
| 14:40-14:50 | #15 | Towards Reliable Large Language Models: Probing, Steering, and Mitigating Hallucinations |
| 14:50-15:00 | #40 | Trustworthy Language Models for Health Applications |
| 15:00-15:10 | #50 | Genomic Language Models for Biomedicine: Current Results in Virology and Future Directions |
| 15:10-15:20 | #70 | Multimodal AI-Based Integration of Handwriting for Cognitive Decline Detection: A survey |
| 15:20-15:30 | #72 | A Tablet-Based Protocol for Multimodal Cognitive Assessment |
| 15:30-15:40 | #97 | GAN-based synthesis of Diffusion Gradient Directions in Diffusion Tensor Imaging |
| 15:40-15:50 | #24 | MedSecure: Adaptive Adversarial Attacks for Medical Imaging |
| 15:50-16:00 | #32 | A Conceptual Taxonomy of Adversarial Machine Learning: Attacks and Defences |
| 16:00-16:10 | #28 | Understanding Robust Representation Learning and Data Utility under Low-Resource Conditions |
| 16:10-16:20 | #115 | Leveraging Adaptive Data-Driven Granulation for Situation-Aware ADHD Recognition |
| 16:20-16:30 | #23 | NeuroFuse-MS: From Images to Outcomes with a Knowledge-Aware Multimodal Approach to Multiple Sclerosis Progression Prediction |
| 16:30-16:40 | #12 | Hybrid Quantum-Classical Networks via Knowledge Distillation |
| 16:40-16:50 | #64 | Trustworthy Graph Neural Networks through SMT Verification |
| 16:50-17:00 | #130 | Transformer-based HBO-fNIRS-T model for binary motor task classification |
| 17:00-17:10 | #103 | LAPPATO_MCB: Literature-Aware Pipeline Partner for Adaptive Transplant Optimization |