AI researcher · Generative models for medical imaging

Danilo Danese

Generative AI for high-dimensional, low-sample-size domains.

Flow matching and diffusion for full-resolution 3D brain MRI.

Research

Scalable generative models for high-dimensional, low-sample-size domains.

Portrait of Danilo Danese

Danilo DanesePolitecnico di Bari · SisInfLab
Previously: Visiting researcher, University College London; Queen Square Analytics

Research on generative models and representation learning in high-dimensional, low-sample-size (HDLSS) domains, with 3D neuroimaging as the main setting: how to generate realistic volumetric data from few subjects, how to do so within modest compute, and how to verify that what a model generates or explains is reliable and not merely plausible.

The same questions extend to explainable AI for clinical prediction and to multimodal recommender systems, where supervision is sparse. Academic research is complemented by applied projects with industry partners and by the operation of multi-GPU and HPC infrastructure for large-scale model training.

Flow matchingDiffusionWavelets3D brain MRIBrain-age modelingExplainable AIMultimodal recommendation

Publications

2026

  1. JournalMedical Image Anal. 113 · 2026

    FlowLet: Conditional 3D brain MRI synthesis using wavelet flow matching

    Danilo Danese, Angela Lombardi, Matteo Attimonelli, Giuseppe Fasano, Tommaso Di Noia

  2. JournalExpert Syst. Appl. 307 · 2026

    Large-scale benchmarks for multimodal recommendation with Ducho

    Matteo Attimonelli, Danilo Danese, Angela Di Fazio, Daniele Malitesta, Claudio Pomo, Tommaso Di Noia

  3. JournalBrain Informatics · 2026

    STABLE-BAG: a stability-aware framework for SHAP-based brain age gap decomposition

    Angela Lombardi, Giuseppe Fasano, Mariangela Ciuffreda, Tommaso Colafiglio, Danilo Danese, Francesco Musicco, Eugenio Di Sciascio, Tommaso Di Noia

  4. ConferenceMICCAI · 2026Top 9% - Oral presentation

    WaveDiT: Distribution-Aware Wavelet Flow Matching for Efficient 3D Brain MRI Synthesis

    Danilo Danese, Angela Lombardi, Giuseppe Fasano, Matteo Attimonelli, Tommaso Di Noia

  5. ConferenceMICCAI (BraTS Local Synthesis, Oral) · 2026

    Now You Have My Healthy Attention: A U-DiT for Brain-MRI Inpainting

    Danilo Danese, Angela Lombardi, Tommaso Di Noia

  6. ConferenceMICCAI DS · 2026

    From Explanation Stability to Wavelet-Domain Generation: Trustworthy Brain Age Modeling from Structural MRI

    Danilo Danese

  7. PreprintCoRR · 2026

    Data Processing for Offline Evaluation in Recommender Systems: a Survey

    Alberto Carlo Maria Mancino, Angela Di Fazio, Danilo Danese, Matteo Attimonelli, Daniele Malitesta, Antonio Ferrara, Claudio Pomo, Tommaso Di Noia

  8. PreprintCoRR · 2026

    Grounding Free-Form Instructions for Fashion Complementary Image Generation

    Matteo Attimonelli, Claudio Pomo, Alessandro De Bellis, Danilo Danese, Dietmar Jannach, Tommaso Di Noia

  9. PreprintCoRR · 2026

    Who Are You Explaining To? A Multi-Agent System for Audience-Aware XAI Narratives

    Francesco Musicco, Danilo Danese, Giuseppe Fasano, Angela Lombardi, Alberto Carlo Maria Mancino, Tommaso Di Noia

2025

  1. ConferencexAI (4) · 2025

    Comparing XAI Explanations and Synthetic Data Augmentation Strategies in Neuroimaging AI

    Danilo Danese, Giuseppe Fasano, Angela Lombardi, Eugenio Di Sciascio, Tommaso Di Noia

  2. ConferenceCIKM · 2025

    Do Recommender Systems Really Leverage Multimodal Content? A Comprehensive Analysis on Multimodal Representations for Recommendation

    Claudio Pomo, Matteo Attimonelli, Danilo Danese, Fedelucio Narducci, Tommaso Di Noia

  3. ConferencexAI (Late-breaking Work, Demos, Doctoral Consortium) · 2025

    Explainable Evaluation of Emotion Recognition with Low-Cost EEG: Feature Engineering and Interpretability Insights

    Tommaso Colafiglio, Angela Lombardi, Paolo Sorino, Domenico Lofù, Danilo Danese, Fedelucio Narducci, Eugenio Di Sciascio, Tommaso Di Noia

2024

  1. JournalIEEE Access 12 · 2024

    NeuroSense: A Novel EEG Dataset Utilizing Low-Cost, Sparse Electrode Devices for Emotion Exploration

    Tommaso Colafiglio, Angela Lombardi, Paolo Sorino, Elvira Brattico, Domenico Lofù, Danilo Danese, Eugenio Di Sciascio, Tommaso Di Noia, Fedelucio Narducci

  2. ConferenceWWW (Companion Volume) · 2024

    Ducho 2.0: Towards a More Up-to-Date Unified Framework for the Extraction of Multimodal Features in Recommendation

    Matteo Attimonelli, Danilo Danese, Daniele Malitesta, Claudio Pomo, Giuseppe Gassi, Tommaso Di Noia

  3. ConferenceICWE Workshops · 2024

    Integrating eXplainable AI in Healthcare: A Web Application Framework for Advancing the One Health Paradigm

    Danilo Danese, Tommaso Di Noia, Angela Lombardi, Domenico Lofù, Fatemeh Nazary, Rodolfo Sardone, Paolo Sorino

  4. ConferencexAI (Late-breaking Work, Demos, Doctoral Consortium) · 2024

    Optimizing Synthetic Data from Scarcity: Towards Meaningful Data Generation in High-Dimensional Low-Sample Size Domains

    Danilo Danese

Experience

Industry, research and teaching

Experience

  1. Jul – Oct 2026
    Visiting researcher · MANIFOLD Lab, University College London (UCL)
    Generative super-resolution of portable 64 mT brain MRI to 3 T quality on real paired scans, with pre-registered tests that the recovered detail belongs to the subject and is not hallucinated.
  2. Apr – Jul 2026
    Imaging research scientist intern · Queen Square Analytics, London
    Developed and deployed deep-learning pipelines for longitudinal and cross-sectional brain-atrophy quantification, covering inference optimisation, automated quality control and cloud processing on AWS.
  3. Nov 2023 – Jan 2027
    Ph.D. student, generative AI · Politecnico di Bari
    Generative AI for 3D medical imaging (wavelet-domain flow matching, diffusion transformers, low-field super-resolution and healthy-tissue inpainting), brain-age augmentation, XAI attribution stability and multimodal representation learning. Thesis: Reliable Representation Learning under Constrained Supervision.
  4. May – Nov 2023
    Research fellow · SisInfLab, Politecnico di Bari
    Deep learning and time-series analysis of Sentinel-2 multispectral imagery (vegetation indices, remote sensing) to assess Xylella fastidiosa damage in olive groves.
  5. Sep 2022 – Apr 2023
    Research intern · SisInfLab, Politecnico di Bari
    Generative models for the furnishing industry with Natuzzi: 3D showroom synthesis and product-image generation.

Education

  1. 2023 – 2027
    Ph.D. in Electrical and Information Engineering
    Politecnico di Bari. Supervisors: Prof. Tommaso Di Noia and Prof. Angela Lombardi.
  2. 2019 – 2023
    M.Sc. in Computer Science Engineering
    Politecnico di Bari, Information Systems. Thesis: autoregressive transformer for text-to-3D generation of indoor scenes.
  3. 2013 – 2019
    B.Sc. in Computer Science and Automation Engineering
    Politecnico di Bari.

Projects

  1. 2025 – 2026
    CINECA ISCRA, HPC grants
    Two Class C projects, Italian SuperComputing Resource Allocation (GPU hours).
  2. 2024 – 2026
    MISTRAL, European research project
    AI toolkit for health-impact assessment and disability-related cost prediction; federated learning.
  3. 2023 – 2026
    OMIBREED and REACH XY, national research projects
    High-dimensional multi-omics data analysis and deep learning on olive trees infected by Xylella fastidiosa.
  4. 2023 – 2024
    Industry research
    Almaviva (2024): privacy-preserving federated learning across hospital sites. Natuzzi (2023): autoregressive transformer for 3D showroom synthesis; diffusion fine-tuning for product images.

Teaching

  1. 2024 – 2026
    Teaching assistant, Politecnico di Bari
    Deep Learning; Foundations of Machine Learning.
  2. 2024 – 2025
    Lecturer, ITS Academy Apulia Digital Maker; Spegea Business School
    Artificial Intelligence, from fundamentals to generative AI; Network and System Security.

Service

  1. Organisation
    Session Chair, xAI 2027 (Bari); Local Organization Chair, Brain Informatics 2025; Program Committee, ECAI 2025; Student Volunteer, ACM RecSys 2024 (Bari).
  2. Reviewer
    AAAI 2025; ACL Rolling Review 2026; Brain Informatics (journal, 2026); Brain Informatics 2025; CIKM 2025, 2026; CVPR 2026, 2027; Data Mining and Knowledge Discovery; ECAI 2025; ECIR 2025; ICLR 2026, 2027; MICCAI 2026; NeurIPS 2026; RecSys 2024; Scientific Reports; UMAP 2025; xAI 2024, 2025.

Other projects

Open source & tools

macOS App · AI

WaveDiT Studio

Native macOS app for age-conditioned 3D brain MRI synthesis running locally on Apple Silicon MPS.

macOS App

μStats

A lightweight, pixel-snapped system statistics monitor for the Mac menu bar.

VS Code Extension

AgentMux

Multi-agent tmux sidebar for VS Code connecting Claude, Codex, Antigravity, and Devin.

VS Code Themes

Color Sea

A vibrant collection of deep, high-contrast dark color themes tailored for VS Code.

The paper's main figure, enlarged