Danilo Danese

Exploring High Dimensional Low Sample Size data

[Danilo Danese @danilo_danese]

@iScienceLuvr @RiversHaveWings Thanks, this means a lot! Katherine's Colab notebooks were what first pulled me into generative modeling. That whole era of open, hackable diffusion code shaped how many of us got started. Building on HDiT feels like giving a bit back to a lineage I owe a lot to. Thank you.

[Danilo Danese @danilo_danese]

@iScienceLuvr @MattAttimonelli @TommasoDiNoia @MICCAI_Society Bonus: want to run this locally? This a native macOS app that lets you generate full brains and slice through them in real-time, no cloud. Grab it:
🍎 https://t.co/hwf561lSfR

[Danilo Danese @danilo_danese]

One full-size 3D brain. Every voxel, no lossy latent. Generated in 1s.
That's WaveDiT, 𝗲𝗮𝗿𝗹𝘆 𝗮𝗰𝗰𝗲𝗽𝘁 at #MICCAI2026 (top 9% of submissions). Now we can finally unveil it. 🧠
Try it live in your browser, no install:
🤗 https://t.co/FdjlMBTsOa
🌐 https://t.co/5bPpMoZfSZ

[Danilo Danese @danilo_danese]

@iScienceLuvr Open-source:
📄 https://t.co/SkdEUmD40c
💻 https://t.co/CBcIm1FbJM
Thanks to my coauthors Angela Lombardi, Giuseppe Fasano, @MattAttimonelli , @TommasoDiNoia at SisInfLab, and to @MICCAI_Society.
#MICCAI #MedicalImaging #GenerativeAI #FlowMatching #Wavelets #Neuroimaging #MRI

[Danilo Danese @danilo_danese]

Thanks to my coauthors Angela Lombardi, @MattAttimonelli , Giuseppe Fasano & @TommasoDiNoia at @sisinflab

#GenerativeAI #MedicalImaging #FlowMatching #Wavelets #Neuroimaging #MRI

[Danilo Danese @danilo_danese]

Meet FlowLet 🧠, a framework for synthesising entirely new 3D brain MRI volumes, just accepted at Medical Image Analysis (Elsevier).

Flow Matching in an invertible wavelet domain → new brains, in a few deterministic steps.

🌐 https://t.co/838fVd1muf
🧵

[Danilo Danese @danilo_danese]

So we rebuilt the evaluation: region-level, across 95 brain structures, and tested it on Brain Age Prediction.

It's all open-source:
📄 https://t.co/PLYhiBJnoR
💻 https://t.co/tPM0k7WPiT

[Aixin Sun @AixinSG]

3 papers in 5 days. Authors shall cite each other and consolidate all findings :) #recsys

[Claudio Pomo @scne]

Thrilled to announce our paper, "Do Recommender Systems Really Leverage Multimodal Content?", has been accepted at #CIKM2025! 🔥
We investigate if the gains in Multimodal RecSys come from true understanding or just bigger models. A deep dive into what really works.
(Thread 👇)

[Claudio Pomo @scne]

I want to extend a special and heartfelt thank you to my main co-authors, @MattAttimonelli and @danilo_danese. This paper is a direct result of their brilliant insights and deep commitment. I am incredibly proud of what we have accomplished together! 🙌

[Danilo Danese @danilo_danese]

@cyrilzakka @argmax @awnihannun Everything works well! Nice Job!

[Paolo Sorino @paolo_sorino]

🎉 Excited to announce our @IEEEAccess article! NeuroSense: EEG dataset for emotion recognition with low-cost devices.
🧠Available on GitHub 👉 https://t.co/0I2Mrz2DVS
📚 Paper 👉 https://t.co/9YEO93UxGc
#EEG #EmotionRecognition #AffectiveComputing

[Danilo Danese @danilo_danese]

@scne just presented their latest work at @ACMRecSys #GraphLearning session.
This work, co-authored by @dmalitesta @alberto_mancino @walteranelli @TommasoDiNoia Explores the relationship between topological datasets characteristics and GNN based recommender systems.

[Danilo Danese @danilo_danese]

The @ACMRecSys Session about Graph Learning has just started! Hosted by the one and only @sciueferrara

[Danilo Danese @danilo_danese]

Day 3 of @ACMRecSys #recsys2024 #bari
First session: Multi-task Learning