iiinova — where your digital self keeps evolving

Eleonora Grassucci

@eleonoragrassucci.bsky.social

21 followers 11 following 9 posts

Assistant Professor @Sapienza, Rome. Generative AI, Multimodal Learning, Generative Semantic Communication

Posts Replies Media

Eleonora Grassucci @eleonoragrassucci.bsky.social · 23/01/2025

GRAM is going to #ICLR2025! More on this soon, and see y'all in Singapore! #multimodal #contrastive #learning

020

Eleonora Grassucci @eleonoragrassucci.bsky.social · 20/12/2024

Super interesting work on #GenAI #Video2Audio with impressive results from my friends @riccardofosco.bsky.social @Christian Marinoni together with @emilianpos.bsky.social @mcomunita.bsky.social Luca Cosmo, Joshua Reiss and @dacom.bsky.social ! 👇 Go check it out!

041

Eleonora Grassucci @eleonoragrassucci.bsky.social · 18/12/2024

No more pairwise cosine similarity for multimodal learning we can directly go up to n modalities!🔴 👉GRAM can align *from 2 to n modalities* altogether in a joint fashion by gaining alignment insights from the volume of the parallelotope spanned by the modality vectors. 1/n🧵

110

Reposted by Eleonora Grassucci

arxiv cs.CV @arxiv-cs-cv.bsky.social · 27/03/2024

Eleonora Lopez, Eleonora Grassucci, Debora Capriotti, Danilo Comminiello Towards Explaining Hypercomplex Neural Networks arxiv.org/abs/2403.17929

001

Reposted by Eleonora Grassucci

arxiv cs.IT @arxiv-cs-it.bsky.social · 26/03/2024

Jinho Choi, Jihong Park, Eleonora Grassucci, Danilo Comminiello Semantic Communication Challenges: Understanding Dos and Avoiding Don'ts arxiv.org/abs/2403.15649

001

Reposted by Eleonora Grassucci

arxiv cs.CV @arxiv-cs-cv.bsky.social · 05/03/2024

Eleonora Lopez, Eleonora Grassucci, Martina Valleriani, Danilo Comminiello Multi-View Hypercomplex Learning for Breast Cancer Screening arxiv.org/abs/2204.05798

001

Reposted by Eleonora Grassucci

arxiv cs.CV @arxiv-cs-cv.bsky.social · 17/05/2024

Giordano Cicchetti, Eleonora Grassucci, Jihong Park, Jinho Choi, Sergio Barbarossa, Danilo Comminiello Language-Oriented Semantic Latent Representation for Image Transmission arxiv.org/abs/2405.09976

001