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

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!

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🧵

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

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

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

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