Reposted by @pinlab.bsky.socialFabio Galasso @galasso.bsky.social · 25/01/2025Our @pinlab.bsky.social has 2 #ICLR25 papers accepted! I'm proud of the strong team and of the fantastic collaborators. 041
Reposted by @pinlab.bsky.socialFabio Galasso @galasso.bsky.social · 25/01/2025"Compositional Entailment Learning for Hyperbolic Vision-Language Models" #ICLR25 With: Avik Pal, Max van Spengler, Guido Maria D'Amely di Melendugno, Alessandro Flaborea, and @pascalmettes.bsky.social Paper: arxiv.org/abs/2410.06912arxiv.orgCompositional Entailment Learning for Hyperbolic Vision-Language ModelsImage-text representation learning forms a cornerstone in vision-language models, where pairs of images and textual descriptions are contrastively aligned in a shared embedding space. Since visual and... 073
Reposted by @pinlab.bsky.socialFabio Galasso @galasso.bsky.social · 25/01/2025"Following the Human Thread in Social Navigation" #ICLR25 With: Luca Scofano, Alessio Sampieri, Tommaso Campari, Valentino Sacco, Indro Spinelli, @lambertoballan.bsky.social Paper: arxiv.org/abs/2404.11327arxiv.orgFollowing the Human Thread in Social NavigationThe success of collaboration between humans and robots in shared environments relies on the robot's real-time adaptation to human motion. Specifically, in Social Navigation, the agent should be close ... 031
pinlab.bsky.social @pinlab.bsky.social · 25/01/2025Hello World on @bsky.app ! This is the Perception and INtelligence lab (PINlab) at the Computer Science department of the Sapienza University of Rome. Our webpage: www.pinlab.orgpinlab.orgPINlabperception and intelligence lab 020
