iiinova — where your digital self keeps evolving

Giuseppe Marra

@giuseppemarra.bsky.social

375 followers 482 following 1 posts

Assistant Professor in Artificial Intelligence KU Leuven Belgium

Posts Replies Media

Reposted by Giuseppe Marra

Gabriele Venturato @gabventurato.bsky.social · 25/02/2025

🔥 Can AI reason over time while following logical rules in relational domains? We will present Relational Neurosymbolic Markov Models (NeSy-MMs) next week at #AAAI2025! 🎉 📜 Paper: arxiv.org/pdf/2412.13023 💻 Code: github.com/ML-KULeuven/... 🧵⬇️

12511

Reposted by Giuseppe Marra

David Debot @daviddebot.bsky.social · 24/02/2025

🚀 Do you care about safe AI? Do you want RL agents that are both smart & trustworthy? At #AAAI2025, we present our demo for neurosymbolic RL—combining deep learning with probabilistic logic shields for safer, interpretable AI in complex environments. 🏰🔥 🧵👇 (1/8)

184

Giuseppe Marra @giuseppemarra.bsky.social · 17/02/2025

We’re hiring multiple PhD students at KU Leuven, Belgium, including several in neurosymbolic AI with myself and Luc De Raedt. If you’re passionate about topics like the intersection of deep learning, probabilistic logic and interpretable deep learning, apply soon! www.kuleuven.be/personeel/jo...

kuleuven.be

Several PhD Positions in Artificial Intelligence at Computer Science KU Leuven

All positions are in the Machine Learning subgroup of the Section for Declarative Languages and Artificial Intelligence (DTAI), which is part of the Department of Computer Science at KU Leuven. The DT...

031

Reposted by Giuseppe Marra

David Debot @daviddebot.bsky.social · 04/12/2024

🚨 Interpretable AI often means sacrificing accuracy—but what if we could have both? Most interpretable AI models, like Concept Bottleneck Models, force us to trade accuracy for interpretability. But not anymore, due to Concept-Based Memory Reasoner (CMR)! #NeurIPS2024 (1/7)

2247