Gabriele Venturato
@gabventurato.bsky.social
PhD Student in Neurosymbolic AI @ DTAI Lab, KU Leuven
🔬 In experiments, NeSy-MMs outperform existing neurosymbolic & deep models on both generative & discriminative tasks.
They generalize better to out-of-distribution settings and allow test-time constraint adaptation, making them robust & versatile.
They generalize better to out-of-distribution settings and allow test-time constraint adaptation, making them robust & versatile.
February 25, 2025 at 11:01 AM
🔬 In experiments, NeSy-MMs outperform existing neurosymbolic & deep models on both generative & discriminative tasks.
They generalize better to out-of-distribution settings and allow test-time constraint adaptation, making them robust & versatile.
They generalize better to out-of-distribution settings and allow test-time constraint adaptation, making them robust & versatile.
Markov models are great for sequential problems, but deep models struggle with constraints, and neurosymbolic AI doesn’t scale.
NeSy-MMs bridge this gap: a new class of differentiable models that provably satisfy relational logical constraints while scaling efficiently.
NeSy-MMs bridge this gap: a new class of differentiable models that provably satisfy relational logical constraints while scaling efficiently.
February 25, 2025 at 11:01 AM
Markov models are great for sequential problems, but deep models struggle with constraints, and neurosymbolic AI doesn’t scale.
NeSy-MMs bridge this gap: a new class of differentiable models that provably satisfy relational logical constraints while scaling efficiently.
NeSy-MMs bridge this gap: a new class of differentiable models that provably satisfy relational logical constraints while scaling efficiently.
🔥 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/...
🧵⬇️
📜 Paper: arxiv.org/pdf/2412.13023
💻 Code: github.com/ML-KULeuven/...
🧵⬇️
February 25, 2025 at 11:01 AM
🔥 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/...
🧵⬇️
📜 Paper: arxiv.org/pdf/2412.13023
💻 Code: github.com/ML-KULeuven/...
🧵⬇️