Luc De Raedt

Very proud of this work from my group, achieving really impressive speedups in neurosymbolic inference.

23.04.2025 11:07 — 👍 8    🔁 0    💬 1    📌 0

#ai #llms #reasoning #deepseek #3sat #iclr | Rishi Hazra 🚨 𝗡𝗲𝘄 𝗣𝗮𝗽𝗲𝗿 𝗔𝗹𝗲𝗿𝘁: 𝗛𝗮𝘃𝗲 𝗟𝗮𝗿𝗴𝗲 𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗠𝗼𝗱𝗲𝗹𝘀 𝗟𝗲𝗮𝗿𝗻𝗲𝗱 𝘁𝗼 𝗥𝗲𝗮𝘀𝗼𝗻? Despite their impressive performance on reasoning tasks, LLMs often succeed by fitting to patterns rather than understanding logic. Are...

What is reasoning and have LLMs learned it?

We answer these two questions in our new pre-print using the phase transition in random 3-SAT.
arxiv.org/abs/2504.039...

Together with @rishihazra95.bsky.social, @gabventurato.bsky.social and @lucderaedt.bsky.social

Here is also a longer thread:

09.04.2025 06:39 — 👍 10    🔁 4    💬 1    📌 0

Leuven.ai Creative AI Event

Leuven.AI proudly presents its first Creative AI event. Featuring keynotes on computational creativity, humor and poetry generation, and human-machine collaboration.
Check out the program: ai.kuleuven.be/events/creat... @leuvenai.bsky.social @kuleuvenuniversity.bsky.social

10.03.2025 16:10 — 👍 5    🔁 3    💬 0    📌 0

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...

We are hiring for PhD positions! I’m looking for people interested in exploring the intersection of learning and reasoning with applications to anomaly detection and sports. @dtai-kuleuven.bsky.social @wannesm.bsky.social

www.kuleuven.be/personeel/jo...

11.02.2025 19:39 — 👍 17    🔁 16    💬 1    📌 0

The Gradient of Algebraic Model Counting Algebraic model counting unifies many inference tasks on logic formulas by exploiting semirings. Rather than focusing on inference, we consider learning, especially in statistical-relational and neuro...

This was joint work with @lucderaedt.bsky.social.

27.02.2025 23:47 — 👍 6    🔁 1    💬 0    📌 0

We all know backpropagation can calculate gradients, but it can do much more than that!

Come to my #AAAI2025 oral tomorrow (11:45, Room 119B) to learn more.

27.02.2025 23:45 — 👍 27    🔁 10    💬 1    📌 0

🚀 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)

24.02.2025 12:26 — 👍 6    🔁 4    💬 1    📌 1

🔥 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/...

🧵⬇️

25.02.2025 11:01 — 👍 24    🔁 11    💬 1    📌 1