Sign in

Luc De Raedt

@lucderaedt.bsky.social
503 followers 184 following 2 posts

Professor of AI, DTAI, KU Leuven; Wallenberg Guestprofessor AASS, Örebro University; Director Leuven.AI, AAAI and EurAI Fellow, Former PC Chair IJCAI, ICML, ECAI and ECMLPKDD, ERC AdG 2015 and 2023

PostsRepliesMedia
Reposted by Luc De Raedt
Rik Adriaensen @rik-a3.bsky.social · 22/01/2026
📌 Tomorrow we present a poster on ProbLog4Fairness: A Neurosymbolic Approach to Modeling and Mitigating Bias at #AAAI (Machine Learning 2, poster 1233, 12pm - 2 pm).
142
Luc De Raedt @lucderaedt.bsky.social · 05/12/2025
Great work from our student Jaron Maene and Efthymia Tsamoura !
000
Reposted by Luc De Raedt
mantas-simkus.bsky.social @mantas-simkus.bsky.social · 07/11/2025
The 4th European Summer School on Artificial Intelligence (ESSAI 2026) will take place 6–10 July 2026 in Vienna, Austria. We invite leading AI researchers to submit course proposals for this premier event. The deadline for course proposals is December 3, 2025. Full details at essai2026.eu
101
Luc De Raedt @lucderaedt.bsky.social · 23/04/2025
Very proud of this work from my group, achieving really impressive speedups in neurosymbolic inference.
180
Reposted by Luc De Raedt
Pedro Zuidberg Dos Martires @pedrozudo.bsky.social · 09/04/2025
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:
linkedin.com
#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...
1114
Reposted by Luc De Raedt
Nix @nix-cartoonist.bsky.social · 10/03/2025
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
Leuven.ai Creative AI Event
053
Reposted by Luc De Raedt
Jesse Davis @jessejdavis.bsky.social · 11/02/2025
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...
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...
11716
Reposted by Luc De Raedt
Jaron Maene @jjcmoon.bsky.social · 27/02/2025
This was joint work with @lucderaedt.bsky.social.
arxiv.org
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...
061
Reposted by Luc De Raedt
Jaron Maene @jjcmoon.bsky.social · 27/02/2025
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.
12710
Reposted by Luc De Raedt
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
Reposted by Luc De Raedt
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