20th International conference on Neurosymbolic Learning and Reasoning University of Lisbon, Lisbon, Portugal 1 to 4 September 2026

Lisbon
Joined November 2024
🦕NeSy 2025 is officially closed! Thanks again to everyone for attending this successful edition 😊 We will see you 1-4 September in another beautiful place: Lisbon! 🇵🇹
5
3
16
3,324
🦕The 20th conference on Neurosymbolic AI will be in Lisbon, Portugal, September 1-4, 2026! We have two submission phases: 🚨 Deadline 1: Feb 24 (abstract), Mar 3 (full) 🚨 Deadline 2: Jun 9 (abstract), Jun 16 (full) #neurosymbolic #NeSy2026
1
1
4
395
Recordings of the NeSy 2025 keynotes are now available! 🎥 Check out insightful talks from @guyvdb , @tkipf and @dlmcguinness on our new Youtube channel. Topics include using symbolic reasoning for LLM, and object-centric representations youtube.com/@NeSyconference
5
12
3,107
I gave a keynote at @nesyconf on "Symbolic Reasoning in the Age of Large Language Models" Check out the recording if you are curious about neurosymbolic generative AI: youtube.com/watch?v=OtmiJRTl…
7
45
4,499
NeSy 2026 retweeted
Happy to receive the Runner-up Best Paper Award at the @nesyconf at @ucsc "Understanding Boolean Function Learnability on Deep Neural Networks: PAC Learning Meets Neurosymbolic Models” w/@vardi Avelar, Tavares, Nicolau, Flach, Zhang paper here: openreview.net/pdf?id=RrqvMv…
3
8
659
🌊 Had an amazing time at NeSy 2025 @nesyconf in Santa Cruz! Very well-organized conference, great talks, inspiring discussion and of course enjoying the beautiful beach and Bay Area vibes. 🏖️✨ #NeSy2025 #neurosymbolicAI #SantaCruz
1
2
2
344
Good morning from the final day of NeSy 2025 🦕 Yesterday we had another successful poster session outside, just after the weather cleared up! 🌞
1
1
5
240
Now @YuqichengZ is opening the oral session with a beautiful talk on a Neurosymbolic extension of Retrieval Augmented Generation (RAG) with an argumentation framework CC @BoXiongs
1
1
5
212
Next, @Octavio_Arriaga discusses the importance of physics in learning algorithms, in particular in computer vision and robotics 🤖⚛️ And @EmilevanKrieken introduced new work on reasoning shortcuts: Be aware of them when you apply your NeSy predictors ♻️!
2
3
311
Good morning from day 2 at NeSy in Santa Cruz! Starting with a nice oral session, such as studying how well neural networks learn boolean functions (with some surprising results!) @luislamb and verifying NeSy models for robustness
1
3
1
8
871
We're glad to announce the NeSy 2025 Test of Time award for "Probabilistic Inference Modulo Theories"! 🏆Rodrigo de Salvo Braz was here to accept the award. This is groundwork for recent NeSy approaches like DeepSeaProbLog and the probabilistic algebraic layer.
1
8
13
929
Now, @dlmcguinness is giving her keynote talk, reflecting on how insights from her career can help grow the field of Neurosymbolic to where it should be: At the top 🚀
1
3
154
The (iconic) school bus to NeSy 2025.nesyconf.org/
3
8
540
X loops back into the real world... via my colleague at NeSy!
It's time for @tkipf 's keynote! Does object-centric representations still matter in the age of Generative AI where Transformers are key? Yes - But it's not part of the architecture:
1
5
18
4,622
Do world models need objects? @tkipf made a strong case today at @nesyconf from objects as the symbols of the physical world to SlotFormer, enabling compositional video dynamics prediction from just a single frame. Exciting directions for object-centric generative models.
1
4
114
Good morning from NeSy! We are very happy to welcome you here in Santa Cruz, and are glad to announce the conference is growing 📈 Check out this thread below for live updates from the conference 🦕
1
3
10
550
It's time for @tkipf 's keynote! Does object-centric representations still matter in the age of Generative AI where Transformers are key? Yes - But it's not part of the architecture:
1
1
1
5
4,875
Object representations can be used in different settings: - Videos - 3D modelling - Robotic representations This especially helps in the low-data regime!
3
206
Just by adding the DFA that constraints the reasoning to include the number at least once, it improved the performance. This is a good illustration of how simple rules can significantly improve the performance of LLMs. #Neurosymbolic #Nesy
1
1
3
159