Artur d'Avila Garcez

Reasoning in Neurosymbolic AI Knowledge representation and reasoning in neural networks have been a long-standing endeavor which has attracted much attention recently. The principled integration of reasoning and learning in neural...

Reasoning in Neurosymbolic AI: arxiv.org/abs/2505.20313

AI beyond ChatGPT: an analysis of the state of AI 2 years on from GPT4 and an opinion on where it should be heading:
www.staff.city.ac.uk/~aag/papers/...

NeSy 2025 late deadline approaching (abstract May 30, paper June 6). 2025.nesyconf.org/call-for-pap...

19th Conference on Neurosymbolic Learning and Reasoning (NeSy 2025), Santa Cruz, California, September 8th to 10th 2025.

🙌🏻 NeSy Confence = Amazing Speakers!!! 🙌🏻

⏳Do not forget to submit your abstract before the deadline!

NeSy 2025 industry abstracts (2 pages) deadline June 15, 2025.nesyconf.org/call-for-pap... 19th International Conference on Neurosymbolic Learning and Reasoning (NeSy 2025), held in Santa Cruz (CA, USA) from September 8-10, 2025.

When building human allied AI systems, it is imperative to think of who is in control. In our blue sky paper at #AAAI, we argue that a deeper understanding of whether human is in the loop or if AI is in the loop is essential! arxiv.org/pdf/2412.14232

Indeed. The first NeSy workshop was in Scotland as part of IJCAI...

Together with @kareemyousrii.bsky.social, we announce the Neurosymbolic Generative Models special track at the NeSy 2025 Conference 🎉

Call for Papers is live!
2025.nesyconf.org/nesy-generat...

See you in Santa Cruz in Sep 2025!

@nesyconf.org

How many more of these examples of unreliable LLMs until something really bad happens?

Three Lecturer openings at @citystgeorges.bsky.social: www.city.ac.uk/about/jobs/a....
Join our new AI center covering, among others: NeSy AI, MAS, Reinforcement Learning, NLP, Computer Vision, KGs, Adaptive Systems.

@arturgarcez.bsky.social @pmadhyastha.bsky.social @ealonso.bsky.social

Track Editors:

Alessandro Abate, University of Oxford, U.K.
Eleonora Giunchiglia, Imperial College London, U.K.
Bettina Könighofer, Graz University of Technology, Austria
Luca Pasa, University of Padova, Italy
Matteo Zavatteri, University of Padova, Italy

Excited to help organise 🦕NeSy 2025 this year!

It will be in sunny Santa Cruz 🌅 See CFP down below.

A reminder that the recording of NeSy2024 is available at sites.google.com/view/nesy202... and the recording of NeSy2023 is at sites.google.com/view/nesy202...

📣 Does your model learn high-quality #concepts, or does it learn a #shortcut?

Test it with our #NeurIPS2024 dataset & benchmark track paper!

rsbench: A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts

What's the deal with rsbench? 🧵

ARC Prize - Official Guide The official guide to ARC Prize.

ARC2025: a great test for neurosymbolic systems 🦕
arcprize.org/guide

Can someone ask o1 pro or similar what it makes of this picture?

Sora still appears to have trouble with physics Exactly as I warned in February

The new Sora apparently fails in the same ways as its predecessor, exactly as I predicted the day after the original came out.

Super interesting from the perspective of innateness and empiricism debate.

open.substack.com/pub/garymarc...

A Semantic Framework for Neuro-Symbolic Computing The field of neuro-symbolic AI aims to benefit from the combination of neural networks and symbolic systems. A cornerstone of the field is the translation or encoding of symbolic knowledge into neural...

Very pleased that "A Semantic Framework for Neurosymbolic Computation" (with Simon Odense), towards a semantics for deep learning, has been accepted for publication in the AI journal (after a 2-year reviewing process):
arxiv.org/abs/2212.12050

@abeba.bsky.social reaches quite similar conclusions to my own re that Casey Newton piece:

Lewis: What's your favourite thing about Brazil so far?

Colleague: The people, they're lovely!

Lewis: You like the city?

Colleague: Yeah, I do! Do you like the city?

Lewis: I love it here, I'm Brazilian now! 🇧🇷😁

A reliable way to make people believe in falsehoods is frequent repetition, because familiarity is not easily distinguished from truth. Authoritarian institutions and marketers have always known this fact. Daniel Kahneman

@karpathy.bsky.social's post (in the other place) about the "history of attention" in deep learning seems relevant to neurosymbolic AI folks in connection with work on relational learning...

#libraries

Knowledge Graphs Interest Group at the Alan Turing Institute This interest group will facilitate research and innovation in a critical area of data science and AI. - Knowledge Graphs Interest Group at the Alan Turing Institute

The Turing Interest Group on Knowledge Graphs: github.com/turing-knowl...

We have built a community around #KGs involving academia, industry, and government.

📢 Next (in person) meet up on Friday November 29 in Edinburgh. Registration is free.

🏫 We are also gathering teaching material.

🔥 Follow this page 👉 bsky.app/profile/nesy... to stay updated with the 2025 Neuro-symbolic AI conference 🦕🦕🦕

NeSy2025 The NeSy series is the longest standing gathering for the presentation and discussion of cutting edge research in neurosymbolic AI. NeSy is the annual meeting of the Neural-Symbolic Learning and Reaso...

NeSy is on Bluesky! bsky.app/profile/nesy...

Check out the 2025 edition of the NeSy conference:
2025.nesyconf.org

General Chair: @lgilpin.bsky.social
Programme Chairs: @e-giunchiglia.bsky.social @emilevankrieken.com @pascalhitzler.bsky.social

@tarekbesold.bsky.social @arturgarcez.bsky.social