#NeuroSymbolic

2025-06-06

Double award! 🏆 🏆 Best Poster and the Dieter Fensel Visionary Award at European Semantic Web Conference went to the work "Representing and querying data tensors in and ", done by Piotr Marciniak, our CTO Piotr Sowiński, and Maria Ganzha.

We are deeply thankful for this distinction! The work is absolutely key to systems we are building.

Poster: ostrzyciel.eu/assets/pdf/poste
Paper: arxiv.org/pdf/2504.19224
Website, code, datasets, and more: w3id.org/rdf-tensor

Larry SwansonLarrySwanson
2025-05-23

Much of the conversation around AI lately is about systems that combine neural-network tech like and symbolic AI like .

Frank van Harmelen's puts his AI research in the larger context of how these technical systems can best support .

While some in the AI world seek to replace with machines, Frank focuses on AI systems that collaborate with people to create .

knowledgegraphinsights.com/fra

2025-04-09

#DIN #Spec 91526 released on #Knowledge #Graphs for #Language models and vice versa: Hybrid applications of #symbolic and sub-symbolic #AI

The #standardization focuses on the advantages of hybrid approaches that combine symbolic knowledge with modern language models.

@NFDI4DS was involved in creating the specification together with other partners from academia and industry.

Read more: dinmedia.de/en/technical-rule/

#LLM #neurosymbolic #KG #DINSPEC

Hacker Newsh4ckernews
2025-03-22
2025-01-24

🌟 Call for Submissions for ISWC 2025 is out!! 🌟
The International Semantic Web Conference 2025 will take place in Nara, Japan.
Deadline for the Research track: May 6, 2025 (abstracts), May 13, 2025 (full papers)

#ISWC2025 website: iswc2025.semanticweb.org/

#semanticweb #knowledgegraphs #ontologies #logic #AI #generativeAI #llms #neurosymbolic #neurosymbolicAI @iswc_conf @fizise @tabea @sashabruns @enorouzi @MahsaVafaie

Webpage of the ISWC 2025 Conference. The Background picture is showing a autumn landscape with a few trees with colorful leafs. Under the trees, a bunch of deers are grazing. Seems to be a picture from the conference location, which is Nara in Japan, famous for its deers that are not shy of tourists...
FIZ ISE Research Groupfizise@sigmoid.social
2025-01-20

Yesterday, the GenAIK 2025 workshop on the integration of generative AI and knowledge graphs took place in Abu Dhabi co-located with #coling2025

#GenAIK2025 website: genetasefa.github.io/GenAIK202

#generativeAI #knowledgegraphs #AI #semanticweb #ontologies #neuroAI #neurosymbolic @GenAsefa @GenAIK @albertmeronyo @lihuchen @fiz_karlsruhe @lysander07 @NFDI4DS

The empty conference room shortly before the start of the GenAIK 2025 workshop. The welcome screen displays the skyline of Abu Dhabi with the workshop title, venue, and date...
2024-12-17

The schedule for the next VSAonline webinar series (January to June 2025) is published at:

sites.google.com/view/hdvsaonl

There are 11 talks around #VectorSymbolicArchitecture / #HyperdimensionalComputing

The talks are (almost always) recorded and published online, in case you can't participate in the live session.

@cogsci
#VSA #HDC #CompCogScii #MathPsych #AI #neuromorphic #neurosymbolic #ComputationalNeuroscience #ComputationalCognitiveScience #MathematicalPsychology

2024-12-15

SynaLinks HybridAGI:The Programmable Neuro-Symbolic AGI

makertube.net/videos/watch/336

2024-11-27

SEMANTICS 2025, Research & Innovation track, Call for papers is out! Deadlines:
abstracts: April 25, 2024
full paper: May 2, 2025

2025-eu.semantics.cc/page/cfp_

#SemanticWeb #knowledgegraphs #llms #AI #generativeAI #symbolicAI #neurosymbolic #cfp #semantics2025 @semantics @fizise @AxelPolleres

Webpage of the SEMANTICS 2025 conference featuring a promotional image for the 21st International Conference on Semantic Systems, SEMANTICS 2025, taking place in Vienna from September 3rd to 5th, 2025. The image features a scenic sunset view of the Vienna skyline reflected in a body of water, with the conference logo prominently displayed.  The text also highlights the conference's focus on Machine Learning, Data Science, Linked Data, and Natural Language Processing.
2024-11-19

Very glad to be at @istecnico, @ULisboa_, @InescID for a research visit of 2 weeks, with Miguel Couceiro.

If you're in the area and would like to talk about #knowledgeGraphs or #neuroSymbolic #ArtificialIntelligence, feel free to reach out!

#Neurosymbolic AI combines neural networks with symbolic reasoning to bring true logic & reasoning to LLMs. By integrating solvers, graphs of rules, & PKGs, we enhance AI beyond just pattern matching. The future is reasoning-driven AI! #NeurosymbolicAI #LLM #AI #KnowledgeGraphs #SymbolicReasoning
youtube.com/watch?v=473QKajx3Q

2024-10-18

Interesting new paper: "Graph-constrained Reasoning (GCR)" - Enabling Faithful KG-grounded LLM Reasoning with Zero Hallucination! 🧠 by Linhao Luo, Zicheng Zhao, Chen Gong, Gholamreza Haffari, Shirui Pan

paper: arxiv.org/pdf/2410.13080
GCR code on GitHub: github.com/RManLuo/graph-const

#knowledgegraphs #llms #semanticweb #neurosymbolic #hybridaI #AI

Illustration of existing KG-enhanced LLM reasoning paradigms and proposed graphconstrained reasoning (GCR). 1) First, given a KG, we convert it into the KG-Trie, serving as a structured index to facilitate efficient reasoning path searches using LLMs. 2) Then, we design a graph-constrained decoding process that employs a lightweight KG-specialized LLM to generate multiple KG-grounded reasoning paths and hypothesis answers. This ensures the faithfulness of the reasoning process while leveraging the strong capabilities of LLMs to efficiently explore reasoning paths within KGs. 3) Finally, we input the generated reasoning paths and hypothesis answers into a powerful general LLM to utilize its inductive reasoning ability to produce final answers.
2024-06-18

Thanks to Dr. Somak Aditya for enriching our work on Neurosymbolic NLP/AI! Somak is Assistant Professor at IIT Kharagpur and has been visiting UKP Lab as guest faculty in June. He is staying with us until the end of June, continuing his work on Reasoning and Code Prompting.

Learn more about Somak's work on Reasoning and Robustness of LLMs here:

➡️ adityasomak.github.io/

#CodePrompting #Reasoning #NLProc #AI #Neurosymbolic #NLP #LLMs

Jason MorrisLexpedite@mstdn.ca
2024-06-02

Very close 🤏🏻 to being able to create a demo with my new §Blawx prototype demonstrating 4 of the myriad ways neuro-symbolic AI can be used to enhance #RulesAsCode: drafting the code, running an interview, converting facts to symbolic representations, and converting symbolic AI results to natural language.

Stay tuned...

#AI #NeuroSymbolic #LegalTech

Sören Auer 🇪🇺🇺🇦soeren_auer@mstdn.social
2024-05-15

Our article "Linked Open Literature Review using the #NeuroSymbolic Open Research #KnowledgeGraph" @orkg with Fidel Jiomekong and Allard Oelen is now available as #OpenAccess in the ACM The Web Conference proceedings 2024 dl.acm.org/doi/10.1145/3589335 - includes a nice demo video by Fidel

Martin Ruskovmapto@qoto.org
2024-05-13

#mediapool.bg want to illustrate an article on bread prices in Bulgaria. What I see is #GenAI overdoing the job.

After having studied how #midjuorney v4 could illustrate fairy tales (for anyone interested, qoto.org/@mapto/11011125214281 ) I really want to research more about what stops GenAI from overdoing it with bread around a baker. The greatest obstacle I encounter is the obscurity of most models that engage with #neurosymbolic. It's practically useless, because the creators of such models prefer to be very secretive about what they do. The one exception reported results that do not seem to be reproducible (twitter.com/Birchlabs/status/1).

Image sourced from: mediapool.bg/kzk-tavanat-za-na

Image of a baker surrounded by bread that is exaggeratedly AI-generated
2024-05-08

The future of what is currently labeled as "neurosymbolic AI" is going to be algebraic.
Category theory is the only framework that provides the required abstraction to characterise all the ingredients in the same language.

#neurosymbolicai
#neurosymbolic
#categorytheory

2024-04-18

Interesting talk by Sergei Nirenburg: "Mutual Trust in Human-AI Teams Relies on Metacognition"

youtube.com/watch?v=KmMe4QrQiR

#AI #ML #CognitiveScience #NeuroSymbolic #ArtificialIntelligence #MachineLearning #LLM

Client Info

Server: https://mastodon.social
Version: 2025.07
Repository: https://github.com/cyevgeniy/lmst