
💡Where do #knowledge #graph #foundation #models actually struggle to generalize? It depends on the half-links seen in the inference graph! 👇👇👇 arxiv.org/pdf/2606.18001 with Obaidah Theeb, @danlhz , @tetraduzione , Steffen Staab

#MSCA PhD student in #ML #AI at @Uni_Stuttgart | #knowledge #graphs #neuro #symbolic #reasoning

💡Where do #knowledge #graph #foundation #models actually struggle to generalize? It depends on the half-links seen in the inference graph! 👇👇👇 arxiv.org/pdf/2606.18001 with Obaidah Theeb, @danlhz , @tetraduzione , Steffen Staab


Thanks to everyone who stopped by our work! If you missed it and want to know more, just drop me a message! #ICML2025
Spotlight poster coming soon at #ICML2025 @icmlconf! 📌East Exhibition Hall A-B E-1806 🗓️Wed 16 Jul 4:30 p.m. PDT — 7 p.m. PDT 📜arxiv.org/pdf/2410.12537 Let’s chat! I’m always up for conversations about knowledge graphs, reasoning, neuro-symbolic AI, and benchmarking.


Spotlight poster coming soon at #ICML2025 @icmlconf! 📌East Exhibition Hall A-B E-1806 🗓️Wed 16 Jul 4:30 p.m. PDT — 7 p.m. PDT 📜arxiv.org/pdf/2410.12537 Let’s chat! I’m always up for conversations about knowledge graphs, reasoning, neuro-symbolic AI, and benchmarking.
🚨Is complex query answering really complex?🚨 unfortunately not! the current benchmarks boil down to link prediction 98% of the time... how to fix this??? 👇👇👇 📜arxiv.org/abs/2410.12537 with @c_gregucci @BoXiongs @loreloc_ @PMinervini @ststaab

To appear at ICML 2025 (@icmlconf) as a spotlight! 🚀🚀🚀
🚨Is complex query answering really complex?🚨 unfortunately not! the current benchmarks boil down to link prediction 98% of the time... how to fix this??? 👇👇👇 📜arxiv.org/abs/2410.12537 with @c_gregucci @BoXiongs @loreloc_ @PMinervini @ststaab

hi, we found problematic benchmarks in complex query answering as well! arxiv.org/abs/2410.12537 @tetraduzione @Mniepert @c_gregucci @chrsmrrs @michael_galkin

We will be hiring one research fellow to work on multi-modal foundation models! The job ad will be online in the next few days 🙂
Our Generative AI Hub (genai.ac.uk/) will soon be hiring a Research Fellow to work on multi-modal AI models at @InfAtEd! If you're interested, please watch this space! 🚀🚀🚀

We are going to present our poster "Sum of Squares Circuits" at AAAI in Philadelphia today Hall E 12:30pm-14:00pm poster #840 We trace expressiveness connections of different types of additive and subtractive deep mixture models and tensor networks 📜 arxiv.org/abs/2408.11778
We learn more expressive mixture models that can subtract probability density by squaring them 🚨We show squaring can reduce expressiveness To tackle this we build sum of squares circuits🆘 🚀We explain why complex parameters help, and show an expressiveness hierarchy around🆘

Finally, LOgically COnsistent (LoCo) LLaMas can outperform solver-based baselines and SFT! I thank @tetraduzione and @looselycorrect for the guidance in realizing this project, get in touch or come to chat in Singapore! arxiv.org/abs/2409.13724

Many people are in the middle of the @CVPR deadline. So I'm sharing my guide to writing a CVPR paper (or any paper). My students have had this for years but I haven't shared it publicly before. I hope you find it useful and write a great paper. #CVPR2025 medium.com/@black_51980/writ…

🚨Is complex query answering really complex?🚨 unfortunately not! the current benchmarks boil down to link prediction 98% of the time... how to fix this??? 👇👇👇 📜arxiv.org/abs/2410.12537 with @c_gregucci @BoXiongs @loreloc_ @PMinervini @ststaab
yes! the way missing edges are placed is the key ingredient to complexity in CQA. 🚨🚨🚨 Unfortunately, all current benchmarks are baby benchmarks requiring to predict a single missing edge for 99% queries... Bottom line: we are just evaluating link prediction...

Large Language Models don't reason. Thank you, Apple.

We learn more expressive mixture models that can subtract probability density by squaring them 🚨We show squaring can reduce expressiveness To tackle this we build sum of squares circuits🆘 🚀We explain why complex parameters help, and show an expressiveness hierarchy around🆘

Interested in LLMs and KGs? Join our challenge on Knowledge Base construction with LLMs. #ISWC2024 #KnowledgeGraphs #LLM
Join the LM-KBC CHALLENGE @ ISWC 2024! Can you construct high-quality KBs directly from LLMs? 2 months time till submissions are due. @iswc_conf lm-kbc.github.io/challenge20…

From the hackathon to escape rooms🙂 @IAkaichi @UQudus @EKoulierakis @kouagou_dah @c_gregucci @Marm_mhm
Workshop 2nd day: Team building activity in an escape room 🙂@knowgraphs