Lorenzo Loconte

PhD Student @ University of Edinburgh

[Lorenzo Loconte @loreloc_]

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🆘

[Peyman Milanfar @docmilanfar]

AI people going on about Johnson-Lindenstrauss lemma like it was discovered yesterday.

it’s just another example of how most folks don’t read or know anything more than 5 years old

[Viacheslav Borovitskiy @vabor112]

Happy to share a major milestone: after years of development, we are officially launching Version 1.0 of the GeometricKernels library!

To top it off, our accompanying paper has just been published in JMLR (MLOSS)! 🎉

https://t.co/orSv60ydUX

[Adrián Javaloy @javaloyML]

I am a bit late to the party, but I am happy to share that our latest work was accepted to #ICLR2026 🥳🥳

📜 How to Square Tensor Networks and Circuits Without Squaring Them

https://t.co/5dKwvVtkD4

[Stefano Teso ✈️ AAAI26 @looselycorrect]

Good news everyone! This year we will be organizing a workshop on Unifying Concept Representation Learning at ICLR'26!

The workshop is about unifying ideas and techniques from #NeSy AI, #XAI and #Causal representation learning. Have a look at the CfP!

[NeurIPS Europe Conference @EurIPSConf]

Congratulations to everyone who got their @NeurIPSConf papers accepted 🎉🎉🎉

At #EurIPS we are looking forward to welcoming presentations of all accepted NeurIPS papers, including a new “Salon des Refusés” track for papers which were rejected due to space constraints!

[NeSy 2026 @nesyconf]

@luislamb 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.

[Samy Badreddine @sbadredd]

@deedydas Insightful! We tackled the same problem in Knowledge Graph Completion. Dot-product scoring on low-dim embeddings severely limits what a model can predict. We call this a “rank bottleneck” to align with the existing LM literature. Our paper for context: https://t.co/IePSDw9VYb

[NeurIPS Europe Conference @EurIPSConf]

EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅

EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @NeurIPSConf and #NordicAIR and is co-developed by @ELLISforEurope

https://t.co/RSAvf9lcZm

[Cosimo Gregucci@ICML @c_gregucci]

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
📜https://t.co/flFPGWWTJW

Let’s chat! I’m always up for conversations about knowledge graphs, reasoning, neuro-symbolic AI, and benchmarking.

[Emanuele Marconato @ema_marconato]

🧵Why are linear properties so ubiquitous in LLM representations?

We explore this question through the lens of 𝗶𝗱𝗲𝗻𝘁𝗶𝗳𝗶𝗮𝗯𝗶𝗹𝗶𝘁𝘆:

“All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling”

Published at #AISTATS2025🌴

1/9

[Emile van Krieken @EmilevanKrieken]

We propose Neurosymbolic Diffusion Models! We find diffusion is especially compelling for neurosymbolic approaches, combining powerful multimodal understanding with symbolic reasoning 🚀

Read more 👇

[Lorenzo Loconte @loreloc_]

@flavioAd we do not need AI for this

https://t.co/Vl80fsrhOw

https://t.co/Ymg7H5UnYN

[Lennert De Smet @LennertDS_]

Just under 10 days left to submit your latest endeavours in ⚡#tractable⚡ probabilistic models❗

Join us at TPM @auai.org #UAI2025 and show how to build #neurosymbolic / #probabilistic AI that is both fast and trustworthy!

[Diego Calanzone @diegocalanzone]

In LoCo-LMs, we propose a neuro-symbolic loss function to fine-tune a LM to acquire logically consistent knowledge from a domain graph, i.e. wrt. to a set of logical consistency rules.
@looselycorrect @tetraduzione

https://t.co/YXGg38mIon

[Jaron Maene @jjcmoon]

We developed a library to make logical reasoning embarrassingly parallel on the GPU.

For those at ICLR 🇸🇬: you can get the juicy details tomorrow (poster #414 at 15:00). Hope to see you there!

[Eleonora Giunchiglia @e_giunchiglia]

🚨New at #ICLR: we introduce the first ever 𝐥𝐚𝐲𝐞𝐫 that makes 𝐚𝐧𝐲 neural network 𝐜𝐨𝐦𝐩𝐥𝐢𝐚𝐧𝐭 𝐛𝐲 𝐝𝐞𝐬𝐢𝐠𝐧 with constraints expressed as 𝐝𝐢𝐬𝐣𝐮𝐧𝐜𝐭𝐢𝐨𝐧𝐬 𝐨𝐟 𝐥𝐢𝐧𝐞𝐚𝐫 𝐢𝐧𝐞𝐪𝐮𝐚𝐥𝐢𝐭𝐢𝐞𝐬—even if they define 𝐧𝐨𝐧-𝐜𝐨𝐧𝐯𝐞𝐱 𝐬𝐩𝐚𝐜𝐞𝐬!

[Lorenzo Loconte @loreloc_]

@RussellTsuchida Amazing work Russell! Thanks for sharing

[Pasquale Minervini @PMinervini]

@chaitjo @benfinkelshtein @ffabffrasca @mmbronstein @phanein @michael_galkin @chrsmrrs hi, we found problematic benchmarks in complex query answering as well! https://t.co/5qmkguhEIT @tetraduzione @Mniepert @c_gregucci @chrsmrrs @michael_galkin

[Bhavya Kailkhura @bkailkhu]

Our paper "Low-rank finetuning for LLMs is inherently unfair" won a 𝐛𝐞𝐬𝐭 𝐩𝐚𝐩𝐞𝐫 𝐚𝐰𝐚𝐫𝐝 at the @RealAAAI colorai workshop! #AAAI2025

Congratulations to amazing co-authors @nandofioretto @WatIsDas @CuongTr95450563 and M. Romanelli 🥳🥳🥳