Pinned Tweet
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🆘
Lorenzo Loconte retweeted
What is TMLR doing under a 300% increase in submissions?
- Suspensions of >150 authors
- Publicly naming major violations
- Submission quotas distinguishing slop patterns
- Desk rejections 6% → 53%; focus on clarity
- AI reviews evaluating soundness
blog.tmlr.org/2026/adapting-…
Lorenzo Loconte retweeted
📢 PhD opportunity @inria_sophia at the intersection of #KnowledgeGraphs, #SemanticWeb, #NLP and #LLMs.
🧠 Extracting from and verbalizing RDF to text to support collaborative co-editing of wikis and their corresponding linked data
🔗 jobs.inria.fr/public/classic…
#AI #MachineLearning
Lorenzo Loconte retweeted
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
Lorenzo Loconte retweeted
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)! 🎉
github.com/geometric-kernels…
Lorenzo Loconte retweeted
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
arxiv.org/abs/2512.17090
Lorenzo Loconte retweeted
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!
📢 Announcing the Workshop on **Unifying Concept Representation Learning** at ICLR’26 ( @iclr_conf ).
When? 26 or 27 April 2026
Where? Rio de Janeiro, Brazil
Call for papers, schedule, invited speakers & more: ucrl-iclr26.github.io
Looking forward to your submissions!
Lorenzo Loconte retweeted
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!
Lorenzo Loconte retweeted
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.
Lorenzo Loconte retweeted
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: arxiv.org/abs/2506.22271
Lorenzo Loconte retweeted
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
eurips.cc
Lorenzo Loconte retweeted
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
Lorenzo Loconte retweeted
🧵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
Lorenzo Loconte retweeted
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 retweeted
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!
Lorenzo Loconte retweeted
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
arxiv.org/abs/2409.13724
Lorenzo Loconte retweeted
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!
Lorenzo Loconte retweeted
🚨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 retweeted
hi, we found problematic benchmarks in complex query answering as well! arxiv.org/abs/2410.12537 @tetraduzione @Mniepert @c_gregucci @chrsmrrs @michael_galkin
Lorenzo Loconte retweeted
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 🥳🥳🥳
Fine-tuning your LLM with LoRA for critical areas like ⚖️ criminal justice, 🏥 healthcare, or 💼 hiring?
⚠️ Think again! ⚠️
🚨 We found that LoRA can amplify #AI #harms:
❗️False sense of #safety #alignment
🚫Increased #unfairness and #bias, hitting minority groups the hardest