←
Lorenzo Loconte162 posts
Lorenzo Loconte avatar

Lorenzo Loconte

@loreloc_
◷ Joined March 2017▧ 29 Photos and videos
Lorenzo Loconte avatar
Lorenzo Loconte@loreloc_·7 Oct 2024

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🆘

Jaron Maene avatar
⟳ Lorenzo Loconte retweeted
Jaron Maene@jjcmoon·Oct 20

I let gpt-6 astra review 250 random ICLR submissions. It didn't recommend clear accept for a single paper.

Post attachment
Transactions on Machine Learning Research avatar
⟳ Lorenzo Loconte retweeted
Transactions on Machine Learning Research@TmlrOrg·Oct 16

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-…

Peyman Milanfar avatar
⟳ Lorenzo Loconte retweeted
Peyman Milanfar@docmilanfar·Mar 29

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 avatar
⟳ Lorenzo Loconte retweeted
Viacheslav Borovitskiy@vabor112·Mar 12

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…

Post attachment
Adrián Javaloy avatar
⟳ Lorenzo Loconte retweeted
Adrián Javaloy@javaloyML·Feb 12

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

Stefano Teso avatar
⟳ Lorenzo Loconte retweeted
Stefano Teso@looselycorrect·28 Dec 2025

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!

NeurIPS Europe avatar
⟳ Lorenzo Loconte retweeted
NeurIPS Europe@EurIPSConf·19 Sep 2025

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!

Post attachment
NeSy 2026 avatar
⟳ Lorenzo Loconte retweeted
NeSy 2026@nesyconf·9 Sep 2025

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.

Post attachmentPost attachmentPost attachment
Samy Badreddine avatar
⟳ Lorenzo Loconte retweeted
Samy Badreddine@sbadredd·1 Sep 2025

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

Cosimo Gregucci avatar
⟳ Lorenzo Loconte retweeted
Cosimo Gregucci@c_gregucci·10 Jul 2025

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.

Post attachment

🚨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

Post attachment
Emanuele Marconato avatar
⟳ Lorenzo Loconte retweeted
Emanuele Marconato@ema_marconato·13 Jun 2025

🧵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

Post attachment
Emile van Krieken avatar
⟳ Lorenzo Loconte retweeted
Emile van Krieken@EmilevanKrieken·21 May 2025

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