#UAI2025 is about to start in Rio de Janeiro 🇧🇷 in Copacabana ⛱️🌊🩴 If you're curious about the program, you can check it out here: auai.org/uai2025/ UAI 2025

Welcome to Rio 🇧🇷! While we start, enjoy the sun, our local coffee swag ☕ and our upcoming five tutorials for the day (auai.org/uai2025/tutori…) 💙 stay tuned!

a huge thank you to our amazing volunteers 💙 working relentlessly to make the conference go smooth! auai.org/uai2025/volunt…

and "Hyperparameter Optimization and Algorithm Selection: Practical Techniques, Theory, and New Frontiers" by Dravyansh Sharma (TTIC)

presentations from the first oral session on learning auai.org/uai2025/schedu…

poster session going strong 💪

Although he could be surfing right now, Jonas Seng is busy presenting our work on the interplay between probabilistic circuits and federated learning UAI 2025 in Rio 🇧🇷. I am here till Friday and will be happy to chat about cauaslity, PCs or anything under the sun.

we open day 3 with Elias Bareinboim (Elias Bareinboim ) giving a keynote on "Towards Causal Artificial Intelligence" reprising some of the themes of his upcoming book (causalai-book.net)

congratulations to Frédéric Koriche, Jean-Marie Lagniez and Chi Tran for winning the 🏆 Best Paper Award 🏆 at #UAI2025 for "Probabilistic Explanations for Regression Models" 👉 openreview.net/forum?id=ipnYs…

congratulations to Paula Cordero Encinar, Francesca Romana Crucinio and O. Deniz Akyildiz (O. Deniz Akyildiz) for winning the 🏆 Best Student Paper Award 🏆 at #UAI2025 with "Proximal Interacting Particle Langevin Algorithms" 👉 openreview.net/forum?id=rTqyD…

and to leander, Paolo Morettin , Roberto Sebastiani, andrea passerini antonio vergari ⚔️ not at #ICML2025 for the ✨Best Student Paper Runner Up Award✨ for "A Probabilistic Neurosymbolic Layer for Algebraic Constraint Satisfaction" 👉 openreview.net/forum?id=9Ukxf…

The faces behind the UAI 2025 PR machine and cameras antonio vergari ⚔️ not at #ICML2025 Riccardo Massidda

Fazl Barez Tal Haklay Leshem (Legend) Choshen 🤖🤗 Mor Geva I think the best one for me was the work from Artidoro Pagnoni on Byte Latent Transformer (arxiv.org/abs/2412.09871) which creates new avenues for creating multimodal foundation models similar to our PIXAR (arxiv.org/abs/2401.03321) antonio vergari ⚔️ not at #ICML2025

SEMMA (transliteration of செம்ம - meaning awesome), my first PhD work, is accepted to #EMNLP2025 Main! I also found out today that SEMMA has the (tied) highest average reviewer score in this ARR cycle 💪 📜: arxiv.org/abs/2505.20422

SEMMA is now accepted at #EMNLP2025 Main! We worked very hard on this paper, and I had a great time collaborating with Arvindh Arun Bo Xiong mojtaba nayyeri antonio vergari ⚔️ not at #ICML2025 Ponnurangam Kumaraguru “PK” and Steffan. Feels great to have my first co-author paper get accepted at such a great venue!

zoom out to understand how fast you are going. It works also in #academia #phdlife

Arxiv Preprint: arxiv.org/abs/2505.20422 W/ mojtaba nayyeri Bo Xiong antonio vergari ⚔️ not at #ICML2025 Edward Raff May be of intrest to: Gabrielle Kaili-May Liu AmirHossein DabiriAghdam Lorenzo Xiao lynnette ng Jiarui Liu Mona Diab Zhaopeng Tu Sheshera Mysore Shoubin Yu Jiayuan Zhu Ziqi Zhang Jaehong Yoon

Orion Weller Love the "critical-n" idea! Alongside learning embeddings, have you tried a Linear Programme to verify test set predictability? We (antonio vergari ⚔️ not at #ICML2025) did this for MLC arxiv.org/abs/2310.10443 and guaranteed top-k thresholded outputs are predictable by constraining the embeddings.

Good morning from day 2 at NeSy in Santa Cruz! Starting with a nice oral session, such as studying how well neural networks learn boolean functions (with some surprising results!) Luis Lamb and verifying NeSy models for robustness

Luis Lamb 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.