Adrián Javaloy @javaloyml.bsky.social · 16/09/2026It has been a while since I have been active here, and lots of things have changed: different city, different role. I have been swamped, but I finally managed to update my website. More news sooner than later! (I accept suggestions for lab names) adrianjav.github.io 1163
Reposted by Adrián JavaloyOisin Mac Aodha @oisinmacaodha.bsky.social · 15/05/2026🎓 Announcing the 1st Bath Summer School in Machine Learning 📅 5–7 August 2026 | 📍 University of Bath Topics: ODEs/SDEs, Bayesian methods, Self-Supervised Learning, World Models Open to PhDs, postdocs & staff at EU/UK universities www.bathmlsummerschool.org 0169
Adrián Javaloy @javaloyml.bsky.social · 06/05/2026Good luck to everyone pushing for NeurIPS! (And please do not take down OpenReview this time 🙏) 010
Reposted by Adrián JavaloyAnnalena Kofler @annalenakofler.bsky.social · 08/04/2026This great blogpost summarizes my own experience where I deleted code that Claude had written for me because I realized that I understood nothing in this file. 051
Reposted by Adrián JavaloyRobert Peharz @ropeharz.bsky.social · 27/03/2026🚨 Opportunity for #Neurosymbolic AI folks! I’m looking for a PhD student or postdoc to join the 🇦🇹 FWF Cluster of Excellence Bilateral AI (think #NeSy++): www.bilateral-ai.net Feel free to reach out or share 🙌bilateral-ai.netBilateral AI - HomeBilateral AI is an Austrian Cluster of Excellence developing Broad AI by combining symbolic and sub-symbolic AI. Discover research, news and events. 084
Adrián Javaloy @javaloyml.bsky.social · 12/02/2026I 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/2512.17090arxiv.orgHow to Square Tensor Networks and Circuits Without Squaring ThemSquared tensor networks (TNs) and their extension as computational graphs--squared circuits--have been used as expressive distribution estimators, yet supporting closed-form marginalization. However, ... 1143
Reposted by Adrián JavaloyEleonora Giunchiglia @e-giunchiglia.bsky.social · 06/11/2025Want to use your favourite #NeSy model but afraid of the reasoning shortcuts?🫣 Fear not💪🏻In our #NeurIPS2025 paper we show that you just need to equip your favourite NeSy model with prototypical networks and the reasoning shortcuts will be a problem of the past! 1143
Reposted by Adrián JavaloyAEMET @aemet.es · 05/11/2025📈 Tenerife Norte bate su récord de temperatura para noviembre: 33 °C el día 4. ➡️ Supera ampliamente el registro máximo anterior, de 31 °C. Tenerife Norte tiene una serie de datos de 85 años. 18242
Adrián Javaloy @javaloyml.bsky.social · 28/10/2025Convince me that Dagstuhl seminars are real and not AI generated 😒 010
Reposted by Adrián JavaloyClément Canonne @ccanonne.github.io · 04/09/2025To: Reviewer 2 My name is Inigo Montoya You killed my paper Prepare to die 1546
Reposted by Adrián JavaloyFrançois Rozet @francois-rozet.bsky.social · 03/09/2025Does a smaller latent space lead to worse generation in latent diffusion models? Not necessarily! We show that LDMs are extremely robust to a wide range of compression rates (10-1000x) in the context of physics emulation. We got lost in latent space. Join us 👇 1278
Reposted by Adrián JavaloyClément Canonne @ccanonne.github.io · 29/08/2025Friday afternoon! Finally time to look back at a busy week, and ask oneself — "wait, what did I do, again?" 1122
Reposted by Adrián JavaloyNeurIPS Europe @neuripseurope.bsky.social · 13/08/2025We are excited to bring #EurIPS 2025 to Copenhagen in December. Consider becoming a sponsor and support us in making this inaugural event a success! Sponsorship packages are available and can be further customized if necessary. Reach out if you have any questions ❔ Info: eurips.cc/become-spons... 0188
Reposted by Adrián JavaloyAdrián Javaloy @javaloyml.bsky.social · 06/08/2025It's been a while, but I am happy to share that my PhD dissertation is finally available online! 🎉 Not only it contains most of my work, but there is plenty of brand new content: publikationen.sulb.uni-saarland.de/handle/20.50... 🧵1/4publikationen.sulb.uni-saarland.dePublikationen der UdS: Meet my expectations: on the interplay of trustworthiness and deep learning optimization 183
Adrián Javaloy @javaloyml.bsky.social · 06/08/2025It's been a while, but I am happy to share that my PhD dissertation is finally available online! 🎉 Not only it contains most of my work, but there is plenty of brand new content: publikationen.sulb.uni-saarland.de/handle/20.50... 🧵1/4publikationen.sulb.uni-saarland.dePublikationen der UdS: Meet my expectations: on the interplay of trustworthiness and deep learning optimization 183
Adrián Javaloy @javaloyml.bsky.social · 03/08/2025What a nice experience! Thank you everyone who attended TPM! Particularly those who engaged in the poster sessions, few times I had so much fun discussing my poster! 090
Reposted by Adrián Javaloyantonio vergari ⚔️ short-circuiting @nolovedeeplearning.bsky.social · 02/08/2025likely one of the best editions of #TPM ever! big thanks to @poorvagarg.bsky.social @jsleland.bsky.social @javaloyml.bsky.social @zzhe.bsky.social @lennertds.bsky.social Lingyun Yao and Christoph Staudt for organizing it and to everyone who attended it! 0132
Reposted by Adrián JavaloySiby Hess @ilsebyl.bsky.social · 25/07/2025My maternity leave project is now somewhat out: I made a jupyterbook about the basics of ML, that I teach at TUE. You can check it out here: sibylse.github.io/TUEML/intro.... The linA part is not yet formulated out and there are other todos, but maybe it helps someone with their own course design 😅sibylse.github.ioWelcome to the Data Mining and Machine Learning Book — Data Mining and Machine Learning Jupyter Book 164
Reposted by Adrián JavaloyJohn Leland @jsleland.bsky.social · 25/07/2025Last talk of the day for TPM! @auai.org #TPM2025 0122
Reposted by Adrián Javaloyuai2026 @auai.org · 23/07/2025we almost end the day (banquet incoming) with an extremely lively poster session! 0164
Reposted by Adrián Javaloyuai2026 @auai.org · 22/07/2025the conference cannot officially start without a proper reception 🍹 0134
Adrián Javaloy @javaloyml.bsky.social · 18/07/2025Next week I will be in 🌴 Rio 🌴 attending (and helping organizing) UAI 2025 and TPM 2025. If you are also attending and want to talk science (e.g. probabilistic generative models, causality, multi-objective machine learning, etc) or just hang out, not everything is work, feel free to reach me out! 061
Adrián Javaloy @javaloyml.bsky.social · 18/07/2025Unrelatedly, the rule of mandatory physical attendance for authors was changed *after* the submission deadline: web.archive.org/web/20250514... People submitted their works under some given premises, altering them a posteriori is questionable at best... 020
Reposted by Adrián JavaloyEmile van Krieken @emilevankrieken.com · 17/07/2025Hmm, this rule seems very recently changed? web.archive.org/web/20250514... This was what it said just before the deadline, so people submitting to NeurIPS couldn't have known about the mandatory physical presence 🤔 072
Reposted by Adrián JavaloyPierre Marion @pierremarion.bsky.social · 17/07/2025✨Thrilled to see EurIPS launch — the first officially endorsed European NeurIPS presentation venue! 👀 But NeurIPS now requires at least one author to attend in San Diego or Mexico (and not just virtually as before). This is detrimental to many. Why not allow presenting at EurIPS or online? 1/4 22511
Reposted by Adrián JavaloyGautam Kamath @gautamkamath.com · 17/07/2025For years, people have suggested having alternate NeurIPS locations, outside the US. 2025 is the first time it will be done, with satellite locations in Copenhagen and Mexico City. I wonder if this will be a one-off thing, or whether the trend will continue. 4193
Reposted by Adrián Javaloyuai2026 @auai.org · 15/07/2025less than one week to go! Check our schedule comprising: 1 ❤️🩹mentoring session 2 🔑 keynotes 3 🧑🔧 workshops 5 📊 tutorials 20 🗣️ orals 229 📜 posters 👉 www.auai.org/uai2025/scheduleauai.org 0105
Reposted by Adrián JavaloyMotonobu Kanagawa @motonobu-kanagawa.bsky.social · 24/06/2025We've written a monograph on Gaussian processes and reproducing kernel methods (with @philipphennig.bsky.social, @sejdino.bsky.social and Bharath Sriperumbudur). arxiv.org/abs/2506.17366arxiv.orgGaussian Processes and Reproducing Kernels: Connections and EquivalencesThis monograph studies the relations between two approaches using positive definite kernels: probabilistic methods using Gaussian processes, and non-probabilistic methods using reproducing kernel Hilb... 03711
Reposted by Adrián JavaloyImage and Signal Processing • ISP @isp-uv-es.bsky.social · 26/05/2025❗📅 Extended deadline: May 29th 👥 Several positions: - Postdoc ( Project 1: AI for Earth System Modeling) - PhD, Postdoc, Scientific Programmer (Project 2: Next-Gen Foundation Models) - PhD + Postdoc (Project 3 – AI for Scientific Discovery) 📝 Apply here: forms.gle/grkEhmXrDout...docs.google.com 002
Adrián Javaloy @javaloyml.bsky.social · 25/05/2025We have extended the submission deadline for TPM to the 2nd of June! Remember that **we accept recently accepted works that fit in topic,** so if you want to travel to Rio and share your work it's a no brainer imho 🌴🌴 132
Reposted by Adrián JavaloyFrançois Rozet @francois-rozet.bsky.social · 23/05/2025📢 I am looking for AI post-doc/research/engineer positions in Europe (Paris, London, Zurich, ...) starting 2026. My work revolves around generative modeling and AI for Science, with 4+ publications at top conferences during my PhD. If you are hiring, please reach out! If not, please repost 🔁 21911
Reposted by Adrián JavaloyI-X @imperial-ix.bsky.social · 22/05/2025Join us for our next I-X seminar with Dr Antonio Vergari @nolovedeeplearning.bsky.social titled "Logically-Consistent Deep Learning". 🕓 13:00 - 14:00 (GMT) 📅 Thursday, 5 June 📍 Hybrid (White City Campus / Microsoft Teams) Register via link below. www.imperial.ac.uk/events/19426...imperial.ac.ukI-X Seminar: Logically-Consistent Deep Learning with Dr Antonio VergariIn this talk, Dr Antonio Vergari (University of Edinburgh) will speak about logically-consistent deep learning. 074
Reposted by Adrián Javaloyantonio vergari ⚔️ short-circuiting @nolovedeeplearning.bsky.social · 22/05/2025Rio is looking forward to seeing all your works on #fast #reliable #tractable #models #circuits #tensor #networks #flows! please share! 068
Reposted by Adrián JavaloyEmile van Krieken @emilevankrieken.com · 21/05/2025We propose Neurosymbolic Diffusion Models! We find diffusion is especially compelling for neurosymbolic approaches, combining powerful multimodal understanding with symbolic reasoning 🚀 Read more 👇 49327
Reposted by Adrián JavaloyLauren Nicole DeLong @laurendelong.bsky.social · 13/05/2025📣 🗞️ 👉 Just in time for Mental Health Awareness Week 🧠 🎉Our study is now published in Nature Comms Medicine! ⚡ We look at whether certain patterns of physical conditions affect the risk of developing #depression 📜 Paper: www.nature.com/articles/s43... 🖥️ Post: www.ed.ac.uk/news/multipl...nature.comCluster and survival analysis of UK biobank data reveals associations between physical multimorbidity clusters and subsequent depression - Communications MedicineDeLong et al. investigate several clustering techniques to identify patterns of physical multimorbidity. They find several clusters which align to known body systems and use survival analyses to deter... 031
Reposted by Adrián Javaloythe beggars out of here getter @milesklee.bsky.social · 04/05/2025“The whole thing feels like Black Mirror.” “He would listen to the bot over me.” “It gave my husband the title of ‘spark bearer’ because he brought it to life.” Relationships are being destroyed thanks to spiritual mania, supernatural delusions, and arcane prophecy — all fueled by AI chatbots:rollingstone.comPeople Are Losing Loved Ones to AI-Fueled Spiritual FantasiesMarriages and families are falling apart as people are sucked into fantasy worlds of spiritual prophecy by AI tools like OpenAI's ChatGPT 962188600
Reposted by Adrián JavaloyAdrián Javaloy @javaloyml.bsky.social · 30/04/2025This year I am co-organizing the 8th iteration of the Tractable Probabilistic Modeling #TPM workshop at #UAI2025 🌴 Rio de Janeiro edition 🌴 🌐 lnkd.in/dDK8T5Au ⏰ Submission deadline: May 23th AoE 🌴 Date: July 15th 🧵👇 1159
Reposted by Adrián JavaloyNicola Branchini @nicolabranchini.bsky.social · 02/05/2025🚨 New paper: “Towards Adaptive Self-Normalized IS”, @ IEEE Statistical Signal Processing Workshop. TLDR; To estimate µ = E_p[f(θ)] with SNIS, instead of doing MCMC on p(θ) or learning a parametric q(θ), we try MCMC directly on p(θ)| f(θ)-µ | (variance-minimizing proposal). arxiv.org/abs/2505.00372arxiv.orgTowards Adaptive Self-Normalized Importance SamplersThe self-normalized importance sampling (SNIS) estimator is a Monte Carlo estimator widely used to approximate expectations in statistical signal processing and machine learning. The efficiency of S... 13111
Adrián Javaloy @javaloyml.bsky.social · 30/04/2025Today we have @lennertds.bsky.social from KU Leuven teaching us how to adapt NeSy methods to deal with sequential problems 🚀 Super interesting topic combining DL + NeSy + HMMs! Keep an eye on Lennert's future works! 093
Adrián Javaloy @javaloyml.bsky.social · 30/04/2025This year I am co-organizing the 8th iteration of the Tractable Probabilistic Modeling #TPM workshop at #UAI2025 🌴 Rio de Janeiro edition 🌴 🌐 lnkd.in/dDK8T5Au ⏰ Submission deadline: May 23th AoE 🌴 Date: July 15th 🧵👇 1159
Reposted by Adrián JavaloyGilles Louppe @glouppe.bsky.social · 29/04/2025<proud advisor> Hot off the arXiv! 🦬 "Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation" 🌍 Appa is our novel 1.5B-parameter probabilistic weather model that unifies reanalysis, filtering, and forecasting in a single framework. A thread 🧵 25215
Reposted by Adrián JavaloyLena Zellinger @lenazellinger.bsky.social · 28/04/2025It’s great to have @wouterboomsma.bsky.social talking at UoE today! Happening at 2pm at EFI 2.35. 092
Reposted by Adrián JavaloyOisin Mac Aodha @oisinmacaodha.bsky.social · 23/04/2025Tomorrow in poster session 2 at #ICLR2025 Neehar (@therealpaneni.bsky.social) will be presenting his work on comparing neural networks via concepts. Representational Similarity via Interpretable Visual Concepts arxiv.org/abs/2503.15699 nkondapa.github.io/rsvc-page/ 091
Reposted by Adrián Javaloyantonio vergari ⚔️ short-circuiting @nolovedeeplearning.bsky.social · 16/04/2025the #TPM ⚡Tractable Probabilistic Modeling ⚡Workshop is back at @auai.org #UAI2025! Submit your works on: - fast and #reliable inference - #circuits and #tensor #networks - normalizing #flows - scaling #NeSy #AI ...& more! 🕓 deadline: 23/05/25 👉 tractable-probabilistic-modeling.github.io/tpm2025/ 13819
Reposted by Adrián JavaloyMartin Trapp @trappmartin.eurosky.social · 16/04/2025It’s crazy that there is now a funding freeze for Harvard. It’s also crazy that the ~2.2 billion account to only ~4% of the budget of Harvard. In fact, the total budget is larger than the governmental budget of Nepal. And the frozen budget (2.2 billion) is larger than the total budget of ETH. 4161
Reposted by Adrián JavaloyAleksander Molak @alxndrmlk.bsky.social · 11/04/2025Did you know that @javaloyml.bsky.social has a Python library for Causal Normalizing Flows? #CausalSky 121