Emile van Krieken

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

It 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

We're hiring a postdoc on Neurosymbolic World Models in the Learning and Reasoning group! The position is together with Filip Ilievski and @cgmsnoek.bsky.social, and offers the possibility for PhD co-supervision. Feel free to reach out to us for any questions! workingat.vu.nl/vacancies/po...

Missed our poster on byte-level LLMs at ICLR on Tuesday? Come chat to us at the CoLoRAI workshop tomorrow afternoon at 15:15! grigoris.ece.wisc.edu/workshops/co... @emilevankrieken.com @nolovedeeplearning.bsky.social

I especially love this diagram.

When reality surpasses fiction! Top: fictional forecast for August 2050, broadcast by French TV in 2014 to warn about the consequences of global warming. Bottom: Real French forecast for yesterday, June 22, 2026.

shamelessly stolen

🎓 Applications are now open for the ELLIS Summer School on Machine Learning & Computer Vision in Munich! Get insights into: → Computer Vision → Machine Learning → Natural Language Processing 📍 TU Munich 🇩🇪 📅 15–18 September ⏰ Apply by 30 June 🔗 https://bit.ly/4vvEzJk

🚨 Last call for applicants interested in #Neurosymbolic AI / #NeSy! We’re still looking for a PhD student or postdoc to join the 🇦🇹 FWF Cluster of Excellence Bilateral AI: www.bilateral-ai.net jobs.tugraz.at/de/jobs/4663... jobs.tugraz.at/de/jobs/71ba... 📅 Deadline: May 31 (just a few days left!)

value-driven transport! a new framework for generative modeling, combining elements of * optimal control / RL * optimal transport * stochastic primal-dual optimization thread about our new work with @pmorenoz.bsky.social (@upf.edu) & Adrian Müller (@ethz.ch) 1/

My first paper with my first PhD student @pedrocvieira.bsky.social just landed on arXiv! 🎉 “Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?” Spoiler alert: the answer is largely no—at least, not much more than a single model does. 🧵👇 📄 arxiv.org/abs/2605.22593

Do you want to connect with the European AI research community? NeurIPS Europe is coming to Paris (Dec 9th-13th) and we are looking for sponsors to help to make it happen. Tiers from Bronze (10k€) to Platinum (60k€). neurips.cc/sponsors/pro... @ellis.eu

We're looking for a new colleague at @amlab.bsky.social: Assistant Professor in AI for Science 🔬🤖 World-class ML research, Amsterdam's thriving AI ecosystem (ELLIS, startups, big tech), and some of the best academic labor conditions in Europe ❤️ Deadline: May 30 👉 werkenbij.uva.nl/en/vacancies...

Claude Code has certainly made me write code faster. But it turns out, the bottleneck is still experiment run time and experiment analysis

I’m seeing close to zero reaction/conversation about this on here. This is huge news for open research on language models, especially in the US.

Sharing “Neural Thickets”. We find: In large models, the neighborhood around pretrained weights can become dense with task-improving solutions. In this regime, post-training can be easy; even random guessing works Paper: arxiv.org/abs/2603.12228 Web: thickets.mit.edu 1/

🚨2 PhD positions with me @amlab.bsky.social on learning causally grounded concepts 🚨 Are you interested in improving the #interpretability #robustness and #safety of AI by integrating #causal reasoning? Join us in beautiful Amsterdam 🇳🇱🌷🚲 Deadline: 20 April www.academictransfer.com/en/jobs/3593...

You are here

Claude just told me to remove an offhand footnote about Anthropic's dealings with the DoW 😱🤨

Spot-on. My work got cognitively more challenging, not less, with LLMs, as much more challenging things are achievable now.

🧵New paper: "Lost in Backpropagation: The LM Head is a Gradient Bottleneck" The output layer of LLMs destroys 95-99% of your training signal during backpropagation, and this significantly slows down pretraining 👇

Well, this seems like a big deal. arxiv.org/abs/2603.087... "This is the first algorithm that can PAC learn even intersections of two halfspaces in time 2^o(n)."

LLMs are nothing more than models of the distribution of the word forms in their training data, with weights modified by post-training to produce somewhat different distributions.

The AI discourse sometimes seems to center on "Is AI good or is it bad?" I find this framing unproductive. AI is not a fixed thing. I would prefer to ask "How might we use this technology for good, and mitigate the bad?" What a shame if the best use we can come up with is no use at all.

To kick off the PhD journey with @pseudomanifold.topology.rocks: What are the limitations of the WL metric, and what is an 𝘪𝘯𝘧𝘰𝘳𝘮𝘢𝘵𝘪𝘷𝘦 𝘮𝘦𝘵𝘳𝘪𝘤? We answer these questions with our 𝗚𝗿𝗮𝗽𝗵 𝗛𝗼𝗺𝗼𝗺𝗼𝗿𝗽𝗵𝗶𝘀𝗺 𝗗𝗶𝘀𝘁𝗼𝗿𝘁𝗶𝗼𝗻 arxiv.org/abs/2511.03068 @olgatticus.bsky.social, Kavir and @erikjbekkers.bsky.social

"He is from [MASK] [MASK]" → "San York"? dLLMs fail because they ignore token dependencies. This Factorization Barrier arises from a structural misspecification: models are restricted to fully factorized outputs. We break this barrier with CoDD, enabling coherent parallel generation. 🚀

Sam is a snake

time traveler from 12 months from now just sent me this

In light of the current funding situation (worldwide), a modest proposal: instead of pouring billions of dollars into GenAI claiming "it *could* accelerate science and research," consider putting 1% of that amount in what *will* accelerate science and research. Namely, funding science and research.

why do science? it won,t make the model Bigger

X is hiring a creative writing specialist at $40 an hour to make Grok better at writing and a true LOL at the qualifications

New open source: cuthbert 🐛 State space models with all the hotness: (temporally) parallelisable, JAX, Kalman, SMC

Best conference with the best people and in the best place 😎 😜 Also the submission deadline is conveniently one month later than #ICML2026, just in case you needed it 😅

🦕The 20th conference on Neurosymbolic AI will be in Lisbon, Portugal, September 1-4, 2026! The CFP is out: 2026.nesyconf.org/call-for-pap... with two phases: 🚨 Deadline 1: Feb 24 (abstract), Mar 3 (full) 🚨 Deadline 2: Jun 9 (abstract), Jun 16 (full) #neurosymbolic #NeSy2026

We introduce epiplexity, a new measure of information that provides a foundation for how to select, generate, or transform data for learning systems. We have been working on this for almost 2 years, and I cannot contain my excitement! arxiv.org/abs/2601.03220 1/7

Good call! I maintain a list of Neurosymbolic folks on Bsky, see here 🦕 go.bsky.app/RMJ8q3i

#XAI, #neurosymbolic methods #nesy and #causal #representation #learning #CRL all care about learning #interpretable #concepts, but in different ways. We are organizing this #ICLR2026 workshop to bring these three communities together and learn from each other 🦾🔥💥 Submission deadline: 30 Jan 2026

Emile will present our work on Knowledge Graph Embeddings at Eurips' Salon des Refusés on Friday! We show how linearity prevent KGEs from scaling to larger graphs + propose a simple solution using a Mixture of Softmaxes (see LLM literature) to break the limitations at a low parameter cost. 🔨

Recordings of the NeSy 2025 keynotes are now available! 🎥 Check out insightful talks from @guyvdb.bsky.social, @tkipf.bsky.social and D McGuinness on our new Youtube channel www.youtube.com/@NeSyconfere... Topics include using symbolic reasoning for LLM, and object-centric representations!

🚨 New paper alert! We introduce Vision-Language Programs (VLP), a neuro-symbolic framework that combines the perceptual power of VLMs with program synthesis for robust visual reasoning.

The simplex algorithm is super efficient. 80 years of experience says it runs in linear time. Nobody can explain _why_ it is so fast. We invented a new algorithm analysis framework to find out.

Want 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!

I'm in Suzhou to present our work on MultiBLiMP, Friday @ 11:45 in the Multilinguality session (A301)! Come check it out if your interested in multilingual linguistic evaluation of LLMs (there will be parse trees on the slides! There's still use for syntactic structure!) arxiv.org/abs/2504.02768

🌍Introducing BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data! LLMs learn from vastly more data than humans ever experience. BabyLM challenges this paradigm by focusing on developmentally plausible data We extend this effort to 45 new languages!