Emile van Krieken
@emilevankrieken.com
Post-doc @ VU Amsterdam, prev University of Edinburgh.
Neurosymbolic Machine Learning, Generative Models, commonsense reasoning
https://www.emilevankrieken.com/
Neurosymbolic Machine Learning, Generative Models, commonsense reasoning
https://www.emilevankrieken.com/
Pinned
Emile van Krieken
@emilevankrieken.com
· May 21
We propose Neurosymbolic Diffusion Models! We find diffusion is especially compelling for neurosymbolic approaches, combining powerful multimodal understanding with symbolic reasoning 🚀
Read more 👇
Read more 👇
Reposted by Emile van Krieken
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.
We invented a new algorithm analysis framework to find out.
Beyond Smoothed Analysis: Analyzing the Simplex Method by the Book
Narrowing the gap between theory and practice is a longstanding goal of the algorithm analysis community. To further progress our understanding of how algorithms work in practice, we propose a new alg...
arxiv.org
October 27, 2025 at 1:43 AM
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.
We invented a new algorithm analysis framework to find out.
Reposted by Emile van Krieken
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!
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!
November 6, 2025 at 10:40 AM
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!
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!
Reposted by Emile van Krieken
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
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
November 6, 2025 at 7:08 AM
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
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
Reposted by Emile van Krieken
🌍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!
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!
October 15, 2025 at 10:53 AM
🌍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!
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!
Reposted by Emile van Krieken
Unfortunately, our submission to #NeurIPS didn’t go through with (5,4,4,3). But because I think it’s an excellent paper, I decided to share it anyway.
We show how to efficiently apply Bayesian learning in VLMs, improve calibration, and do active learning. Cool stuff!
📝 arxiv.org/abs/2412.06014
We show how to efficiently apply Bayesian learning in VLMs, improve calibration, and do active learning. Cool stuff!
📝 arxiv.org/abs/2412.06014
Post-hoc Probabilistic Vision-Language Models
Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success in classification, retrieval, and generative tasks. For this, VLMs deterministically map images and text descripti...
arxiv.org
September 18, 2025 at 8:34 PM
Unfortunately, our submission to #NeurIPS didn’t go through with (5,4,4,3). But because I think it’s an excellent paper, I decided to share it anyway.
We show how to efficiently apply Bayesian learning in VLMs, improve calibration, and do active learning. Cool stuff!
📝 arxiv.org/abs/2412.06014
We show how to efficiently apply Bayesian learning in VLMs, improve calibration, and do active learning. Cool stuff!
📝 arxiv.org/abs/2412.06014
Accepted to NeurIPS! 😁
We will present Neurosymbolic Diffusion Models in San Diego 🇺🇸 and Copenhagen 🇩🇰 thanks to @euripsconf.bsky.social 🇪🇺
We will present Neurosymbolic Diffusion Models in San Diego 🇺🇸 and Copenhagen 🇩🇰 thanks to @euripsconf.bsky.social 🇪🇺
We propose Neurosymbolic Diffusion Models! We find diffusion is especially compelling for neurosymbolic approaches, combining powerful multimodal understanding with symbolic reasoning 🚀
Read more 👇
Read more 👇
September 19, 2025 at 9:01 AM
Accepted to NeurIPS! 😁
We will present Neurosymbolic Diffusion Models in San Diego 🇺🇸 and Copenhagen 🇩🇰 thanks to @euripsconf.bsky.social 🇪🇺
We will present Neurosymbolic Diffusion Models in San Diego 🇺🇸 and Copenhagen 🇩🇰 thanks to @euripsconf.bsky.social 🇪🇺
Reposted by Emile van Krieken
A really neat paper thinking through what "Identifiability" means, how we can determine it, and implications for modeling.
Arxiv: arxiv.org/abs/2508.18853
#statssky #mlsky
Arxiv: arxiv.org/abs/2508.18853
#statssky #mlsky
September 16, 2025 at 1:49 AM
A really neat paper thinking through what "Identifiability" means, how we can determine it, and implications for modeling.
Arxiv: arxiv.org/abs/2508.18853
#statssky #mlsky
Arxiv: arxiv.org/abs/2508.18853
#statssky #mlsky
Reposted by Emile van Krieken
The most expensive part of training is the data, not the compute
Nikhil Kandpal & Colin Raffel calculate a really low bar for how much it would cost to produce LLM training data with 3.8$\h
Well, several scales more than the compute.
Luckily (?), companies don't pay for the data
🤖📈🧠
Nikhil Kandpal & Colin Raffel calculate a really low bar for how much it would cost to produce LLM training data with 3.8$\h
Well, several scales more than the compute.
Luckily (?), companies don't pay for the data
🤖📈🧠
September 12, 2025 at 2:20 PM
The most expensive part of training is the data, not the compute
Nikhil Kandpal & Colin Raffel calculate a really low bar for how much it would cost to produce LLM training data with 3.8$\h
Well, several scales more than the compute.
Luckily (?), companies don't pay for the data
🤖📈🧠
Nikhil Kandpal & Colin Raffel calculate a really low bar for how much it would cost to produce LLM training data with 3.8$\h
Well, several scales more than the compute.
Luckily (?), companies don't pay for the data
🤖📈🧠
Organising NeSy 2025 together with some of my favourite people (@e-giunchiglia.bsky.social @lgilpin.bsky.social @pascalhitzler.bsky.social) really was a dream. Super proud of what we've achieved! See you next year 😘
🦕NeSy 2025 is officially closed! Thanks again to everyone for attending this successful edition 😊
We will see you 1-4 September in another beautiful place: Lisbon! 🇵🇹
nesy-ai.org/conferences/...
We will see you 1-4 September in another beautiful place: Lisbon! 🇵🇹
nesy-ai.org/conferences/...
September 11, 2025 at 3:47 AM
Organising NeSy 2025 together with some of my favourite people (@e-giunchiglia.bsky.social @lgilpin.bsky.social @pascalhitzler.bsky.social) really was a dream. Super proud of what we've achieved! See you next year 😘
Reposted by Emile van Krieken
Our second keynote speaker is @tkipf.bsky.social, who will discuss object-centric representation learning!
Do objects need a special treatment for generative AI and world models? 🤔 We will hear on Monday!
Do objects need a special treatment for generative AI and world models? 🤔 We will hear on Monday!
September 6, 2025 at 8:51 PM
Our second keynote speaker is @tkipf.bsky.social, who will discuss object-centric representation learning!
Do objects need a special treatment for generative AI and world models? 🤔 We will hear on Monday!
Do objects need a special treatment for generative AI and world models? 🤔 We will hear on Monday!
Reposted by Emile van Krieken
It is almost time to welcome you all in Santa Cruz! 🦕
We will start with an exciting and timely keynote by
@guyvdb.bsky.social
on "Symbolic Reasoning in the Age of Large Language Models" 👀
📆 Full conference schedule: 2025.nesyconf.org/schedule/
We will start with an exciting and timely keynote by
@guyvdb.bsky.social
on "Symbolic Reasoning in the Age of Large Language Models" 👀
📆 Full conference schedule: 2025.nesyconf.org/schedule/
September 5, 2025 at 1:28 PM
It is almost time to welcome you all in Santa Cruz! 🦕
We will start with an exciting and timely keynote by
@guyvdb.bsky.social
on "Symbolic Reasoning in the Age of Large Language Models" 👀
📆 Full conference schedule: 2025.nesyconf.org/schedule/
We will start with an exciting and timely keynote by
@guyvdb.bsky.social
on "Symbolic Reasoning in the Age of Large Language Models" 👀
📆 Full conference schedule: 2025.nesyconf.org/schedule/
Reposted by Emile van Krieken
Does 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 👇
We got lost in latent space. Join us 👇
September 3, 2025 at 1:40 PM
Does 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 👇
We got lost in latent space. Join us 👇
Reposted by Emile van Krieken
We are immensely excited to announce our 4 leading researchers within our community as the #EurIPS keynote speakers🎉
@ulrikeluxburg.bsky.social
Michael Jordan
Emtiyaz Khan
Amnon Shashua
More details to come as we get closer to December, so stay tuned
@ulrikeluxburg.bsky.social
Michael Jordan
Emtiyaz Khan
Amnon Shashua
More details to come as we get closer to December, so stay tuned
August 29, 2025 at 7:31 AM
We are immensely excited to announce our 4 leading researchers within our community as the #EurIPS keynote speakers🎉
@ulrikeluxburg.bsky.social
Michael Jordan
Emtiyaz Khan
Amnon Shashua
More details to come as we get closer to December, so stay tuned
@ulrikeluxburg.bsky.social
Michael Jordan
Emtiyaz Khan
Amnon Shashua
More details to come as we get closer to December, so stay tuned
Reposted by Emile van Krieken
Ironic: as LLMs make writing much easier, I am finding not more, but less interesting and novel things to read online.
And so I keep paying more attention to the fewer people who still write their original thoughts (without LLMs - you can tell how repetitive it gets with them)
And so I keep paying more attention to the fewer people who still write their original thoughts (without LLMs - you can tell how repetitive it gets with them)
August 27, 2025 at 6:16 AM
Ironic: as LLMs make writing much easier, I am finding not more, but less interesting and novel things to read online.
And so I keep paying more attention to the fewer people who still write their original thoughts (without LLMs - you can tell how repetitive it gets with them)
And so I keep paying more attention to the fewer people who still write their original thoughts (without LLMs - you can tell how repetitive it gets with them)
Reposted by Emile van Krieken
This is a good feed to have in the mixer. It shows all papers being shared by your follows
**Please repost** If you're enjoying Paper Skygest -- our personalized feed of academic content on Bluesky -- we'd appreciate you reposting this! We’ve found that the most effective way for us to reach new users and communities is through users sharing it with their network
August 20, 2025 at 5:50 AM
This is a good feed to have in the mixer. It shows all papers being shared by your follows
Reposted by Emile van Krieken
Free online Neuro-Symbolic AI Summer School today and tomorrow. Looks like some interesting talks!
Neuro-Symbolic AI Summer School 2025 · Luma
Tired of the same old AI ideas and looking for something new? Or wondering if there are any deep alternatives to models that hallucinate, elude human…
lu.ma
August 14, 2025 at 12:27 PM
Free online Neuro-Symbolic AI Summer School today and tomorrow. Looks like some interesting talks!
Reposted by Emile van Krieken
We 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...
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...
August 13, 2025 at 12:51 PM
We 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...
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...
Reposted by Emile van Krieken
Thank you! Somebody (@gracekind.net ) has finally found the perfect way to answer these "its just matrix multiplication" takes.
Also, the take "there is nothing new with deep learning, neural nets were around 50y ago" is like "nothing new with humans, amino acides were around 4.4 billion y ago".
Also, the take "there is nothing new with deep learning, neural nets were around 50y ago" is like "nothing new with humans, amino acides were around 4.4 billion y ago".
August 10, 2025 at 7:10 AM
Thank you! Somebody (@gracekind.net ) has finally found the perfect way to answer these "its just matrix multiplication" takes.
Also, the take "there is nothing new with deep learning, neural nets were around 50y ago" is like "nothing new with humans, amino acides were around 4.4 billion y ago".
Also, the take "there is nothing new with deep learning, neural nets were around 50y ago" is like "nothing new with humans, amino acides were around 4.4 billion y ago".
Reposted by Emile van Krieken
GPT-5 lands first place on NoCha, our long-context book understanding benchmark.
That said, this is a tiny improvement (~1%) over o1-preview, which was released almost one year ago. Have long-context models hit a wall?
Accuracy of human readers is >97%... Long way to go!
That said, this is a tiny improvement (~1%) over o1-preview, which was released almost one year ago. Have long-context models hit a wall?
Accuracy of human readers is >97%... Long way to go!
August 8, 2025 at 2:13 AM
GPT-5 lands first place on NoCha, our long-context book understanding benchmark.
That said, this is a tiny improvement (~1%) over o1-preview, which was released almost one year ago. Have long-context models hit a wall?
Accuracy of human readers is >97%... Long way to go!
That said, this is a tiny improvement (~1%) over o1-preview, which was released almost one year ago. Have long-context models hit a wall?
Accuracy of human readers is >97%... Long way to go!
Reposted by Emile van Krieken
We built the simplest possible social media platform. No algorithms. No ads. Just LLM agents posting and following.
It still became a polarization machine.
Then we tried six interventions to fix social media.
The results were… not what we expected.
arxiv.org/abs/2508.03385
It still became a polarization machine.
Then we tried six interventions to fix social media.
The results were… not what we expected.
arxiv.org/abs/2508.03385
Can We Fix Social Media? Testing Prosocial Interventions using Generative Social Simulation
Social media platforms have been widely linked to societal harms, including rising polarization and the erosion of constructive debate. Can these problems be mitigated through prosocial interventions?...
arxiv.org
August 6, 2025 at 8:24 AM
We built the simplest possible social media platform. No algorithms. No ads. Just LLM agents posting and following.
It still became a polarization machine.
Then we tried six interventions to fix social media.
The results were… not what we expected.
arxiv.org/abs/2508.03385
It still became a polarization machine.
Then we tried six interventions to fix social media.
The results were… not what we expected.
arxiv.org/abs/2508.03385
Reposted by Emile van Krieken
It'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...
🧵1/4
Not only it contains most of my work, but there is plenty of brand new content:
publikationen.sulb.uni-saarland.de/handle/20.50...
🧵1/4
Publikationen der UdS: Meet my expectations: on the interplay of trustworthiness and deep learning optimization
publikationen.sulb.uni-saarland.de
August 6, 2025 at 7:57 PM
It'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...
🧵1/4
Not only it contains most of my work, but there is plenty of brand new content:
publikationen.sulb.uni-saarland.de/handle/20.50...
🧵1/4
Reposted by Emile van Krieken
hey wasn't this the same company that made a beautiful shiny "research" post about how AI evals should include error bars or something like that. or did they decide the CLT didn't apply here
August 6, 2025 at 3:20 AM
hey wasn't this the same company that made a beautiful shiny "research" post about how AI evals should include error bars or something like that. or did they decide the CLT didn't apply here
Reposted by Emile van Krieken
A reminder that the 70+ year-old research discipline of AI is much bigger than genAI, much bigger than just deep learning, much bigger than Big Tech. AI includes symbolic reasoning, multi-agent systems and statistical machine learning and is used for astrophysics, renewable energy and climate models
August 4, 2025 at 7:24 AM
A reminder that the 70+ year-old research discipline of AI is much bigger than genAI, much bigger than just deep learning, much bigger than Big Tech. AI includes symbolic reasoning, multi-agent systems and statistical machine learning and is used for astrophysics, renewable energy and climate models
Reposted by Emile van Krieken
Our illustrated guide to non-Euclidian ML is finally published!
Check it out for
⭐️ gorgeous figures (with new additions!) on topology, algebra, and geometry in the field
⭐️ broken down tables for easy reading
⭐️ accessible text, additional refs, and more
iopscience.iop.org/article/10.1...
Check it out for
⭐️ gorgeous figures (with new additions!) on topology, algebra, and geometry in the field
⭐️ broken down tables for easy reading
⭐️ accessible text, additional refs, and more
iopscience.iop.org/article/10.1...
August 1, 2025 at 3:24 PM
Our illustrated guide to non-Euclidian ML is finally published!
Check it out for
⭐️ gorgeous figures (with new additions!) on topology, algebra, and geometry in the field
⭐️ broken down tables for easy reading
⭐️ accessible text, additional refs, and more
iopscience.iop.org/article/10.1...
Check it out for
⭐️ gorgeous figures (with new additions!) on topology, algebra, and geometry in the field
⭐️ broken down tables for easy reading
⭐️ accessible text, additional refs, and more
iopscience.iop.org/article/10.1...
Reposted by Emile van Krieken
Supermassive congrats to Giwon Hong (@giwonhong.bsky.social) for the amazing feat! 🙂
July 31, 2025 at 12:48 AM
Supermassive congrats to Giwon Hong (@giwonhong.bsky.social) for the amazing feat! 🙂