
PhD Machine Learning @KU_Leuven | #neurosymbolic learning & #probabilistic reasoning
Joined January 2022
- Tweets97
- Following310
- Followers155
- Likes423
Jaron Maene retweeted
An internal model at OpenAI has produced a claimed refutation of ETH! Russell Impagliazzo, Mohan Paturi, and I have been asked to help organize an open and independent examination of this claim. 1/4
I let gpt-6 astra review 250 random ICLR submissions. It didn't recommend clear accept for a single paper.
Jaron Maene retweeted
Just a little under 5 days left to submit your work on #tractable #probabilistic #models to TPM [email protected] (June 12, AoE)! If you have ongoing projects or recently accepted papers that are #tractable, #causal or #neurosymbolic, then check the CfP at
tractable-probabilistic-mode…
Jaron Maene retweeted
When you prompt an LLM for code, you get one deterministic program. However, the LLM actually defines a distribution over many programs, and existing methods discard it‼️ PPoT uses this distribution to extract free performance and efficiency gains. 🧵👇
Jaron Maene retweeted
the next-gen EUV machine from ASML got delivered yesterday at @imec_int in Leuven.
as a Belgian, it's amazing to see such unique machines being deployed in my alma mater's city
Belgian chip research lab imec has secured an ASML $400-million High NA EUV lithography machine.
imec, which helped ASML develop EUV technology, is giving companies and researchers shared access to this cutting-edge chipmaking tool. #EuStrategicAutonomy
reuters.com/business/belgium…
Jaron Maene retweeted
Only 10 days left to submit your work to ProbML (formerly AABI)!
👉 probml.cc/call/
Jaron Maene retweeted
Too many papers fail to provide a reasonable related literature comparison. I'm not even talking about a good comparison...it’s simply part of doing research to place your result within the existing literature.
Jaron Maene retweeted
If you care about enforcing constraints over time without breaking your computational resources, then read our new blog post over at @aihuborg!
It focuses on showing how our neurosymbolic Markov models beat the SOTA in out-of-distribution generalisation and so much more.
Relational neurosymbolic Markov models ift.tt/bJTtBEY
Jaron Maene retweeted
all the LLM bros are obsessed with counting model weights, but me? I do weighted model counting 😎
Replying to @xuanalogue
Especially glad I started the PhD after the Russell-Domingos-Tenenbaum-etc synthesis of logic and symbolic representations with probability theory. We actually can have the best of both worlds!
1/5 Tomorrow I’ll talk about the 𝐩𝐫𝐨𝐛𝐚𝐛𝐢𝐥𝐢𝐬𝐭𝐢𝐜 𝐩𝐫𝐨𝐠𝐫𝐚𝐦𝐦𝐢𝐧𝐠 𝐬𝐞𝐦𝐚𝐧𝐭𝐢𝐜𝐬 𝐨𝐟 𝐝𝐢𝐟𝐟𝐞𝐫𝐞𝐧𝐭𝐢𝐚𝐛𝐥𝐞 𝐩𝐫𝐨𝐯𝐢𝐧𝐠 at #NeurIPS San Diego (poster #614 11am).
📃 openreview.net/pdf?id=rEUbDh…
📺 youtube.com/watch?v=sOTXBsmG…
4/5 We show how to factorize this equivalence distribution using latent categorical variables—a kind of embeddings.
Plus we develop exact (via singularization + magic sets) and approximate (Monte Carlo) inference methods.
5/5 Joint work with Efthymia Tsamoura.
Paper: openreview.net/pdf?id=rEUbDh…






















