🚨 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 🙌

The best AI conference will be in Amsterdam in 2026.

Amsterdam heeft achtentachtig prachtige grachten

Ready to bike along the canals? 🚲
The 42nd Conference on Uncertainty in AI will be in Amsterdam, August 17-21! 🇳🇱

CfP is out 👉 auai.org/uai2026/call...

🚨 Feb 25: Paper submission
🗣️ Apr 23–May 2: rebuttal period
🎉💀 Jun 1: Author notification

#UAI2026 #ML #stats #learning #reasoning #uncertainty #AI

👀

conspiracy physics and you (and also me) YouTube video by Angela Collier

@acollierastro.bsky.social is the coolest person on the internet and I am envious of everyone who knows her personally

I guess this calls for an adequate celebration.

Attending my forst tutorial of this year's UAI IN Rio. Fun fact about Rio. It's the only city outside of Europe that was the capital of a European countr at some point.

Unfortunately, this will also entail unavoidable collateral damage with people not at fault being called out.

Let's be honest, if you are looking for a community NeurIPS might be the wrong place. It's simply too big and anonymous. With anonymity comes people gaming the system and I think we should be calling out bad behavior more aggressively, eg."co-authoring" 10 papers and not contributing to peer-review.

Humans Learn Language from Situated Communicative Interactions. What about Machines? Katrien Beuls, Paul Van Eecke. Computational Linguistics, Volume 50, Issue 4 - December 2024. 2024.

One of the papers co-authored by her:

I think Katrien Beuls has been doing empirical research in this direction in the context of robotics.

Haha, meant the latter.

You said the naughty word🤭

The crazy thing about epicycles: at the time Kopernicus introduced his model they were far superior in terms of predictive power compared to the heliocentric model. This was still true when Kepler refined the model with ellipses. Epicycles had been extremely refined over time (capital+labor)

For machine learning this means that neural nets will keep on winning not necessarily for technical reasons but for sheer volume of investment and work hours that are being poured in their development.

Basically, every model and even the way we do science is a child of its time and has to be understood not only in a scientific context but also in a societal and economic one.

I guess all the answers above. But I meant it more in post-modernist philosophy of science way (reading Feyerabend at the moment)

Hot take: neural networks are the epicycles of the 21st century.

Ever changing from physics to AI and studying probabilistic ML, I have been wondering, how does all of this relate to quantum information theory 🎲.

I believe I've gotten a whole lot closer to the answer.
arxiv.org/abs/2506.01824

I'll be presenting the work at this year's @auai.org in Rio 😎

We developed a library to make logical reasoning embarrasingly parallel on the GPU.

For those at ICLR 🇸🇬: you can get the juicy details tomorrow (poster #414 at 15:00). Hope to see you there!

TLDR; yes... well, kind of 🙃

#ai #llms #reasoning #deepseek #3sat #iclr | Rishi Hazra 🚨 𝗡𝗲𝘄 𝗣𝗮𝗽𝗲𝗿 𝗔𝗹𝗲𝗿𝘁: 𝗛𝗮𝘃𝗲 𝗟𝗮𝗿𝗴𝗲 𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗠𝗼𝗱𝗲𝗹𝘀 𝗟𝗲𝗮𝗿𝗻𝗲𝗱 𝘁𝗼 𝗥𝗲𝗮𝘀𝗼𝗻? Despite their impressive performance on reasoning tasks, LLMs often succeed by fitting to patterns rather than understanding logic. Are...

What is reasoning and have LLMs learned it?

We answer these two questions in our new pre-print using the phase transition in random 3-SAT.
arxiv.org/abs/2504.039...

Together with @rishihazra95.bsky.social, @gabventurato.bsky.social and @lucderaedt.bsky.social

Here is also a longer thread:

Hmmm but many PPLs do numeric integration... and automatic differentiation is definitely not the same as numeric differentiation

For years I have been studyibg the top researchers in AI. They all share one personal trait:
attention to DETIAL.

I miss the times when all we cared about was end-to-end differentiability. Now all there seems to be is world domination this, world domination that.

Dieses Paradox schreit nach einem Namen.

I think deepseek is amazing and I kind of like it... Buuuut... 🙃

(Saw something like this in someone else's post but can't find it back)

Well, the only thing that matters is statistics, e.g. the mean of a distribution, or the probability that your sample will fall into a subset of the support. Hot take: only use densities to make nice plots and convince reviewer #2.

Probability densities are like the sun. Look at them directly and they will blind you 😎
@paolomorettin.bsky.social

Is it still okay to justify gaps in my CV with the pandemic? Asking for a friend.