Moritz Schauer

Compressing Biology: Evaluating the Stable Diffusion VAE for Phenotypic Drug Discovery High-throughput phenotypic screens generate vast microscopy image datasets that push the limits of generative models due to their large dimensionality. Despite the growing popularity of general-purpos...

Excited to share our recent paper, ”Compressing Biology,” to be presented at the Imageomics workshop at NeurIPS 2025. 🔬💻 Work led by my amazing PhD student Télio Cropsal. #cellpainting #stablediffusion #imageomics

arxiv.org/abs/2510.19887

#AITHYRA, Vienna's new Biomedical AI institute, is hiring Postdocs!

Come work with us. Openings in: 🔹 Generative AI 🔹 Multimodal ML 🔹 Virology 🔹 Enzyme Function

Apply by Nov 20: oeaw.ac.at/aithyra/post... #PostDoc #AI #ML #Vienna #ScienceJobs

Great first day of the 3rd annual CHAIR Structured Learning Workshop @ Chalmers! 🥳

Event page & agenda: ui.ungpd.com/Events/60bfc...

1st day featuring:
@betapata.bsky.social
@janstuehmer.bsky.social
@arnauddoucet.bsky.social
@frejohk.bsky.social

Very nice by Jun Otsuka @junotk.bsky.social and Hayato Saigo: link.springer.com/article/10.1...
about causal interventions/do calculus via string diagram surgery

Our process causation paper is published in Synthese! We propose that process causation (a la Salmon, Dowe, MDC new mechanists) can be modeled using a category-theoretic framework.
link.springer.com/article/10.1...

Confounding is just the failure of the Doob conditioning functor from a Markov category into the associated category of backward-forward optics to be lax comonoidal

Oh, hats up to Mike Hicks who authored a policy paragraph on double-blind reviewing and amphibious type systems for POPL 2013 which has stand the test of time and is used in ICSME, OOPSLA, ECOOP, SPLASH, ICFP, PLDI, POPL, CSF, CAV... pldi12.cs.purdue.edu/others/dbr-f...

"But I am conditioning on the outcome all the time and I think I understand the world just fine!"

Nice this is getting close to a recursive situation where ignoring collider bias you can find evidence that collider bias is all made up.

2025 CHAIR Structured Learning Workshop -- Apply to attend: ui.ungpd.com/Events/60bfc...

A golden Marburg Weidenhausen night accentuated by blue paper recycling bins…

I wanted a poster session on a ferris wheel

So this is how I learned programming when I was twelve! 😃

Are you passionate about AI for molecular engineering? Just two weeks left to apply to the 2 PhD positions currently open in our team at Chalmers! 🎓

For details: ailab.bio/join-us

Somehow relatedly I sometimes think of Bayesian inference as harm reduction tool as well

Please, please put your hyperparameter tuning procedure into the paper. For your method and the baselines

Ich habe versucht meinen Kollegen dieses deutsche Konzept zu erklären und dabei kam ich stark ins Zweifeln ob die Kinder wirklich einfach nach Hause geschickt werden?! Aber anscheinend hatte ich es richtig 🙃

Yeah Moritz, *electricity*, that’s totally why you were doing this (bridges for random walks on random graphs)

I can only recommend it, it was a very nice experience when I did it.

link 📈🤖
Parallel computations for Metropolis Markov chains with Picard maps (Grazzi, Zanella) We develop parallel algorithms for simulating zeroth-order (aka gradient-free) Metropolis Markov chains based on the Picard map. For Random Walk Metropolis Markov chains targeting log-concave distributio

Don’t let your idea of good wine be shaped by a generation you wouldn’t trust to choose the tiles for an underpass

bayescomp2025.sg

Tomorrow at #BayesComp @rseyer.bsky.social with arxiv.org/abs/2504.12190 (poster presentation, 19 Jun 2025, 5.30pm - 7.30pm local time)

It’s giving late-game vibes of Sid Meier’s Civilization, where the player is bored and just trying to see what happens if they declare some wars before they abandon the game.

Yeah, in general you should be averaging the densities not the means, and I took a shortcut that for Bernoullis this is the same

A university profile of "Dr Amy Lloyd" who works as a research fellow on Alzheimer's research

Has nominative determinism gone too far

h/t @benjaminschneider.ch

Reads like made up reasons. As if dual licensing didn’t exist.

https://xkcd.com/2110/

Right, you don't need error bars on error bars.
Probabilistic uncertainty about uncertainty collapses. This is the “monadic join” in probability.
Instead of a coin with random bias p ∼ π, you can flip a coin with the deterministic bias μ.
Just take μ = E[p]. #statistics

Uh, was it even wrong? Now that I read it, it reads like a grammar thing... (the year of the letter vs year of the disease)