Det här var banne mig det finaste jag hört på länge.

Uppträdanden på gator o torg ”som vi inte är vana vid” säger Tove L om Palestinarörelsen. #agenda Hört talas om ungdomskravaller från 50-talet o framåt? Eller -68? Vietnamdemonstrationer? Irakkriget? EU-mötet 2001. Vid alla har det skett olämpligheten. You name it. Sluta vara så historielös!

Somebody really committed to the bit! Almost @theonion.com level satire

A new revised version of "Uncertainty in Bayesian leave-one-out cross-validation based model comparison" with Sivula, @mansmag.bsky.social, and Matamoros. We have clarified the goal of the paper, made more clear that the uncertainty is described by the posterior of unknown elpd difference, 1/4

"Classifying Hate: Legal and Ethical Evaluations of ML-Assisted Hate Crime Classification and Estimation in Sweden" (w Hannes Waldetoft & @mansmag.bsky.social) studies where models succeed and struggle when classifying hate crime motivations in police reports. facctconference.org/static/docs/...

"Formalising Anti-Discrimination Law in Automated Decision Systems" (w @mansmag.bsky.social) tackles shortcomings in algo fairness approaches when applied to anti-discrimination law, introducing a novel decision-theoretic framework to mitigate unlawful discrimination. arxiv.org/abs/2407.00400

Ja, jag reagerade också på detta. Detta är verkligen ett underligt beteende av en svensk utrikesminister.

We are hiring postdocs in Computational Social Science 📍SweCSS, Norrköping, Sweden ⏰Deadline June 3 🔗https://liu.se/en/work-at-liu/vacancies/26854 Please apply // help us spread the word

If you are in AISTATS, talk with Jakob about your wishes for the future of posteriordb!

posteriordb is a database with models, data, and reference posteriors, making it easier to test and compare inference. v1.0.0 recently released discourse.mc-stan.org/t/posteriord.... Jakob Torgander presents proceedings.mlr.press/v258/magnuss... May 5 in AISTATS Oral sess. 5 and in Poster sess. 3

Smart money is on Sweden this year? (src eurovisionworld.com/odds/eurovis...)

Sharing our new preprint "An Image is Worth K Topics: A Visual Structural Topic Model with Image Embeddings" with @mansmag.bsky.social @matmagnani.bsky.social Alexandra Segerberg and Nataša Sladoje. Available on ArXiv: arxiv.org/abs/2504.10004

So excited to have two papers at @facct.bsky.social w @mansmag.bsky.social! 📄 One paper formalises UK anti-discrimination law in framework for automated decision-making: arxiv.org/abs/2407.00400 💡 The other explores transformers for better hate crime classification in Sweden. See you in Athens!

Wow. Two accepted paper at @facct.bsky.social 2025. A big thanks to @hollisargeant.bsky.social for pulling me into the field.

Stora institutioner sviktar, och styrelseledamöter och rektorer darrar. Hatten av för Leo Gerdén som vågar säga som det är, trots att han som utbytesstudent vid Harvard tar en personlig risk. www.thecrimson.com/article/2025...

Excited to be part of the Cramér Society’s virtual mini-conference next Monday (13:00–16:00), alongside @marfig.bsky.social, @mathurinmassias.bsky.social, @mansmag.bsky.social, and Ulrike Schneider! Hope you’ll join us! statistikframjandet.se/cramersallsk... #statsky #statistics

The world is a mess but rejoice for this Eurovision 2025 entry from Sweden is fantastic eurovisionworld.com/eurovision/2...

In the Swedish Parliament, it took 24 years for the total number of women MPs ever in parliament to outnumber the number of male MPs with Andersson as a last name.

Are you interested in learning computational social science methods? If so, you now have the opportunity to apply for the second round of the Swedish Interdisciplinary Research School in Computational Social Science (SIRCSS) at @iasliu.bsky.social ⌛Apply by 31st of March! liu.se/en/research/...

A recording of a talk I gave at the Institute for Analytical Sociology at Linköping University, which is a pretty good summary of the "AI + humanities" work I completed last year. I loved that this audience had so many questions!

This is really bad. The US will become less and less relevant on the international stage.

Grateful for my topic modeling and word embeddings training, which made me suspicious of any output that "looks good" but for which I haven't seen any alternative outputs that might also "look good." Running a prompt and getting output that looks good isn't sufficient evidence for a paper.

Don't forget #AABI, the Symposium on Advances in Approximate Bayesian Inference is coming to Singapore!! Co-located #ICLR2025 Workshop Track: February 7, AoE Proceedings Track: February 7, AoE Fast Track: February 18 / March 14, AoE approximateinference.org/call/ #ML #Bayes #GenAI

Hi @neuripsconf.bsky.social, when will video of the invited talks be available online?