Big day ahead for @chengkunli.bsky.social -- no pressure! www.helsinki.fi/en/faculty-s... @univhelsinkics.bsky.social Featuring @upicchini.bsky.social as our honoured Opponent, and your truly as the Custos. Looking forward to the big event.

We’re launching a new AI Methods & Software Hub in the ML cluster and are looking for a Director to build and lead it! Shape how ML/AI and software drive scientific discovery—in close collaboration with AI and domain scientists—within an extremely vibrant and collaborative ecosystem!

1. Dear colleagues, I finally got my first extremely well-crafted, highly manipulative nerd-sniping email from a prospective student whose core was 100% AI-assisted and that felt weird and I almost fell for it. We are in for a fun ride, aren't we?

Today NeurIPS is announcing our official satellite event in Paris. After responding to the call from Ellis following the success of EurIPS in December, we are pleased to reach a new milestone by joining forces with the NeurIPS organizing committee for the 2026 edition.

𝐷𝑖𝑓𝑓𝑒𝑟𝑒𝑛𝑡𝑙𝑦!

The fitting ending for a great research journey!

24-Hour Final Call for BAMB! 2026 ⏳ Join us in Barcelona (July 12–23) and learn from our expert faculty: @meganakpeters.bsky.social @marcelomattar.bsky.social @khamascience.bsky.social @thecharleywu.bsky.social Apply now: www.bambschool.org

Yes, this still happens! Before doing a manual check, I deploy agents to do the first check for me (literally a /doublecheck skill in Claude Code which I force to call automatically at the end of each task). This often catches issues, including once a totally fabricated MCMC analysis...

A bit of a delayed celebration, but happy that our three submitted papers were accepted at @iclr-conf.bsky.social 2026! This was a... complicated year for ICLR, but hopefully now we can focus on the science.

This game was 100% designed, made, and tested by Claude Code with one prompt to "make a complete Sierra-style adventure game with EGA-like graphics and text parser, with 10-15 minutes of gameplay." I gave two prompts to play test the game & deploy it. Play: enchanted-lighthouse-game.netlify.app

1/ Excited to share our new work published in Transactions on Machine Learning Research (TMLR), Stacking Variational Bayesian Monte Carlo (S-VBMC)!

I'd like to propose the following norm for peer review of papers. If a paper shows clear signs of LLM-generated errors that were not detected by the author, the paper should be immediately rejected. My reasoning: 1/ #ResearchIntegrity

What an amazing Yule gift from @stefanradev.bsky.social & colleagues: a tour-de-force tutorial on diffusion models for simulator-based inference. This is one of the most comprehensive and useful review/tutorials I have ever seen -- a must read! Kudos to all the authors! arxiv.org/abs/2512.20685

EurIPS was pretty fun! Thanks to @lacerbi.bsky.social , @conorhassan.bsky.social , and all organizers of the Amortized ProbML team for the great workshop and for inviting me as a speaker! 🙌 Also great to be able to present our spotlight paper on sparsity on the main stage 😍

Tobias Niehues @tobnie.bsky.social is presenting our work with @dominikstrb.bsky.social 'Amortized Bayesian decision-making for inferring decision-making parameters from behavior' at the Amortized ProbML Workshop and the @ellis.eu UnConference. Please come by our poster!

1/ Very happy with this spotlight paper at @neuripsconf.bsky.social where we continue our "Amortize Everything" agenda. After the Amortized Conditioning Engine (Chang et al., AISTATS, 2025) which amortizes all sorts of inference tasks, here with ALINE we amortize both inference & design.

I’m super excited to present our new work in #Eurips2025 and #Neurips2025! We developed FNOPE: a new simulation-based inference (SBI) method which excels at inferring function-valued parameters! Paper: openreview.net/forum?id=yB5... Code: github.com/mackelab/fnope (1/9)

Are there non-predatory for-profit publishers? This "thing" clearly never went through peer review despite what they say. Well, maybe it did go through "peer review": LLM reviewers reviewed an LLM-written paper, fair enough.

If you are at ELLIS UnConference on Dec 2 (pre @euripsconf.bsky.social ), join us at our Amortized ProbML workshop! Come for our great speakers: @paulbuerkner.com Yingzhen Li @davidruegamer.bsky.social @liza-semenova.bsky.social & poster session; stay for our hot takes on amortized probML!

Very interesting work on emerging object-binding representations in vision transformers by @kordinglab.bsky.social arxiv.org/abs/2510.24709 This might seem an oddly specific property but the good ol' binding problem reflects a fundamental primitive of cognition, epistemology, you name it.

I answered in thread but it might be of interest. My current advice is to use the stderr of the median (bootstrapped), with a separate metric for reliability if needed. The latter is less standard - we have been reporting e.g. 80% perf quantile and its stderr (bootstrapped).

Claude, GPT-5, Gemini, and Kimi: "write me a horror story done entirely in the dedications to six books (you can give me the title and author of each book as well)" ChatGPT and Claude did pretty well in different ways. Kimi did the usual (sounds good but meaning falls apart).

**Submission DL extended to Oct 25!** You are still in time to submit a short abstract on amortized (simulator-based) inference (SBI), neural processes, prior-fitted networks (PFNs), amortized experimental design, foundation models, and related applications. Call: sites.google.com/view/amortiz...

Reminder that Amortized inference Workshop submissions at the ELLIS Unconference are still open until **Oct 16, 2025**. Only a short abstract (½ page), so go ahead! Workshop: Dec 2, 2025, co-located with EurIPS. Website: sites.google.com/view/amortiz...

Do you like to train neural networks to solve all your nasty probabilistic inference and sequential design problems? Do you love letter salads such as NPs, PFNs, NPE, SBI, BED? Then no place is better than the Amortized ProbML workshop we are organizing at #ELLIS UnConference.

And new paper out: Pleias 1.0: the First Family of Language Models Trained on Fully Open Data How we train an open everything model on a new pretraining environment with releasable data (Common Corpus) with an open source framework (Nanotron from HuggingFace). www.sciencedirect.com/science/arti...

@gershbrain.bsky.social and I have a new paper in PLOS Comp Bio! We study how two cognitive constraints—action consideration set size & policy complexity—interact in context-dependent decision making, and how humans exploit their synergy to reduce behavioral suboptimality. osf.io/preprints/ps...

Posterior predictive checking of binary, categorical and many ordinal models with bar graphs is useless. Even the simplest models without covariates usually have such intercept terms that category specific probabilities are learned perfectly. Can you guess which model, 1 or 2, is misspecifed? 1/4

Remember to follow the official rebuttal guide.

Superlative initiative! Massive kudos to the organisation team for getting this going in such a short time!

The singularity is awesome

New blog post! You can train a neural network to *just do things* -- such as *predict the optimum of a function*. But how do you get a big training dataset of "functions with known optima"? Read the blog post to find out! (link 👇)

That's a pity. I am not a fan of this place either due to the lack of interesting AI/ML discussions, and that's the only reason I still set foot in Mordor. A shiver goes through my spine at the thought that LinkedIn might be a viable alternative.

sometimes you need to exorcise images from your mind

We propose Neurosymbolic Diffusion Models! We find diffusion is especially compelling for neurosymbolic approaches, combining powerful multimodal understanding with symbolic reasoning 🚀 Read more 👇

If you add "also Cthulhu-y" to the prompt, the results are pretty great.

I had to do it

TIL so many missed opportunities for biology and neuroscience textbooks. He should have had a guest appearance in the League of Extraordinary Gentlemen. (The man on the right is Santiago Ramón y Cajal.)

@huangdaolang.bsky.social will be presenting our work tomorrow on pretrained/amortized transformers for all sorts of inference tasks, go say hi! #AISTATS2025 Poster session 1 Place: Hall A-E Time: Sat 3 May 3 p.m. — 6 p.m. Poster number: 23

Have you thought that in computer memory model weights are given in terms of discrete values in any case. Thus, why not do probabilistic inference on the discrete (quantized) parameters. @trappmartin.bsky.social is presenting our work at #AABI2025 today. [1/3]

We just kicked off #AABI2025 at NTU in Singapore! We're livestreaming the talks here: timrudner.com/aabi2025! Schedule: approximateinference.org/schedule/ #ICLR2025 #ProbabilisticML

I asked "on the other platform" what were the most important improvements to the original 2017 transformer. That was quite popular and here is a synthesis of the responses:

I’ll be at the AABI symposium tomorrow. Looking forward to seeing everyone there!

1/ If you are at ICLR / AABI / AISTATS, check out work from our lab and collaborators on *inference everywhere anytime all at once*! Go talk to my incredible PhD students @huangdaolang.bsky.social & @chengkunli.bsky.social + amazing collaborator Severi Rissanen. @univhelsinkics.bsky.social FCAI

PhD Timeline xkcd.com/3081

🎉 Presenting “Streamlining Prediction in Bayesian Deep Learning” at #ICLR2025! We replace MC estimation with local linearisation + Gaussian approximations → analytic posterior predictive in one forward pass. Fast, performs well, and scales to ViT. 📄 arxiv.org/abs/2411.18425 💻 github.com/AaltoML/SUQ

Reminder that the next OWABI seminar www.warwick.ac.uk/owabi is scheduled on Thursday the 24th April at 11am UK time. Our next speaker is @ayushbharti.bsky.social (Aalto University), who will talk about "Cost-aware simulation-based inference".

1/10🔥 New paper alert in #AABI2025 Proceedings! Normalizing Flow Regression (NFR) — an offline Bayesian inference method. What if you could get a full posterior using *only* the evaluations you *already* have, maybe from optimization runs?

1/ We asked GPT-4.5 -- allegedly the model with the best sense of humor, according to the site we do not talk about here -- to write a comic about our recent AISTATS paper on the Amortized Conditioning Engine (ACE). Then gpt-4o drew it. You judge the result... (text continues 👇)

Llama 4 was a messy release: unreleased finetunes boosting scores, rumors of training on test, released on a weekend, etc As (open) models are commoditized / competition grows, what is the role of Meta's Llama efforts in the future? Should they continue?