Episode 161 of the show is out, with @lacerbi.bsky.social ! We dive into all things neural processes, fast #Bayesian inferences, and LLMs -- hope you enjoy 🖖

Pierre-Simon Laplace@learnbayesstats.bsky.social · 3w ago

Episode 161 is out 🎧 In which @lacerbi.bsky.social explains why transformers are secretly neural processes, how his Amortized Conditioning Engine unifies inference and prediction, and why "amortize everything" needed a rethink. 🔗 learnbayesstats.com/episode/161-... #bayesian #bayesianinference

1/ Great chat with Alex Andorra aka @learnbayesstats.bsky.social about efficient inference, from amortized to surrogate-based approaches and a variety of related topics (prior-fitted networks, foundation models for inference and planning, etc.), many of which are neural processes in a trenchcoat.

Pierre-Simon Laplace@learnbayesstats.bsky.social · 3w ago

Episode 161 is out 🎧 In which @lacerbi.bsky.social explains why transformers are secretly neural processes, how his Amortized Conditioning Engine unifies inference and prediction, and why "amortize everything" needed a rethink. 🔗 learnbayesstats.com/episode/161-... #bayesian #bayesianinference

... and with the video. :) See thread for more info!

Luigi Acerbi@lacerbi.bsky.social · 2mo ago

1/ Amortized probabilistic methods like our amortized conditioning engine (ACE) can solve regression, simulator-based inference, optimization, active learning in a single forward pass... Try it in your browser & see all distributions change in real time! Links and more info👇

1/ Amortized probabilistic methods like our amortized conditioning engine (ACE) can solve regression, simulator-based inference, optimization, active learning in a single forward pass... Try it in your browser & see all distributions change in real time! Links and more info👇

Building the world's first nationwide AI model for healthcare, with high-quality registry data + next-gen machine learning. ELLIS Institute Finland's health moonshot is lifting off, with a boost from Business Finland's funding. Read more: www.ellisinstitute.fi/a-world-firs... 🤝 @fimm-uh.bsky.social

A world-first nationwide AI model will boost decision-making in healthcare | ELLIS Institute Finland

FINe-Health Foundry will use Finland’s national health databases as part of a ‘Swiss Army knife’ AI model for healthcare.

ellisinstitute.fi

Gemma 4 models are great, but what if they were even faster and keeping the same quality? we got you covered! Today we are releasing the Gemma 4 MTP models to help with that: blog.google/innovation-a...

Accelerating Gemma 4: faster inference with multi-token prediction drafters

An overview of how Multi-Token Prediction (MTP) drafters are making Gemma 4 models up to 3x faster at inference.

blog.google

1/ Wouldn't it be nice if you could perform Bayesian inference *efficiently* but also *reliably*? Amortized inference offers the former, while MCMC is often presented as the "gold standard" for accuracy and reliability. Enter the Amortized Bayesian Workflow...

Announcing Talkie: a new, open-weight historical LLM! We trained and finetuned a 13B model on a newly-curated dataset of only pre-1930 data. Try it below! with @alecrad.bsky.social and @nicklevin01.bsky.social

If you are at @iclr-conf.bsky.social, please go and have a chat with Yang Yang, @nasrullohloka.bsky.social or @conorhassan.bsky.social at our posters! (re-posted after fixing the time zone...)

Our researchers are at #ICLR2026 with the latest machine learning advances. Check them out April 23-27 in Rio de Janeiro and on our site ➡️ www.ellisinstitute.fi/ellis-instit... @iclr-conf.bsky.social @csaalto.bsky.social @univhelsinkics.bsky.social @ellis.eu @samikaski.bsky.social

If you're at ICLR and want to chat about amortised inference/neural processes or probabilistic ML more broadly, swing by my poster between 10:30-13:00 on Thursday (poster session 1) in Pavilion 3 at location #206. The poster is about NP-style learning in BNNs to find good priors.

1/ Another @iclr-conf.bsky.social paper thread! Do you want to make SOTA probabilistic predictions using transformers & your dataset is a *set* (not a sequence or time series), so you care about permutation invariance... but also efficiency? Keep reading, we have exactly what you need. 👇

1/ One of the issues of fully amortized inference / pretrained simulator-based inference is that you are stuck with the "prior" training distribution. What if you change your mind after training? In PriorGuide, one of our papers at ICLR this week, we allow the prior to be changed at runtime!

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.

Chengkun Li defends his PhD thesis on Surrogate-based methods for efficient Bayesian posterior computation | Faculty of Science | University of Helsinki

On Wednesday the 1st of April 2026, M.Eng. Chengkun Li defends his PhD thesis on Surrogate-based methods for efficient Bayesian posterior computation. The thesis is related to research done in the Mac...

helsinki.fi

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!

ML for Science@ml4science.bsky.social · 4mo ago

We're hiring a Scientific Director for our AI Methods & Software Hub in Tübingen! This is a unique opportunity to build and lead a central hub at the intersection of cutting-edge ML research and scientific applications. Deadline: 30 April 2026. More info: uni-tuebingen.de/en/128980#c2...

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!

Kit Yates@kityates.bsky.social · 10mo ago

If I was a tutoring company and I wanted to convince you that I could teach your kids maths, I would probably not have an advert that said “3=2” on it! That’s just me though.

The fitting ending for a great research journey!

Computer Science @ University of Helsinki@univhelsinkics.bsky.social · 5mo ago

Public PhD defence Chengkun Li @chengkunli.bsky.social: Surrogate-based methods for efficient Bayesian posterior computation 1.4.2026 at 13, University of Helsinki Main Building, Small Hall (F4050, Fabianinkatu 33, 4th floor) www.helsinki.fi/en/faculty-s...

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

BAMB! 2026 | Barcelona Summer School for Advanced Modeling of Behavior

Intensive training for experienced researchers in cognitive science, computational neuroscience and neuro-AI. Five interconnected modules, expert faculty, hands-on projects. July 12-23, 2026.

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...

Mark Riedl@markriedl.bsky.social · 6mo ago

This is why I always verify the results when I use AI

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

Diffusion Models in Simulation-Based Inference: A Tutorial Review

Diffusion models have recently emerged as powerful learners for simulation-based inference (SBI), enabling fast and accurate estimation of latent parameters from simulated and real data. Their score-b...

arxiv.org

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.

Daolang Huang@huangdaolang.bsky.social · 8mo ago

We jointly amortize Bayesian inference and active data acquisition within a single architecture. Excited to share our #NeurIPS2025 ✨Spotlight✨ paper “ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition”! www.huangdaolang.com/aline/

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)