Sign in

Marvin Schmitt

@marvin-schmitt.com
6.4K followers 540 following 644 posts

⛵️ Research Scientist @ Midjourney 🇪🇺 Member @ellis.eu 🤖 Generative NNs, Deep Learning, ProbML, Simulation Intelligence 🎓 PhD+MSc Computer Science, MSc Psychology 🏡 marvin-schmitt.com

PostsRepliesMedia
Reposted by Marvin Schmitt
Chengkun Li @chengkunli.bsky.social · 30/04/2026
😀 Enter the amortized Bayesian workflow from here 👉 pipme.github.io/amortized-Ba... Huge thanks to my great collaborators: @avehtari.bsky.social, @paulbuerkner.com, @stefanradev.bsky.social, @lacerbi.bsky.social, @marvin-schmitt.com!
pipme.github.io
Amortized Bayesian Workflow
Adaptive Bayesian workflow combining amortized inference with PSIS and MCMC diagnostics.
0219
Reposted by Marvin Schmitt
Luigi Acerbi @lacerbi.bsky.social · 30/04/2026
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...
12710
Reposted by Marvin Schmitt
Aki Vehtari @avehtari.bsky.social · 09/02/2026
Posterior-SBC now also with peer-review stamp in Statistics and Computing doi.org/10.1007/s112... (update your bib files)
doi.org
Posterior SBC: simulation-based calibration checking conditional on data - Statistics and Computing
Simulation-based calibration checking (SBC) refers to the validation of an inference algorithm and model implementation through testing self-consistency with repeated inference on data simulated from ...
1285
Marvin Schmitt @marvin-schmitt.com · 30/01/2026
I took a Waymo today. I had some initial safety concerns, but I felt reassured when I saw the driver had their seat belt fastened.
0110
Marvin Schmitt @marvin-schmitt.com · 29/01/2026
Sunrise in San Francisco ☀️
1110
Marvin Schmitt @marvin-schmitt.com · 26/01/2026
ICLR decisions are out! #ICLR #ICLR2026 @iclr-conf.bsky.social
060
Marvin Schmitt @marvin-schmitt.com · 21/10/2025
Autumn in Helsinki‘s urban woodlands 🇫🇮❤️
071
Marvin Schmitt @marvin-schmitt.com · 12/10/2025
Is this the real life? Is this just fantasy?
080
Reposted by Marvin Schmitt
Michael Kirchhof @mkirchhof.bsky.social · 01/10/2025
Many treat uncertainty = a number. At Apple, we're rethinking this: LLMs should output strings that reveal all information of their internal distributions. We find that Reasoning, SFT, CoT can't do it - yet. To get there, we introduce the SelfReflect benchmark. arxiv.org/pdf/2505.20295
3336
Reposted by Marvin Schmitt
Shubhendu Trivedi @shubhendu.bsky.social · 01/09/2025
Natural idea. Looks like a nice paper too. arxiv.org/abs/2508.21184
arxiv.org
BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design
We propose a general-purpose approach for improving the ability of Large Language Models (LLMs) to intelligently and adaptively gather information from a user or other external source using the framew...
1256
Reposted by Marvin Schmitt
NumFOCUS @numfocus.bsky.social · 13/08/2025
BayesFlow released version 2.0.4, presented numerous findings at the MathPsych/ICCM 2025 conference at Ohio State University, and expanded its contributor list to 25 active members! Congrats to BayesFlow on all these new huge accomplishments!
0123
Marvin Schmitt @marvin-schmitt.com · 17/07/2025
This is a fantastic European initiative to offer an alternative attendance option to the largest AI conference 🇪🇺✨
060
Marvin Schmitt @marvin-schmitt.com · 22/06/2025
The S in Sunday stands for Sinnamon buns; sourdough-based of course 🧡
080
Marvin Schmitt @marvin-schmitt.com · 21/06/2025
Extending my artisanal repertoire: Homemade pickled red onions 💜
1110
Marvin Schmitt @marvin-schmitt.com · 20/06/2025
My 5-year-old asked me whether there are "things that only have one side". Me: *takes a deep breath* Actually …
3321
Marvin Schmitt @marvin-schmitt.com · 18/06/2025
This is a fantastic read about Cameron‘s work in developer advocacy. The post is not only valuable for dedicated devrel folks, but also has many insights for all open source developers. Check it out 👇
023
Marvin Schmitt @marvin-schmitt.com · 18/06/2025
We’re going Italian! 🇮🇹 Sourdough focaccia with rosemary and cherry tomatoes 🌿🍅
2170
Reposted by Marvin Schmitt
Marvin Schmitt @marvin-schmitt.com · 03/06/2025
I'm putting together a visualization workshop for PhD students 🧪📊 Looking for examples of the good, the bad, and the ugly. Do you have examples for a great (or awful) figure? Plots and overview/explainer figures are welcome. Thanks 🧡
11369
Marvin Schmitt @marvin-schmitt.com · 08/06/2025
Back to a basic wheat bread. I‘ve been told that it pairs well with chocolate spread 👀
090
Marvin Schmitt @marvin-schmitt.com · 06/06/2025
Today we’re serving a traditional Finnish rye bread with crispy crust and fine crumb 🇫🇮
1140
Marvin Schmitt @marvin-schmitt.com · 04/06/2025
For my next trick… Traditional rye/wheat mix bread ✨
280
Marvin Schmitt @marvin-schmitt.com · 04/06/2025
My first attempt at sourdough bread went surprisingly well. Any tips or advice from the bread baking pros on here?
Close-up of a sourdough breadTop-down shot of a sourdough bread
7200
Marvin Schmitt @marvin-schmitt.com · 03/06/2025
I'm putting together a visualization workshop for PhD students 🧪📊 Looking for examples of the good, the bad, and the ugly. Do you have examples for a great (or awful) figure? Plots and overview/explainer figures are welcome. Thanks 🧡
11369
Reposted by Marvin Schmitt
BayesFlow @bayesflow.org · 30/05/2025
🧠 Check out the classic examples from Bayesian Cognitive Modeling: A Practical Course (Lee & Wagenmakers, 2013), translated into step-by-step tutorials with BayesFlow! Interactive version: kucharssim.github.io/bayesflow-co... PDF: osf.io/preprints/ps...
kucharssim.github.io
Introduction – Amortized Bayesian Cognitive Modeling
03314
Marvin Schmitt @marvin-schmitt.com · 22/05/2025
Because it wasn't annoying enough that my domain was down for 35 days... Now a bot network farm automatically bought my old personal domain the second it got released. Odds are that they will (1) host explicit+spam content on the website and/or (2) try to sell it back to me for an ungodly price.
100
Marvin Schmitt @marvin-schmitt.com · 06/05/2025
Clouded mind. (created with #midjourney)
Image showing a formation of clouds and sun that assumes the shape of a head (i.e., a clouded mind)
030
Marvin Schmitt @marvin-schmitt.com · 06/05/2025
If you’re into bluesy tunes and parody lyrics, check out our cover song! 🎶 There ain’t no cure for the PhD blues 🎶
021
Marvin Schmitt @marvin-schmitt.com · 16/04/2025
My domain is down. In the meantime, you can find my website at: marvinschmitt.github.io
marvinschmitt.github.io
Marvin Schmitt
Computer Scientist & Psychologist | PhD researcher | Deep Learning, Data Science, Research
010
Marvin Schmitt @marvin-schmitt.com · 03/04/2025
With his research on Bayesian Deep Learning, Vincent has his finger on the pulse of the time in modern AI 🤖 I’m already looking forward to tune in to this conversation between @alex-andorra.bsky.social and @vincefort.bsky.social. … and it also comes with a video version! 👇 youtu.be/3hYYGiucS0U
youtu.be
#129 Bayesian Deep Learning & AI for Science with Vincent Fortuin
YouTube video by Learning Bayesian Statistics
2142
Marvin Schmitt @marvin-schmitt.com · 31/03/2025
Any advice on how to design a pretty cover for a PhD thesis? 📔 #AcademicSky
461
Marvin Schmitt @marvin-schmitt.com · 31/03/2025
Fantastic initiative by @serge.belongie.com and Søren Hauberg 🇪🇺🇩🇰 Please take a moment to answer through the poll below and share in your networks! 👇
0195
Reposted by Marvin Schmitt
Marvin Schmitt @marvin-schmitt.com · 27/03/2025
Official press release from the website of the Finnish Research Council: www.aka.fi/en/about-us/...
aka.fi
RCF preparing call for universities to invite foreign researchers to Finland
The Research Council of Finland (RCF) is planning a new funding call to help universities recruit international experts to Finland. The call would be part of the RCF funding scheme that strengthens un...
0157
Marvin Schmitt @marvin-schmitt.com · 27/03/2025
I defended my PhD last week ✨ Huge thanks to: • My supervisors @paulbuerkner.com @stefanradev.bsky.social @avehtari.bsky.social 👥 • The committee @ststaab.bsky.social @mniepert.bsky.social 📝 • The institutions @ellis.eu @unistuttgart.bsky.social @aalto.fi 🏫 • My wonderful collaborators 🧡 #PhDone 🎓
Image of a graduating PhD student in the trending Studio Ghibli style.
181202
Marvin Schmitt @marvin-schmitt.com · 19/03/2025
Making some final adjustments to my strategy for tomorrow's PhD defense. As always, @xkcd.com is very helpful as inspiration ⚔️
A black and white XKCD-style comic showing a stick figure presenter brandishing a sword and yelling "AAAAAAA!!!" next to a projection screen. Two stick figures sit at a table with microphones looking concerned. The caption reads "THE BEST THESIS DEFENSE IS A GOOD THESIS OFFENSE." The presenter appears to be taking an aggressive approach to their thesis defense, literally going on the offensive.
729210
Reposted by Marvin Schmitt
Jeff Dean @jeffdean.bsky.social · 13/03/2025
Introducing our Gemma 3 open models, the most capable models that you can run on a single GPU or TPU. Multimodal, multilingual, 128k context length, and exceeds quality of other open models that are an order of magnitude larger in terms of hardware footprint. 🎉 blog.google/technology/d...
blog.google
Introducing Gemma 3: The most capable model you can run on a single GPU or TPU
Today, we're introducing Gemma 3, our most capable, portable and responsible open model yet.
213820
Reposted by Marvin Schmitt
ELLIS @ellis.eu · 08/03/2025
This International Women's Day, we're challenging you to #AccelerateAction to get more women & girls in AI and machine learning. It's your turn! Reply with a suggestion for action or tag an inspiring female scientist. #IWD2025 #AccelerateAction #WomenInELLIS
1185
Reposted by Marvin Schmitt
Aki Vehtari @avehtari.bsky.social · 04/03/2025
New paper Säilynoja, Johnson, Martin, and Vehtari, "Recommendations for visual predictive checks in Bayesian workflow" teemusailynoja.github.io/visual-predi... (also arxiv.org/abs/2503.01509)
Abstract
Introduction
A key step in the Bayesian workflow for model building is the graphical assessment of model predictions, whether these are drawn from the prior or posterior predictive distribution. The goal of these assessments is to identify whether the model is a reasonable (and ideally accurate) representation of the domain knowledge and/or observed data. There are many commonly used visual predictive checks which can be misleading if their implicit assumptions do not match the reality. Thus, there is a need for more guidance for selecting, interpreting, and diagnosing appropriate visualizations. As a visual predictive check itself can be viewed as a model fit to data, assessing when this model fails to represent the data is important for drawing well-informed conclusions.

Demonstration
We present recommendations for appropriate visual predictive checks for observations that are: continuous, discrete, or a mixture of the two. We also discuss diagnostics to aid in the selection of visual methods. Specifically, in the detection of an incorrect assumption of continuously-distributed data: identifying when data is likely to be discrete or contain discrete components, detecting and estimating possible bounds in data, and a diagnostic of the goodness-of-fit to data for density plots made through kernel density estimates.

Conclusion
We offer recommendations and diagnostic tools to mitigate ad-hoc decision-making in visual predictive checks. These contributions aim to improve the robustness and interpretability of Bayesian model criticism practices.
46320
Marvin Schmitt @marvin-schmitt.com · 17/02/2025
I can highly recommend this CodeRefinery workshop on reproducible research tooling 🔨 Last year, I took one of their 3-day workshop about Slurm HPC clusters. It was well-planned, beautifully executed, and I learned *a lot*. Check out the details 👇
062
Marvin Schmitt @marvin-schmitt.com · 11/02/2025
It’s great to see that European AI is getting such tailwind on a political level 🇪🇺 InvestAI is a huge endorsement of the ELLIS mission to position Europe at the frontier of AI research which is sustainable on many levels.
030
Marvin Schmitt @marvin-schmitt.com · 11/02/2025
Amortized inference for finite mixture models ✨ The amortized approximator from BayesFlow closely matches the results of expensive-but-trustworthy HMC with Stan. Check out the preprint and code by @kucharssim.bsky.social and @paulbuerkner.com👇
0171
Reposted by Marvin Schmitt
Nathaniel Haines @natehaines.bsky.social · 07/02/2025
1/3 IMO, this method gets back to a more common way of testing parameter recovery. Back in the day, I would typically fit my model to data, generate posterior predictions using the fitted posterior means, then re-fit the model to the posterior predictions to see if I can recover those means well.
142
Reposted by Marvin Schmitt
BayesFlow @bayesflow.org · 28/01/2025
Join us this Thursday for a talk on efficient mixture and multilevel models with neural networks by @paulbuerkner.com at the new @approxbayesseminar.bsky.social!
0124
Reposted by Marvin Schmitt
Approximate Bayes Seminar @approxbayesseminar.bsky.social · 27/01/2025
A reminder of our talk this Thursday (30th Jan), at 11am GMT. Paul Bürkner (TU Dortmund University), will talk about "Amortized Mixture and Multilevel Models". Sign up at listserv.csv.warwick... to receive the link.
0186
Marvin Schmitt @marvin-schmitt.com · 24/01/2025
Bridging LLMs and uncertainty quantification is one of the most interesting open problems in modern deep learning. Follow Michael‘s work for some bleeding-edge research on this topic 👀👇
0120
Marvin Schmitt @marvin-schmitt.com · 23/01/2025
This upcoming ICLR paper solves inverse problems in imaging with a creative combination of flow matching and the plug-and-play framework. Check out Paul‘s explainer thread 👇🧵
080
Marvin Schmitt @marvin-schmitt.com · 16/01/2025
I’ve been using Scholar Inbox for a while now and I absolutely love it. If you don’t use it yet, check it out now! 👉 www.scholar-inbox.com
0121
Reposted by Marvin Schmitt
Serge Belongie @serge.belongie.com · 14/01/2025
Exciting new partnership in AI & Life Sciences announced today in Brussels
1184
Marvin Schmitt @marvin-schmitt.com · 14/01/2025
Paul Bürkner (@paulbuerkner.com) will talk about amortized Bayesian multilevel models in the next Approximate Bayes Seminar on January 30 ⭐️ Sign up to the seminar’s mailing list below to get the meeting link 👇
1214
Reposted by Marvin Schmitt
Hannes Stark @hannes-stark.bsky.social · 05/01/2025
Tomorrow, in the reading group, Johannes Brehmer will present his paper "Does equivariance matter at scale?" arxiv.org/abs/2410.23179 Join us on zoom at 12pm ET / 6pm CET: portal.valencelabs.com/logg
0274
Reposted by Marvin Schmitt
Miles Cranmer @milescranmer.bsky.social · 02/01/2025
🚨 FINAL REMINDER 🚨: Multiple Postdoc and PhD positions in our AI + Physics cluster in DAMTP, Cambridge! Deadlines: - Postdoc: Jan 5th (Sunday) - PhD: Jan 7th (Tuesday) More info below – Please share with researchers and students who might be interested in joining us!
0165