iiinova — where your digital self keeps evolving

psteinb.bsky.social @psteinb.bsky.social · 09/06/2026

Had a blast running a workshop on “Open challenges in SBI” with @helmholtzai.bsky.social yesterday. #HAICON26 The great @deismic.bsky.social shared his views on the genesis of SBI & its future! Posters demoed breadth of SBI uses. Thanks to all who contributed! @sbi-devs.bsky.social @bayesflow.org

032

psteinb.bsky.social @psteinb.bsky.social · 04/05/2026

Deadline extended to May 6, 2026! Go and submit your experiences, please.

020

psteinb.bsky.social @psteinb.bsky.social · 24/04/2026

Don't forget to submit your poster idea on "Open challenges in SBI" at our workshop in Munich on June 8, 2026! 👉 events.hifis.net/event/3955/a... (deadline Apr 29, 2026) We are happy to have @deismic.bsky.social as the keynote speaker. Come join us and show us your #sbi work! @sbi-devs.bsky.social

lnkd.in

This link will take you to a page that’s not on LinkedIn

020

Reposted by @psteinb.bsky.social

Transactions on Machine Learning Research @tmlrorg.bsky.social · 12/02/2026

TMLR's 2025 annual report! The word of the year is growth: whether it's our number of submissions, published papers, or reviewers, pretty much everything has increased ~50%. EXCEPT: our review period, which is still shorter than NeurICMLR (91 vs 126 days) Read on for more! 1/n

1239

psteinb.bsky.social @psteinb.bsky.social · 28/01/2026

Alternatively, this idea might be a thing for LLMs.

000

psteinb.bsky.social @psteinb.bsky.social · 08/01/2026

Well, the incentives to withdraw after the submission deadline at ICLR are negligible. AFAIC, in both cases (withdrawal or rejection) author identities and paper content stay public. To me, this is a shortcoming of the rules.

020

psteinb.bsky.social @psteinb.bsky.social · 03/06/2025

The 0th day of #HAICON25 was a blast! I've had the plsre to participate in a tutorial on @sbi-devs.bsky.social by #AlinaBazarova and #JoseRoblero. @helmholtzai.bsky.social @fz-juelich.de In the afternoon, I ran a birds-of-a-feather on inverse problems in Helmholtz. @hzdr.bsky.social

140

Reposted by @psteinb.bsky.social

RAV @rav-ev.bsky.social · 01/06/2025

Heute vor 6 Jahren wurde Walter #Lübcke von einem Rechtsradikalen ermordet. Walter Lübcke steht für einen Konservatismus, der heute so sehr fehlt. Ein Konservatismus, der humane Werte, das Menschenrecht auf Asyl, offensiv verteidigt. Und der nicht opportunistisch Positionen der #NoAfD übernimmt.

141230281

psteinb.bsky.social @psteinb.bsky.social · 19/05/2025

From anecdotal evidence: same holds for the German schools, I have contact with.

000

psteinb.bsky.social @psteinb.bsky.social · 26/04/2025

@learnbayesstats.bsky.social if you like to explore the field of simulation-based inference more, people like @kylecranmer.bsky.social @glouppe.bsky.social @jakhmack.bsky.social or people of the @sbi-devs.bsky.social project could be really good next guests. Lots of things happening there.

050

psteinb.bsky.social @psteinb.bsky.social · 26/04/2025

I'm done listening. As always, @vincefort.bsky.social is a super knowledgeable guest and a good communicator. Some parts (PAC-Bayes, amortized inference) are sometimes hard to follow due to high density of math/terms. Still very enjoyable and fun episode.

220

psteinb.bsky.social @psteinb.bsky.social · 11/04/2025

🥳Great news, our JOSS paper "sbi reloaded" has been accepted! 🎉 This community lead by the fine folks of @sbi-devs.bsky.social is very welcoming and super fun to work with! I learn with every discussion I have. paper: joss.theoj.org/papers/10.21... review: github.com/openjournals...

github.com

[REVIEW]: sbi reloaded: a toolkit for simulation-based inference workflows · Issue #7754 · openjournals/joss-reviews

Submitting author: @janfb (Jan Boelts) Repository: https://github.com/sbi-dev/sbi Branch with paper.md (empty if default branch): joss-submission-2024 Version: v0.24.0 Editor: @boisgera Reviewers: ...

063

psteinb.bsky.social @psteinb.bsky.social · 11/04/2025

Interesting paper! Thanks for sharing. And from what it looks like, no prompt engineering was done. 🤷 This likely leaves the LLM performance under the table. 🐌 To me, this adds apples-oranges (🍎vs🍊) vibe to the robust & well-done stats analysis. Plus, only #openai models were tested. 🔍

020

Reposted by @psteinb.bsky.social

Riccardo Sapienza @riccard0.bsky.social · 03/04/2025

I also agree that openness is they key skill for a researcher www.nature.com/articles/s41...

nature.com

Openness guides discovery - Nature Biotechnology

Nature Biotechnology - Openness guides discovery

032

Reposted by @psteinb.bsky.social

Serge Belongie @serge.belongie.com · 30/03/2025

Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)

docs.google.com

NeurIPS participation in Europe

We seek to understand if there is interest in being able to attend NeurIPS in Europe, i.e. without travelling to San Diego, US. In the following, assume that it is possible to present accepted papers ...

6279161

psteinb.bsky.social @psteinb.bsky.social · 31/03/2025

Great initiative to see if Neurips could be replicated in Europe! 🇪🇺

000

psteinb.bsky.social @psteinb.bsky.social · 21/03/2025

It's been a blast, thanks to @sbi-devs.bsky.social ! This week's hackathon was phenomenal! 🙏 😍 The sbi hackathon welcomed about 25 people in Tübingen with contributions spanning the globe , e.g. 🇺🇸🇯🇵🇧🇪🇩🇪. Wanna see, what we did? Check out the PRs👇 github.com/sbi-dev/sbi/...

github.com

Pull requests · sbi-dev/sbi

sbi is a Python package for simulation-based inference, designed to meet the needs of both researchers and practitioners. Whether you need fine-grained control or an easy-to-use interface, sbi has ...

0146

psteinb.bsky.social @psteinb.bsky.social · 17/03/2025

This week will be an upskill from dusk till dawn: I'll be at the hackathon of @sbi-devs.bsky.social ! I am so much looking forward to meet and work with collaborators. Learn a lot and push #sbi forward. Can't wait to arrive🚆! @helmholtzai.bsky.social @tuebingen-ai.bsky.social #appliedAI

010

psteinb.bsky.social @psteinb.bsky.social · 15/03/2025

What a gem! Lovely article on our blind focus on accuracy in ML. Can't wait to get my hands on the references therein.

131

psteinb.bsky.social @psteinb.bsky.social · 14/03/2025

Working with #julia sometimes feels like playing minesweeper. Found a helpful library on the web 💣, punched in `add AwesomeLib` and boom 💥 I have to wait for 15min 🥱 to get all dependencies compiled and installed. #21century #oldhardware

000

psteinb.bsky.social @psteinb.bsky.social · 12/03/2025

I think, this is a great opportunity for anyone interested!

000

psteinb.bsky.social @psteinb.bsky.social · 10/03/2025

🗓️ No plans for Wednesday in Dresden, March 12, 5:30pm yet? Then please join us for a fun event on Computer Vision 💻 and Image analysis 🔬 🔭 ... there will be food for thought 🤯 , drinks 🥛 and pizza 🍕 . For the agenda and registration see the link below 👇 events.hifis.net/event/2248/

events.hifis.net

020

psteinb.bsky.social @psteinb.bsky.social · 06/03/2025

Jaw dropping results! Congrats @maxxxzdn.bsky.social for this wonderful treat. Happy to put this into play.

010

psteinb.bsky.social @psteinb.bsky.social · 21/02/2025

The @turingpost.bsky.social send out a survey to its readers. Starting the thing, I already felt excluded a bit 👇👇👇 But hey, being at #Neurips24 already gave be impression that being in academia and working on #AI is a niche profession these days. 🤷

010

psteinb.bsky.social @psteinb.bsky.social · 17/02/2025

Is it time to buy a new laptop, if #julia crashes with an OOM error during project build if it can only use 6GB of RAM? #PrematureOptimisation #InvertedReality

000

psteinb.bsky.social @psteinb.bsky.social · 13/02/2025

**Dresden Image Analysis Regulars** We're excited to invite you to a casual get-together where you'll dive into the latest news and advancements in #CV in #Dresden. ⌚ When? Mar 12, 2025, 5:30pm 🧭 Where? Oncoray in Dresden ✔️ How? Just register on the page below events.hifis.net/event/2248/

events.hifis.net

000

Reposted by @psteinb.bsky.social

Harry Thasarathan @hthasarathan.bsky.social · 07/02/2025

🌌🛰️🔭Wanna know which features are universal vs unique in your models and how to find them? Excited to share our preprint: "Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment"! arxiv.org/abs/2502.03714 (1/9)

15617

psteinb.bsky.social @psteinb.bsky.social · 23/01/2025

Great to see flow matching more and more in the wild!

010

Reposted by @psteinb.bsky.social

Paul Hagemann @yungbayesian.bsky.social · 23/01/2025

Our paper "PnP-Flow: Plug-and-Play Image Restoration with Flow Matching" has been accepted to ICLR 2025. Here a short explainer: We want to restore images (i.e., solve inverse problems) using pretrained velocity fields from flow matching. However, using change of variables is super costly.

1155

psteinb.bsky.social @psteinb.bsky.social · 21/01/2025

This is a lovely episode! I really liked it. I just would wish that citations of books or articles would appear in the show notes. This is often helpful if I am interested to dive deeper into a subject. Perhaps it would help others too?

000

psteinb.bsky.social @psteinb.bsky.social · 20/01/2025

Too bad, really. But I understand.

010

Reposted by @psteinb.bsky.social

Dr Charles Smith @smith-brocca.bsky.social · 09/01/2025

My letter in today's Guardian. Just asking, like. But I think we know the answer.

363170653079

psteinb.bsky.social @psteinb.bsky.social · 08/01/2025

What a great episode! Especially proud and happy to discover yet another alumni of @mpicbg.bsky.social ! 😀 🤗 Thanks so much for all these insights @hugobowne.bsky.social

241

Reposted by @psteinb.bsky.social

sbi - Simulation-based inference @sbi-devs.bsky.social · 30/12/2024

🎉 Just in time for the end of the year, we’ve released a new version of sbi! 📦 v0.23.3 comes packed with exciting features, bug fixes, and docs updates to make sbi smoother and more robust. Check it out! 👇 🔗 Full changelog: github.com/sbi-dev/sbi/...

1276

psteinb.bsky.social @psteinb.bsky.social · 06/01/2025

Thanks so much for the prompt reply. We will have a look and evaluate feasibility of perhaps teaching this and contributing back.

110

psteinb.bsky.social @psteinb.bsky.social · 06/01/2025

Great plot! 😍 A bit of clarification for the top entries: cs.CV = computer science->Computer Vision & Pattern Recognition cs.LG = CS->Machine Learning cs.CL = CS->Computation & Language quant-ph = Quantum Physics cs.RO = CS->Robotics cs.AI = CS->Artificial Intelligence

130

psteinb.bsky.social @psteinb.bsky.social · 06/01/2025

This looks interesting. If possible, it would be cool to have the code for the plot as #FOSS or publicly available in a citable fashion.

000

psteinb.bsky.social @psteinb.bsky.social · 06/01/2025

This was a great episode that I loved very much. @khinsen.net I'd be great to know the repositories behind the MOOCs! I'd love to have a closer look. #reproducibility

111

psteinb.bsky.social @psteinb.bsky.social · 18/12/2024

Sure did. Science wise we had extraordinary discussions, although the demands to AI in physics simulation and fluorescence microscopy are vastly different. But that makes it extra fun!

000