Daniel Gedon

A retrospective on the 2025 SBI Hackathon You walk into a bakery, take one bite of a still-warm pastry, and think: “Whoa - there’s rye flour, a hint of orange zest, maybe cardamom… and is that buckwheat honey?” From that single taste you begi...

Sharing this here a bit late, but @vstaros.bsky.social and I wrote a little something about our experience contributing to the @sbi-devs.bsky.social (simulation-based inference) hackathon. @mlcolab.org @mackelab.bsky.social

We were obviously very hungry while writing.

31.07.2025 11:54 — 👍 10    🔁 3    💬 0    📌 0

My first paper on simulation-based inference (SBI) as part of @mackelab.bsky.social!

Exciting work on adapting state-of-the-art foundation models for posterior estimation. Almost plug-and-play, and surprisingly effective.

Paper/code in thread below 🧵

23.07.2025 18:45 — 👍 17    🔁 2    💬 0    📌 0

I have been genuinely amazed how well tabpfn works as a density estimator, and how helpful this is for SBI ... Great work by @vetterj.bsky.social, Manuel and @danielged.bsky.social!!

23.07.2025 14:37 — 👍 16    🔁 3    💬 0    📌 0

A Collectivist, Economic Perspective on AI Information technology is in the midst of a revolution in which omnipresent data collection and machine learning are impacting the human world as never before. The word "intelligence" is being used as...

What if AI isn’t about building solo geniuses, but designing social systems?
Michael Jordan advocates blending ML, economics, and uncertainty management to prioritize social welfare over mere prediction.
A must-read rethink.
arxiv.org/abs/2507.062...

13.07.2025 13:10 — 👍 36    🔁 9    💬 0    📌 0

The members of the Cluster of Excellence "Machine Learning: New Perspectives for Science" raise their glasses and celebrate securing another funding period.

We're super happy: Our Cluster of Excellence will continue to receive funding from the German Research Foundation @dfg.de ! Here’s to 7 more years of exciting research at the intersection of #machinelearning and science! Find out more: uni-tuebingen.de/en/research/... #ExcellenceStrategy

22.05.2025 16:23 — 👍 74    🔁 20    💬 4    📌 5

Jobs - mackelab The MackeLab is a research group at the Excellence Cluster Machine Learning at Tübingen University!

🎓Hiring now! 🧠 Join us at the exciting intersection of ML and Neuroscience! #AI4science
We’re looking for PhDs, Postdocs and Scientific Programmers that want to use deep learning to build, optimize and study mechanistic models of neural computations. Full details: www.mackelab.org/jobs/ 1/5

30.04.2025 13:43 — 👍 23    🔁 13    💬 1    📌 0

Compositional simulation-based inference for time series Amortized simulation-based inference (SBI) methods train neural networks on simulated data to perform Bayesian inference. While this strategy avoids the need for tractable likelihoods, it often requir...

Excited to present our work on compositional SBI for time series at #ICLR2025 tomorrow!

If you're interested in simulation-based inference for time series, come chat with Manuel Gloeckler or Shoji Toyota

at Poster #420, Saturday 10:00–12:00 in Hall 3.

📰: arxiv.org/abs/2411.02728

25.04.2025 08:53 — 👍 25    🔁 4    💬 2    📌 1

🎉 Exciting news! We are lauching an sbi office hour!

Join the sbi developers Thursdays 09:45-10:15am CET via Zoom (link: sbi Discord's "office hours" channel).

Get guidance on contributing, explore sbi for your research, or troubleshoot issues. Come chat with us! 🤗

github.com/sbi-dev/sbi/...

04.04.2025 07:36 — 👍 13    🔁 4    💬 0    📌 1

Jens Sjölund giving the opening remarks for the LoG meetup

Audience of the LoG meetup

Poster session at the LoG meetup

Organizing team of the LoG meetup

This week, we had the pleasure of hosting Sweden’s first @logconference.bsky.social meetup at Uppsala University! Over two days, we brought together researchers and industry professionals working at the intersection of machine learning, graphs, and geometry.

14.02.2025 09:32 — 👍 7    🔁 2    💬 1    📌 0

Ok, so I can finally talk about this!

We spent the last year (actually a bit longer) training an LLM with recurrent depth at scale.

The model has an internal latent space in which it can adaptively spend more compute to think longer.

I think the tech report ...🐦‍⬛

10.02.2025 16:47 — 👍 23    🔁 7    💬 1    📌 1

1) Some exciting science in turbulent times:

How do mice distinguish self-generated vs. object-generated looming stimuli? Our new study combines VR and neural recordings from superior colliculus (SC) 🧠🐭 to explore this question.

Check out our preprint doi.org/10.1101/2024... 🧵

03.02.2025 19:19 — 👍 44    🔁 17    💬 1    📌 1

🙏 Please help us improve the SBI toolbox! 🙏

In preparation for the upcoming SBI Hackathon, we’re running a user study to learn what you like, what we can improve, and how we can grow.

👉 Please share your thoughts here: forms.gle/foHK7myV2oaK...

Your input will make a big difference—thank you! 🙌

28.01.2025 15:18 — 👍 18    🔁 8    💬 0    📌 1

🚀 Join the 4th SBI Hackathon! 🚀
The last SBI hackathon was a fantastic milestone in forming a collaborative open-source community around SBI. Be part of it this year as we build on that momentum!

📅 March 17–21, 2025
📍 Tübingen, Germany or remote
👉 Details: github.com/sbi-dev/sbi/...

More Info:🧵👇

14.01.2025 15:58 — 👍 20    🔁 5    💬 1    📌 2

Ruoqi Zhang, Ziwei Luo et al. Entropy-regularized diffusion policy with q-ensembles for offline reinforcement learning.
Poster #6305 (West; Wed 11 Dec 11PT)

10.12.2024 16:42 — 👍 1    🔁 0    💬 0    📌 0

From my PhD group:

Sofia Ek, and Dave Zachariah. Externally Valid Policy Evaluation from Randomized Trials Using Additional Observational Data.
Poster #6609 (West; Wed 11 Dec 4.30PT)

10.12.2024 16:42 — 👍 1    🔁 0    💬 1    📌 0

Check out all three NeurIPS papers from our lab! Cool stuff from simulating neural data to source distribution estimation.

Also, great work from my PhD group: papers on (1) generalizable policy evaluations from trial data and (2) entropy-regularized diffusion policies for RL.

10.12.2024 16:42 — 👍 2    🔁 0    💬 1    📌 0

@mackelab.bsky.social is always well represented and there to entertain

05.12.2024 07:39 — 👍 4    🔁 0    💬 0    📌 0

Congrats, so well deserved! 🥳
Curious what will come out of the lab!!

28.11.2024 11:11 — 👍 2    🔁 0    💬 1    📌 0

sbi reloaded: a toolkit for simulation-based inference workflows Scientists and engineers use simulators to model empirically observed phenomena. However, tuning the parameters of a simulator to ensure its outputs match observed data presents a significant challeng...

The sbi package is growing into a community project 🌍 To reflect this and the many algorithms, neural nets, and diagnostics that have been added since its initial release, we have written a new software paper 📝 Check it out, and reach out if you want to get involved: arxiv.org/abs/2411.17337

27.11.2024 11:17 — 👍 60    🔁 22    💬 1    📌 4

Tübingen AI Join the conversation

Here's a fledgling starter pack for the AI community in Tübingen. Let me know if you'd like to be added!

go.bsky.app/NFbVzrA

19.11.2024 13:14 — 👍 24    🔁 13    💬 18    📌 0

You can already find many from our group here.
@jakhmack.bsky.social @rdgao.bsky.social @deismic.bsky.social @auschulz.bsky.social @matthijspals.bsky.social @jkapoor.bsky.social @gmoss13.bsky.social

18.11.2024 19:57 — 👍 4    🔁 0    💬 0    📌 0

Let's start this blue journey 🦋
I recently started as a postdoc in AI for science in Tübingen at @mackelab.bsky.social. I will focus on model discovery, but I am more broadly interested in developing ML methods for science for some hopeful breakthroughs!

18.11.2024 19:57 — 👍 12    🔁 1    💬 1    📌 0