Lightnews — Scholar-powered news

Reposted by Daniel Gedon

Machine Learning in Science @mackelab.bsky.social · 8d

The Macke lab is well-represented at the @bernsteinneuro.bsky.social conference in Frankfurt this year! We have lots of exciting new work to present with 7 posters (details👇) 1/9

1 9 29

Reposted by Daniel Gedon

Richard Gao @rdgao.bsky.social · 16d

I've been waiting some years to make this joke and now it’s real:

I conned somebody into giving me a faculty job!

I’m starting as a W1 Tenure-Track Professor at Goethe University Frankfurt in a week (lol), in the Faculty of CS and Math

and I'm recruiting PhD students 🤗

a man wearing a white shirt and tie smiles in front of a window

ALT: a man wearing a white shirt and tie smiles in front of a window

media.tenor.com

30 31 180

Reposted by Daniel Gedon

sbi - Simulation-based inference @sbi-devs.bsky.social · 29d

From hackathon to release: sbi v0.25 is here! 🎉

What happens when dozens of SBI researchers and practitioners collaborate for a week? New inference methods, new documentation, lots of new embedding networks, a bridge to pyro and a bridge between flow matching and score-based methods 🤯

1/7 🧵

1 16 28

Reposted by Daniel Gedon

Seth Axen 🪓 @sethaxen.com · Jul 31

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.

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...

mlcolab.org

3 11

Daniel Gedon @danielged.bsky.social · Jul 23

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 🧵

Machine Learning in Science @mackelab.bsky.social · Jul 23

New preprint: SBI with foundation models!
Tired of training or tuning your inference network, or waiting for your simulations to finish? Our method NPE-PF can help: It provides training-free simulation-based inference, achieving competitive performance with orders of magnitude fewer simulations! ⚡️

2 18

Reposted by Daniel Gedon

Jakob Macke @jakhmack.bsky.social · Jul 23

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!!

Machine Learning in Science @mackelab.bsky.social · Jul 23

New preprint: SBI with foundation models!
Tired of training or tuning your inference network, or waiting for your simulations to finish? Our method NPE-PF can help: It provides training-free simulation-based inference, achieving competitive performance with orders of magnitude fewer simulations! ⚡️

3 16

Reposted by Daniel Gedon

Francis Bach @bachfrancis.bsky.social · Jul 13

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...

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...

arxiv.org

9 37

Reposted by Daniel Gedon

ML for Science @ml4science.bsky.social · May 22

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

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

4 20 74

Reposted by Daniel Gedon

Machine Learning in Science @mackelab.bsky.social · Apr 30

🎓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

Jobs - mackelab

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

www.mackelab.org

1 13 24

Reposted by Daniel Gedon

Machine Learning in Science @mackelab.bsky.social · Apr 25

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

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...

arxiv.org

2 4 25

Reposted by Daniel Gedon

sbi - Simulation-based inference @sbi-devs.bsky.social · Apr 4

🎉 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/...

4 13

Reposted by Daniel Gedon

Paul Häusner @paulhausner.bsky.social · Feb 14

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.

Jens Sjölund giving the opening remarks for the LoG meetup

1 2 7

Reposted by Daniel Gedon

Jonas @jonasgeiping.bsky.social · Feb 10

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 ...🐦‍⬛

1 7 23

Reposted by Daniel Gedon

Auguste Schulz @auschulz.bsky.social · Feb 3

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... 🧵

1 17 44

Reposted by Daniel Gedon

sbi - Simulation-based inference @sbi-devs.bsky.social · Jan 28

🙏 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! 🙌

8 18

Reposted by Daniel Gedon

sbi - Simulation-based inference @sbi-devs.bsky.social · Jan 14

🚀 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:🧵👇

1 5 20

Daniel Gedon @danielged.bsky.social · Dec 10

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

1

Daniel Gedon @danielged.bsky.social · Dec 10

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)

1 1

Daniel Gedon @danielged.bsky.social · Dec 10

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.

Machine Learning in Science @mackelab.bsky.social · Dec 9

Thrilled to announce we have three #NeurIPS2024 papers! Interested in simulating realistic neural data with diffusion models or recurrent neural networks, or in source distribution sorcery? Have a look 👇 1/4

1 2

Daniel Gedon @danielged.bsky.social · Dec 5

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

4

Daniel Gedon @danielged.bsky.social · Nov 28

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

1 2

Reposted by Daniel Gedon

sbi - Simulation-based inference @sbi-devs.bsky.social · Nov 27

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

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...

arxiv.org

1 22 60

Reposted by Daniel Gedon

Sebastian Dziadzio @dziadzio.bsky.social · Nov 19

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

Tübingen AI

Join the conversation

go.bsky.app

18 13 24

Daniel Gedon @danielged.bsky.social · Nov 18

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

4

Daniel Gedon @danielged.bsky.social · Nov 18

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!

1 1 12