We are organizing the Sim2Science workshop at @neuripsconf.bsky.social! 🔬 Simulators like AlphaFold, VASP, and JOREK power modern science. But they're all imperfect. So, how do we do better science with imperfect models? sim2science.com

We are excited to announce up to 3 PhD positions in a new project on using ML for "Extracting Probabilistic Representations in Exponential Quantum Spaces" (EXPRESSO) with @philipphennig.bsky.social , @mariokrenn.bsky.social, Igor Lesanovsky, @gmartius.bsky.social in the @ml4science.bsky.social.

Tomorrow, I will be presenting our work on a probabilistic framework for LLM-based model discovery at ICML! Come by and say hello if you're around!

Machine Learning in Science@mackelab.bsky.social · last mo.

ModelSMC: we frame LLM-based scientific model discovery as Bayesian inference. Sequential Monte Carlo over executable model structures, with the LLM as a probabilistic proposal mechanism. 📍 Wed Jul 8, at 2:30–4:15 PM KST in Hall A #3512 📄 arxiv.org/abs/2602.18266 🧵 bsky.app/profile/mack...

I am at ICML and present our work on LLM-based model discovery with a probabilistic view. Let me know if you are around and want to chat! I'm happy to discuss ideas.

Machine Learning in Science@mackelab.bsky.social · last mo.

ModelSMC: we frame LLM-based scientific model discovery as Bayesian inference. Sequential Monte Carlo over executable model structures, with the LLM as a probabilistic proposal mechanism. 📍 Wed Jul 8, at 2:30–4:15 PM KST in Hall A #3512 📄 arxiv.org/abs/2602.18266 🧵 bsky.app/profile/mack...

This project closes a loop for me personally. I first learned about SMC almost 7 years ago. With ModelSMC we found a way to include LLMs in a meaningful way within SMC. But more importantly: we want to shift from oracle-style usage of LLM in science to viewing discovery as inference! Check it out!

Machine Learning in Science@mackelab.bsky.social · last mo.

New paper: We recast automated scientific model discovery with LLMs as Bayesian inference! LLMs write code and carry domain knowledge, great for proposing models. The key idea: discovery is inference, not just generation. What distribution of models explains the data? 🧵 arxiv.org/abs/2602.18266

Back from 3 days of hackathon in beautiful Grenoble! ⛰️ It was fun to prepare and run the tutorial with @janboelts.bsky.social. Great discussions, new insights for us, and exciting to see researchers progress on their projects 🚀 Thanks to Pedro Rodriguez and others for organizing and hosting 👏

Jan Boelts@janboelts.bsky.social · 6mo ago

SBI Hackathon Grenoble is a wrap! 🎉 35 researchers and a great hybrid format of 1.5 days of tutorials + 1.5 days of applied hackathon. Many went from “having heard of sbi” to applying full SBI workflows to their own research projects. 🧵👇

Go and work with Richard! If I were starting a PhD again, he’d be at the top of my list. He’s a brilliant researcher and it's just genuine fun with him!

Richard Gao@rdgao.bsky.social · 8mo ago

Finally got the job ad—looking for 2 PhD students to start spring next year: www.gao-unit.com/join-us/ If comp neuro, ML, and AI4Neuro is your thing, or you just nerd out over brain recordings, apply! I'm at neurips. DM me here / on the conference app or email if you want to meet 🏖️🌮

I’m at NeurIPS in San Diego this week to present cool work on foundation models for SBI! Most importantly, I’ll be around to meet people and discuss science. 👨‍🔬

Machine Learning in Science@mackelab.bsky.social · 8mo ago

Second, come by to check out NPE-PFN: We leverage the power of tabular foundation models for training-free and simulation-efficient SBI. SBI has never been so effortless! By @vetterj.bsky.social, Manuel Gloeckler, @danielged.bsky.social, @jakhmack.bsky.social 4/11

Our group is at NeurIPS and EurIPS this year with four papers and one workshop poster. If you are either curious about SBI with autoML, with foundation models, or on function spaces or about differentiable simulators with Jaxley, have a look below 👇 1/11

Our work on training biophysical models with Jaxley is now out in @natmethods.nature.com. Led by @deismic.bsky.social, with @philipp.hertie.ai, @ppjgoncalves.bsky.social & @jakhmack.bsky.social et al. Paper: www.nature.com/articles/s41...

Jaxley: differentiable simulation enables large-scale training of detailed biophysical models of neural dynamics - Nature Methods

Jaxley is a versatile platform for biophysical modeling in neuroscience. It allows efficiently simulating large-scale biophysical models on CPUs, GPUs and TPUs. Model parameters can be optimized with ...

nature.com

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

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

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 🧵

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.

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 · last yr.

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! ⚡️

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 · last yr.

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! ⚡️

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

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

🎓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

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

🎉 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/...

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.

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 ...🐦‍⬛

@tomgoldstein.bsky.social · last yr.

New open source reasoning model! Huginn-3.5B reasons implicitly in latent space 🧠 Unlike O1 and R1, latent reasoning doesn’t need special chain-of-thought training data, and doesn't produce extra CoT tokens at test time. We trained on 800B tokens 👇

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... 🧵

🙏 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! 🙌

🚀 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:🧵👇

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 · 2y ago

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

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

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