Lasse Elsemüller
@elseml.bsky.social
💡 PhD candidate @ Heidelberg University.
🌱 AI for science - simulation-based inference, robust deep learning & cognitive modeling.
🌱 AI for science - simulation-based inference, robust deep learning & cognitive modeling.
Reposted by Lasse Elsemüller
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!
August 13, 2025 at 3:08 PM
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!
Reposted by Lasse Elsemüller
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 🧡
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 🧡
June 3, 2025 at 5:39 AM
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 🧡
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 🧡
Reposted by Lasse Elsemüller
🧠 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...
Interactive version: kucharssim.github.io/bayesflow-co...
PDF: osf.io/preprints/ps...
Introduction – Amortized Bayesian Cognitive Modeling
kucharssim.github.io
May 30, 2025 at 2:28 PM
🧠 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...
Interactive version: kucharssim.github.io/bayesflow-co...
PDF: osf.io/preprints/ps...
Reposted by Lasse Elsemüller
New preprint!
Individual differences in neurophysiological correlates of post-response adaptation: A model-based approach
osf.io/preprints/ps...
This work seeks to extract the effects of response monitoring on decision-making using model-based CogNeuro and methods to study individual differences.
Individual differences in neurophysiological correlates of post-response adaptation: A model-based approach
osf.io/preprints/ps...
This work seeks to extract the effects of response monitoring on decision-making using model-based CogNeuro and methods to study individual differences.
OSF
osf.io
March 6, 2025 at 2:21 PM
New preprint!
Individual differences in neurophysiological correlates of post-response adaptation: A model-based approach
osf.io/preprints/ps...
This work seeks to extract the effects of response monitoring on decision-making using model-based CogNeuro and methods to study individual differences.
Individual differences in neurophysiological correlates of post-response adaptation: A model-based approach
osf.io/preprints/ps...
This work seeks to extract the effects of response monitoring on decision-making using model-based CogNeuro and methods to study individual differences.
Reposted by Lasse Elsemüller
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)
March 4, 2025 at 1:15 PM
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)
Reposted by Lasse Elsemüller
A study with 5M+ data points explores the link between cognitive parameters and socioeconomic outcomes: The stability of processing speed was the strongest predictor.
BayesFlow facilitated efficient inference for complex decision-making models, scaling Bayesian workflows to big data.
🔗Paper
BayesFlow facilitated efficient inference for complex decision-making models, scaling Bayesian workflows to big data.
🔗Paper
February 3, 2025 at 12:21 PM
A study with 5M+ data points explores the link between cognitive parameters and socioeconomic outcomes: The stability of processing speed was the strongest predictor.
BayesFlow facilitated efficient inference for complex decision-making models, scaling Bayesian workflows to big data.
🔗Paper
BayesFlow facilitated efficient inference for complex decision-making models, scaling Bayesian workflows to big data.
🔗Paper
Reposted by Lasse Elsemüller
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.
January 27, 2025 at 9:04 AM
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.
Reposted by Lasse Elsemüller
Scholar inbox is the best paper recommender and I cannot recommend it enough as a conference companion. I don’t know how people do poster sessions without it.
Excited to share that today our paper recommender platform www.scholar-inbox.com has reached 20k users! We hope to reach 100k by the end of the year.. Lots of new features are being worked on currently and rolled out soon.
January 16, 2025 at 9:39 PM
Scholar inbox is the best paper recommender and I cannot recommend it enough as a conference companion. I don’t know how people do poster sessions without it.
Reposted by Lasse Elsemüller
1️⃣ An agent-based model simulates a dynamic population of professional speed climbers.
2️⃣ BayesFlow handles amortized parameter estimation in the SBI setting.
📣 Shoutout to @masonyoungblood.bsky.social & @sampassmore.bsky.social
📄 Preprint: osf.io/preprints/ps...
💻 Code: github.com/masonyoungbl...
2️⃣ BayesFlow handles amortized parameter estimation in the SBI setting.
📣 Shoutout to @masonyoungblood.bsky.social & @sampassmore.bsky.social
📄 Preprint: osf.io/preprints/ps...
💻 Code: github.com/masonyoungbl...
December 10, 2024 at 1:34 AM
1️⃣ An agent-based model simulates a dynamic population of professional speed climbers.
2️⃣ BayesFlow handles amortized parameter estimation in the SBI setting.
📣 Shoutout to @masonyoungblood.bsky.social & @sampassmore.bsky.social
📄 Preprint: osf.io/preprints/ps...
💻 Code: github.com/masonyoungbl...
2️⃣ BayesFlow handles amortized parameter estimation in the SBI setting.
📣 Shoutout to @masonyoungblood.bsky.social & @sampassmore.bsky.social
📄 Preprint: osf.io/preprints/ps...
💻 Code: github.com/masonyoungbl...
Reposted by Lasse Elsemüller
Check out this project on modeling stationary and time-varying parameters with BayesFlow.
The family of methods is called "neural superstatistics", how can it not be cool!? 😎
👨💻 Led by @schumacherlu.bsky.social
The family of methods is called "neural superstatistics", how can it not be cool!? 😎
👨💻 Led by @schumacherlu.bsky.social
Neural superstatistics are a framework for probabilistic models with time-varying parameters:
⋅ Joint estimation of stationary and time-varying parameters
⋅ Amortized parameter inference and model comparison
⋅ Multi-horizon predictions and leave-future-out CV
📄 Paper 1
📄 Paper 2
💻 BayesFlow Code
⋅ Joint estimation of stationary and time-varying parameters
⋅ Amortized parameter inference and model comparison
⋅ Multi-horizon predictions and leave-future-out CV
📄 Paper 1
📄 Paper 2
💻 BayesFlow Code
December 6, 2024 at 12:25 PM
Check out this project on modeling stationary and time-varying parameters with BayesFlow.
The family of methods is called "neural superstatistics", how can it not be cool!? 😎
👨💻 Led by @schumacherlu.bsky.social
The family of methods is called "neural superstatistics", how can it not be cool!? 😎
👨💻 Led by @schumacherlu.bsky.social
Stellar TL;DR of our recent work by our team! ✨
Any single analysis hides an iceberg of uncertainty.
Sensitivity-aware amortized inference explores the iceberg:
⋅ Test alternative priors, likelihoods, and data perturbations
⋅ Deep ensembles flag misspecification issues
⋅ No model refits required during inference
🔗 openreview.net/forum?id=Kxt...
Sensitivity-aware amortized inference explores the iceberg:
⋅ Test alternative priors, likelihoods, and data perturbations
⋅ Deep ensembles flag misspecification issues
⋅ No model refits required during inference
🔗 openreview.net/forum?id=Kxt...
November 26, 2024 at 8:47 AM
Stellar TL;DR of our recent work by our team! ✨
Reposted by Lasse Elsemüller
To celebrate the new beginnings on Bluesky, let's reminisce about one of our highlights from the old days:
The unexpected shout-out by @fchollet.bsky.social that made everyone go crazy on the BayesFlow Slack server and led to a 15% increase in GitHub stars.
The unexpected shout-out by @fchollet.bsky.social that made everyone go crazy on the BayesFlow Slack server and led to a 15% increase in GitHub stars.
November 22, 2024 at 10:37 PM
To celebrate the new beginnings on Bluesky, let's reminisce about one of our highlights from the old days:
The unexpected shout-out by @fchollet.bsky.social that made everyone go crazy on the BayesFlow Slack server and led to a 15% increase in GitHub stars.
The unexpected shout-out by @fchollet.bsky.social that made everyone go crazy on the BayesFlow Slack server and led to a 15% increase in GitHub stars.
Reposted by Lasse Elsemüller
The beta version of BayesFlow 2.0 is becoming more powerful and stable by the day. If you are curious about Amortized Bayesian Inference, give BayesFlow a try!
github.com/bayesflow-or...
github.com/bayesflow-or...
GitHub - bayesflow-org/bayesflow at dev
A Python library for amortized Bayesian workflows using generative neural networks. - GitHub - bayesflow-org/bayesflow at dev
github.com
November 22, 2024 at 8:52 AM
The beta version of BayesFlow 2.0 is becoming more powerful and stable by the day. If you are curious about Amortized Bayesian Inference, give BayesFlow a try!
github.com/bayesflow-or...
github.com/bayesflow-or...
Reposted by Lasse Elsemüller
Thrilled to contribute to this work led by David Frazier providing theory for NPE/NLE in simulation-based inference. These methods are known to match the accuracy of ABC and BSL with fewer simulations, this paper rigorously shows why this can be achieved.
arxiv.org/abs/2411.12068
arxiv.org/abs/2411.12068
The Statistical Accuracy of Neural Posterior and Likelihood Estimation
Neural posterior estimation (NPE) and neural likelihood estimation (NLE) are machine learning approaches that provide accurate posterior, and likelihood, approximations in complex modeling scenarios, ...
arxiv.org
November 21, 2024 at 6:04 AM
Thrilled to contribute to this work led by David Frazier providing theory for NPE/NLE in simulation-based inference. These methods are known to match the accuracy of ABC and BSL with fewer simulations, this paper rigorously shows why this can be achieved.
arxiv.org/abs/2411.12068
arxiv.org/abs/2411.12068
Reposted by Lasse Elsemüller
For those who don’t know yet, I am organising an online talk series together with Arno Solin on “Advances in Probabilistic Machine Learning (APML)”.
It’s free for everyone to join and support early career researchers!
You can register and check out the schedule here: aaltoml.github.io/apml/
It’s free for everyone to join and support early career researchers!
You can register and check out the schedule here: aaltoml.github.io/apml/
Seminar on Advances in Probabilistic Machine Learning
This seminar series aims to provide a platform for young researchers (PhD student or post-doc level) to give invited talks about their research, intending to have a diverse set of talks & speakers on ...
aaltoml.github.io
November 20, 2024 at 8:33 PM
For those who don’t know yet, I am organising an online talk series together with Arno Solin on “Advances in Probabilistic Machine Learning (APML)”.
It’s free for everyone to join and support early career researchers!
You can register and check out the schedule here: aaltoml.github.io/apml/
It’s free for everyone to join and support early career researchers!
You can register and check out the schedule here: aaltoml.github.io/apml/
Reposted by Lasse Elsemüller
The first list filled up, so here's a second list of AI for Science researchers on bluesky.
Let me know if I missed you / if you'd like to join!
bsky.app/starter-pack...
Let me know if I missed you / if you'd like to join!
bsky.app/starter-pack...
November 20, 2024 at 8:56 AM
The first list filled up, so here's a second list of AI for Science researchers on bluesky.
Let me know if I missed you / if you'd like to join!
bsky.app/starter-pack...
Let me know if I missed you / if you'd like to join!
bsky.app/starter-pack...
Reposted by Lasse Elsemüller
I'm making a list of AI for Science researchers on bluesky — let me know if I missed you / if you'd like to join!
go.bsky.app/AcP9Lix
go.bsky.app/AcP9Lix
November 10, 2024 at 12:11 AM
I'm making a list of AI for Science researchers on bluesky — let me know if I missed you / if you'd like to join!
go.bsky.app/AcP9Lix
go.bsky.app/AcP9Lix
Reposted by Lasse Elsemüller
✨ Super excited to share our paper **Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness** arxiv.org/abs/2408.05446 ✨
Inspired by biology we 1) get adversarial robustness + interpretability for free, 2) turn classifiers into generators & 3) design attacks on GPT-4
Inspired by biology we 1) get adversarial robustness + interpretability for free, 2) turn classifiers into generators & 3) design attacks on GPT-4
November 19, 2024 at 6:19 PM
✨ Super excited to share our paper **Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness** arxiv.org/abs/2408.05446 ✨
Inspired by biology we 1) get adversarial robustness + interpretability for free, 2) turn classifiers into generators & 3) design attacks on GPT-4
Inspired by biology we 1) get adversarial robustness + interpretability for free, 2) turn classifiers into generators & 3) design attacks on GPT-4
Reposted by Lasse Elsemüller
Bluesky now has over 20M people!! 🎉
We've been adding over a million users per day for the last few days. To celebrate, here are 20 fun facts about Bluesky:
We've been adding over a million users per day for the last few days. To celebrate, here are 20 fun facts about Bluesky:
November 19, 2024 at 6:51 PM
Bluesky now has over 20M people!! 🎉
We've been adding over a million users per day for the last few days. To celebrate, here are 20 fun facts about Bluesky:
We've been adding over a million users per day for the last few days. To celebrate, here are 20 fun facts about Bluesky:
Reposted by Lasse Elsemüller
Eight years later, Yann LeCun’s cake 🍰 analogy was spot on: self-supervised > supervised > RL
> “If intelligence is a cake, the bulk of the cake is unsupervised learning, the icing on the cake is supervised learning, and the cherry on the cake is reinforcement learning (RL).”
> “If intelligence is a cake, the bulk of the cake is unsupervised learning, the icing on the cake is supervised learning, and the cherry on the cake is reinforcement learning (RL).”
November 17, 2024 at 4:02 PM
Eight years later, Yann LeCun’s cake 🍰 analogy was spot on: self-supervised > supervised > RL
> “If intelligence is a cake, the bulk of the cake is unsupervised learning, the icing on the cake is supervised learning, and the cherry on the cake is reinforcement learning (RL).”
> “If intelligence is a cake, the bulk of the cake is unsupervised learning, the icing on the cake is supervised learning, and the cherry on the cake is reinforcement learning (RL).”
The coolest starter pack out here! (in my totally unbiased opinion)
I created a starter pack for simulation-based inference (aka. likelihood-free inference).
Let me know if you’d like me to add you.
go.bsky.app/GVnJRoK
Let me know if you’d like me to add you.
go.bsky.app/GVnJRoK
November 17, 2024 at 3:29 PM
The coolest starter pack out here! (in my totally unbiased opinion)
Reposted by Lasse Elsemüller
Our Python library BayesFlow implements methods for amortized Bayesian inference. You first train a neural network on simulated data. Then you obtain posterior inference on any real data almost instantly. Check out the dev branch for our new backend and user interface: github.com/bayesflow-or...
GitHub - bayesflow-org/bayesflow at dev
A Python library for amortized Bayesian workflows using generative neural networks. - GitHub - bayesflow-org/bayesflow at dev
github.com
October 26, 2024 at 7:13 AM
Our Python library BayesFlow implements methods for amortized Bayesian inference. You first train a neural network on simulated data. Then you obtain posterior inference on any real data almost instantly. Check out the dev branch for our new backend and user interface: github.com/bayesflow-or...