Lightnews — Scholar-powered news

AMLab

@amlab.bsky.social

750 followers 40 following 43 posts

The official account of the Amsterdam Machine Learning Lab (AMLab) at UvA, co-directed by Max Welling and Jan-Willem van de Meent.

Posts Media Videos Starter Packs

Pinned

AMLab @amlab.bsky.social · Nov 21

Meet our Lab's members: staff, postdocs and PhD students! :)

With this starter pack you can easily connect with us and keep up to date with all the member's research and news 🦋

go.bsky.app/8EGigUy

Reposted by AMLab

Max Zhdanov @maxxxzdn.bsky.social · Jun 21

🤹 New blog post!

I write about our recent work on using hierarchical trees to enable sparse attention over irregular data (point clouds, meshes) - Erwin Transformer, accepted to ICML 2025

blog: maxxxzdn.github.io/blog/erwin/
paper: arxiv.org/abs/2502.17019

Compressed version in the thread below:

AMLab @amlab.bsky.social · May 13

Don's miss this exciting opportunity! 🔥

🚨Application deadline on the 15th of June

Sara Magliacane @smaglia.bsky.social · May 12

New PhD position at the University of Amsterdam in @amlab.bsky.social on learning concepts with theoretical guarantees using #causality and #RL with me, Frans Oliehoek (TU Delft) and Herke van Hoof 💥

Deadline: 15 June

werkenbij.uva.nl/en/vacancies...

Vacancy — PhD Position on Learning Concepts with Theoretical Guarantees Using Causality and RL

Are you interested in improving the interpretability, robustness and safety of current AI systems? If the answer is yes, please continue reading!

werkenbij.uva.nl

Reposted by AMLab

Sara Magliacane @smaglia.bsky.social · May 12

One more week to apply to this exciting position... and another position on #CausalRepresentationLearning and #ReinforcementLearning for learning provably correct #concepts from raw data opening up soon!

Sara Magliacane @smaglia.bsky.social · Apr 17

Exciting new PhD position at Utrecht University on the #causal effects of communication in #multi-agent #RL with Shihan Wang, Mehdi Dastani and me 🎉

This is part of www.hybrid-intelligence-centre.nl, which aims at combining human and machine intelligence.

Deadline 20 May

www.uu.nl/en/organisat...

PhD Position on Causal Effects of Communication in MARL

Join us to work on the causal effects of communication in multi-agent reinforcement learning (MARL).

Reposted by AMLab

Sara Magliacane @smaglia.bsky.social · May 12

New PhD position at the University of Amsterdam in @amlab.bsky.social on learning concepts with theoretical guarantees using #causality and #RL with me, Frans Oliehoek (TU Delft) and Herke van Hoof 💥

Deadline: 15 June

werkenbij.uva.nl/en/vacancies...

Vacancy — PhD Position on Learning Concepts with Theoretical Guarantees Using Causality and RL

Are you interested in improving the interpretability, robustness and safety of current AI systems? If the answer is yes, please continue reading!

werkenbij.uva.nl

AMLab @amlab.bsky.social · May 6

🐳 Controlled Generation with Equivariant Variational Flow Matching

By @eijkelboomfloor.bsky.social , @zmheiko.bsky.social ,
@sharvaree.bsky.social , @erikjbekkers.bsky.social ,
@wellingmax.bsky.social , @canaesseth.bsky.social *, @jwvdm.bsky.social *

📜 As above - paper TBA soon 😉

🧵8 / 8

AMLab @amlab.bsky.social · May 6

🌊 Exponential Family Variational Flow Matching for Tabular Data Generation

By Andrés Guzmán-Cordero*, @eijkelboomfloor.bsky.social *,
@jwvdm.bsky.social

📜 This paper will be shared soon - keep your eyes open! 🤩

🧵7 / 8

AMLab @amlab.bsky.social · May 6

⚠️ The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret

By Lukas Fluri*, @leon-lang.bsky.social *, Alessandro Abate, Patrick Forré, David Krueger, Joar Skalse

📜 arxiv.org/abs/2406.15753

🧵6 / 8

AMLab @amlab.bsky.social · May 6

🔁 SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations

By @gbarto.bsky.social , Dmitry Vetrov, @canaesseth.bsky.social

📜 arxiv.org/abs/2502.02472

🧵5 / 8

AMLab @amlab.bsky.social · May 6

📐 On the Importance of Embedding Norms in Self-Supervised Learning

By Andrew Draganov, @sharvaree.bsky.social , Sebastian Damrich, Jan Niklas Böhm, Lucas Maes, Dmitry Kobak, @erikjbekkers.bsky.social

📜 arxiv.org/abs/2502.09252

🧵4 / 8

AMLab @amlab.bsky.social · May 6

⚖️ A machine learning approach to duality in statistical physics

By Prateek Gupta, Andrea Ferrari, @nabiliqbal.bsky.social

📜 arxiv.org/abs/2411.04838

🧵3 / 8

AMLab @amlab.bsky.social · May 6

🐸 Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems

By @maxxxzdn.bsky.social , @jwvdm.bsky.social , @wellingmax.bsky.social

📜 arxiv.org/abs/2502.17019

🧵2 / 8

AMLab @amlab.bsky.social · May 6

Exciting news: AMLab is happy to have 7 papers accepted at #ICML2025! 🎉

See the thread below for the full list 📝 and meet us in Vancouver to discuss them further! 🇨🇦

🧵1 / 8

AMLab @amlab.bsky.social · May 1

🥇 3 Best Paper Awards for AMLab members!

1. Towards Variational Flow Matching on General Geometries by @olgatticus.bsky.social et al.

2. Generative Uncertainty in Diffusion Models by @metodjazbec.bsky.social et al.

3. SDE Matching by @gbarto.bsky.social et al.

Congrats to everyone! 🔥

Reposted by AMLab

ICLR Conference @iclr-conf.bsky.social · Apr 15

Test of Time Winner

Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba

Adam revolutionized neural network training, enabling significantly faster convergence and more stable training across a wide variety of architectures and tasks.

Reposted by AMLab

Max Zhdanov @maxxxzdn.bsky.social · Mar 5

🤹 Excited to share Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems

joint work with @wellingmax.bsky.social and @jwvdm.bsky.social

preprint: arxiv.org/abs/2502.17019
code: github.com/maxxxzdn/erwin

Reposted by AMLab

Mátyás Schubert @matyasch.bsky.social · Mar 4

A few weeks ago, I presented SNAP at the wonderful #Bellairs Workshop on Causality in Barbados🐢

This Friday 🫰meets 🤌 as I will get to present SNAP again at the kick-off of the newest season of @causalclub.di.unipi.it! Check out this, and their other amazing upcoming talks at causalclub.di.unipi.it

Reposted by AMLab

Olga Zaghen @olgatticus.bsky.social · Feb 19

Variational Flow Matching goes Riemannian! 🔮

In this preliminary work, we derive a variational objective for probability flows 🌀 on manifolds with closed-form geodesics, and discuss some interesting results.

Dream team: Floor, Alison & Erik (their @ below) 💥

📜 arxiv.org/abs/2502.12981
🧵1/5

Reposted by AMLab

Sara Magliacane @smaglia.bsky.social · Feb 17

Congratulations to "my" first PhD student Dr. @rmassidda.it who defended today at the University of Pisa *with honours* a thesis on "Methodological Advancements for Causal Abstraction Learning" 🎉

Riccardo is an amazing @ellis.eu PhD co-supervised w/ Davide Bacciu
@ellisamsterdam.bsky.social

AMLab @amlab.bsky.social · Feb 13

💡 ➡️ 🧠 ➡️ 🚀

Mátyás Schubert @matyasch.bsky.social · Feb 13

Do you want to estimate causal effects for a small set of target variables without knowing the causal graph, but discovering it takes too long? Now you can get adjustment sets in a SNAP🫰accepted at #aistats2025!

📜 arxiv.org/abs/2502.07857
🧩 matyasch.github.io/snap/
🧵 1/10

AMLab @amlab.bsky.social · Feb 13

😍💥

Jacobus Dijkman @jdijkman.bsky.social · Feb 13

🚨 Excited to share our work just published in Physical Review Letters with @wellingmax.bsky.social, @jwvdm.bsky.social, @berndensing.bsky.social, Marjolein Dijkstra and René van Roij: doi.org/10.1103/Phys....

Details below 👇

Learning Neural Free-Energy Functionals with Pair-Correlation Matching

The intrinsic Helmholtz free-energy functional, the centerpiece of classical density functional theory, is at best only known approximately for 3D systems. Here we introduce a method for learning a ne...

AMLab @amlab.bsky.social · Dec 20

Facts 💃🏻

AMLab @amlab.bsky.social · Dec 20

The Christmas spirit has arrived at AMLab! 🎄✨
Yesterday we kicked off the holidays with a festive group dinner and a fun Secret Santa exchange. 🎅

Wishing everyone a restful and joyful winter break and a happy new year! ❄️💫

AMLab @amlab.bsky.social · Dec 16

looks can be deceiving! ;)

AMLab @amlab.bsky.social · Dec 13

Professor Imbens also had a mentoring session with our PhD students actively working on causality, discussing their ideas and the potential impact of their applications! 👨‍🔬👩‍🔬

@matyasch.bsky.social @roelhulsman.bsky.social @rmassidda.it @danruxu.bsky.social 🔥

AMLab @amlab.bsky.social · Dec 13

Yesterday, we had the honor of hosting 2021 Nobel Laureate in Economics, Guido Imbens, at our Lab! 🤩

We had the chance to attend his inspiring talk on Experimental Design in Marketplaces 📈👩‍💻

A big thank you to @smaglia.bsky.social for making this event possible 💥