Lazar Atanackovic

@lazar_atan

Building generative models for biology. Asst Prof @UAlberta · Fellow @AmiiThinks · CIFAR AI Chair · ex-@broadinstitute @UofT

Edmonton, Alberta

lazaratan.github.io

Joined June 2020

998 Following

708 Followers

Replies Reposts Media

Pinned
Lazar Atanackovic
@lazar_atan
Aug 29, 2024
🚀Introducing — Meta Flow Matching (MFM) 🚀 Imagine predicting patient-specific treatment responses for unseen cases or building generative models that adapt across different measures. MFM makes this a reality. 📰Paper: arxiv.org/abs/2408.14608 💻Code: github.com/lazaratan/meta…
GIF
GIF
3
Lazar Atanackovic
@lazar_atan
Oct 13
Training classifier-free guided flows? Global Transport keeps high guidance scales stable 💪 The trick ... compute mini-batch OT couplings without labels! Nothing else changes, so it’s simple and easy to use (and it works 🎯). Check out the thread 🧵 for details.
Katarina Petrovic
@kpetrovvic
Oct 13
New preprint: 🚀 Global Transport (GT) couplings for classifier-free guided flows! Surprisingly, a simple label-free optimal transport coupling beats both class-conditional OT and independent couplings once we push the CFG scale up 🧗 reaching 1.91 FID on ImageNet-256
1
Lazar Atanackovic
@lazar_atan
Sep 24
We’re in! See you @NeurIPSConf! (thread coming soon)
arxiv.org
Measure-to-measure Regression with Transformers
Many learning problems require predicting how populations evolve under an unknown transformation. A natural representation for such populations is a probability measure, with point clouds as a key...
1
Lazar Atanackovic
@lazar_atan
Jul 8
A boid in the hand is better than two in the bush.🐦 Fortunately, @guanton_soup and I have plenty more than one boid at our Wasserstein Lagrangian Mechanics poster @icmlconf. (5pm, Hall A, #1515) If you're interested in population dynamics and OT (🕊️🧬🌊), come flock by!
Kirill Neklyudov
@k_neklyudov
May 13
Population dynamics (eg murmuration of birds 🐦🐦🐦) is notoriously hard to learn; choosing the right model for the dynamics is even harder. In our #ICML2026 spotlight, we introduce Wasserstein Lagrangian Mechanics (WLM) for learning population dynamics from observations, which
GIF
Lazar Atanackovic
@lazar_atan
May 13
Excited to finally share Wasserstein Lagrangian Mechanics (WLM🕊️)! We developed a way to learn population mechanics directly from snapshot data! It was an absolute blast working with @k_neklyudov and @guanton_soup. Check the 🧵 for the deep dive. See you at #ICML2026!
Kirill Neklyudov
@k_neklyudov
May 13
Population dynamics (eg murmuration of birds 🐦🐦🐦) is notoriously hard to learn; choosing the right model for the dynamics is even harder. In our #ICML2026 spotlight, we introduce Wasserstein Lagrangian Mechanics (WLM) for learning population dynamics from observations, which
GIF

Lazar Atanackovic

Lazar Atanackovic’s posts