Vincent Guan (@guanton_soup) - Twitter Profili | Zamantika Mersobahis Locabet

Sabitlenmiş Tweet

Vincent Guan@guanton_soup·13 May

Can we learn how a population evolves just by observing it? 𓆟𓆞𓆝 With @lazar_atan and @k_neklyudov, we came up with Wasserstein Lagrangian Mechanics (WLM), which generalizes least action to the population level. See the 🧵 for our #ICML2026 spotlight paper and some fun gifs🐦

Kirill Neklyudov@k_neklyudov

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 - Covers both first-order (gradient descent) and second-order dynamics (e.g. oscillations) - Allows learning more expressive dynamics (including complex interactions) with fewer assumptions - Generalizes in space (across different initial conditions) and time (beyond the training time snapshots) [1/n] 🧵

English

1

3

11

1.3K

Vincent Guan@guanton_soup·8 Tem

There are many posters at @icmlconf, and one of them is for our spotlight paper on learning population dynamics (done with @lazar_atan and @k_neklyudov). Come by poster #1515 in Hall A today from 5pm-6:45pm for any questions or complaints

Lazar Atanackovic@lazar_atan

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!

English

0

7

22

3K

Vincent Guan retweetledi

Marta Skreta@martoskreto·14 May

Riemannian MeanFlow 🌀🌊 will be at #ICML2026! (don’t worry though, it’s actually a pretty NiceFlow 😎) RMF extends the MeanFlow framework to Riemannian manifolds by learning average velocities directly on the manifold -- this enables fast generation of biomolecules in high dimensions. ⚡️ RMF can generate discrete DNA sequences on the simplex manifold — language flow maps in biology! 🧬 We also show that reward guidance can generate proteins and DNA with structures or functions that we want using fewer steps. 🏆 Huge congrats to @dywoo1247 who led this project and worked incredibly hard to identify the best losses and practices for training these challenging models 🔥 had an awesome time working on this with @hyuunnnnnn, @k_neklyudov, and @sungsoo_ahn_ 🤗 also, if you like this work, check out GFM from Davis et al. who approach the same problem from a different angle :)

Dongyeop Woo@dywoo1247

Can we perform high-quality generative modeling on Riemannian manifolds — in just one forward pass? Introducing Riemannian MeanFlow (RMF) — with @martoskreto, @hyuunnnnnn, @k_neklyudov & @sungsoo_ahn_ 🧵👇 [1/7]

English

2

17

109

14.4K

Vincent Guan retweetledi

Lazar Atanackovic@lazar_atan·13 May

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

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 - Covers both first-order (gradient descent) and second-order dynamics (e.g. oscillations) - Allows learning more expressive dynamics (including complex interactions) with fewer assumptions - Generalizes in space (across different initial conditions) and time (beyond the training time snapshots) [1/n] 🧵

English

0

11

66

8K

Vincent Guan

Keşfet