Soledad Villar

Associate Professor at Johns Hopkins Applied Math and Stats. She/ella. Uruguaya 🇺🇾

[LOGML Summer School @LogmlSchool]

🚀 LOGML26— Mentor applications!

📍 Imperial College London | 13–17 July 2026

Mentor a project team. Attend talks, socials, networking events. 💸 Travel support available.

Deadline: 18 March 2026(AoE)

Apply: https://t.co/LnuzLuFBc2

#LOGML #MachineLearning #SummerSchool

[Johns Hopkins Engineering @HopkinsEngineer]

🧵Meet the 3 Hopkins Engineers selected as 2026 @SloanFoundation Fellows: “early-career scholars…whose creativity and innovation set them apart as the next generation of scientific leaders.” JHU has had 92 Sloan Fellows since 1955!
https://t.co/czCmg3pmXE

[Boris Hanin @BorisHanin]

🚨 2026 @Princeton ML Theory Summer School

Mini-courses by:

- Subhabrata Sen @subhabratasen90
- Lenaic Chizat @LenaicChizat
- Sinho Chewi
- Elliot Paquette @poseypaquet
- Elad Hazan @HazanPrinceton
- Surya Ganguli @SuryaGanguli

August 3 - 14, 2026

Apply by March 31. Link 👇

Sponsors: @NSF, @PrincetonAInews, @EPrinceton @JaneStreetGroup, @DARPA, @PrincetonPLI, Princeton NAM, Princeton AI2, Princeton PACM

Some amazing speakers from previous years: @Andrea__M, @TheodorMisiakie, @KrzakalaF, @_brloureiro, @rakhlin, @DimaKrotov, @CPehlevan, @SoledadVillar5, @SebastienBubeck, @tengyuma

[Johns Hopkins Data Science and AI Institute @HopkinsDSAI]

Join us in advancing data science and AI research! The Johns Hopkins Data Science and AI Institute Postdoctoral Fellowship Program is now accepting applications for the 2026–2027 academic year. Apply now! Deadline: Jan 23, 2026. Details and apply: https://t.co/bdxrDTzc4Q

[Symmetry and Geometry in Neural Representations @neur_reps]

📢 Call for Papers: NeurReps 2025 ‼️‼️‼️

🧠 Submit your research on symmetry, geometry, and topology in artificial and biological neural networks.

Two tracks: Proceedings (9 pages) and Extended Abstract (4 pages).

Deadline: Aug 22, 2025.

https://t.co/A3jYmIlTVH

[Emily Riehl @emilyriehl]

Starting today I'm embarking upon a new adventure: 12 talks over the next 18 days as part of the @LondMathSoc Hardy Lecture Tour (plus a few additions). Titles and abstracts can all be found here:

https://t.co/Rmfplg7J0j

and slides (when available) will eventually be added.

[Mateo Díaz @mateodd25]

When does the performance of an ML model transfer across dimensions?
https://t.co/cqFMdgl6ZV
Kudos to my terrific collaborators Eitan Levin, Yuxin Ma, and @SoledadVillar5.

🧵(1/n)

[Shubhendu Trivedi @_onionesque]

Enjoyed reading this paper! It randomly made me think of the Blow-Up Lemma and the Key Lemma (and later works which had more of an algebraic flavour by Szegedy Balázs). Perhaps nothing more than just family resemblance? https://t.co/ef2sZm06dM (@SoledadVillar5)

[Soledad Villar @SoledadVillar5]

@_onionesque Thanks Shubhendu, I think the resemblance comes from the way we choose to model growing graphs. Other choices could make sense too but I don't know how to model them as consistent sequences. Happy to chat!

@mateodd25

[Soledad Villar @SoledadVillar5]

@murat_kocaoglu_ @JHUCompSci Welcome Murat! It's been a while! Let me know when you get to Baltimore.

[Soledad Villar @SoledadVillar5]

@chaitjo Also, I imagine the translation symmetry is avoided by centering the data, so effectively you are comparing SO(3)-equivariance with no equivariance.

[Soledad Villar @SoledadVillar5]

@chaitjo I trust that better engineering can beat a theoretical gain of a constant factor

[Soledad Villar @SoledadVillar5]

https://t.co/1sPhKDS6j4

[Kaze Wong @physicskaze]

I just learned that one of our #NeurIPS2024 #ML4PS submissions is awarded the best paper award through @instagram when people are dm-ing me (I am not in Vancouver unfortunately)! Huge congrat to the team and Wilson who led the effort!

https://t.co/W6DjnKmTB4

[Soledad Villar @SoledadVillar5]

Super proud of my PhD student Wilson Gregory

He won a best paper award at #ml4ps2024 for our work with @davidwhogg and @physicskaze

Robust Emulator for Compressible Navier-Stokes using Equivariant Geometric Convolutions https://t.co/nnZVqb4v0g

https://t.co/fGsg7uJalU

[Kyle Cranmer @KyleCranmer]

The papers and posters for our Machine Learning and Physical Sciences workshop at #NeurIPS2024 are online #ml4ps2024 @ML4PhyS
https://t.co/okEep7NcMF

[Pim de Haan @pimdehaan]

Our paper got a prize :)
Cheers to lead author @johannbrehmer, and fellow co-authors Sönke Behrends, and @TacoCohen.
Our results hint that yes, also at large scale of data and compute, if your data has symmetries, you might be better off building these into your network.

[Nick Konz @nick_konz]

This position paper by @davidwhogg and @SoledadVillar5 excellently vocalizes the shift in thinking I noticed when transitioning from astronomy research to ML research — a great read for anyone interested in the intersection of ML and the natural sciences! https://t.co/Sqzy3QkxvJ

[Thomas Kipf @tkipf]

The Call for Papers for the Learning on Graphs Conference (LoG 2024) is out!

Submission deadline: September 11th, 2024
Final decision: November 13th, 2024

LoG is one of the best venues for "all things graph" (Graph ML, GNNs, ML for Molecules, RAG+Graphs, ...) - now in its third edition!

Call for Papers: https://t.co/XKv3dzJUzw

[Teresa Huang @TeresaNHuang]

Thank you Sole for always having the utmost faith in me and the tremendous support throughout my PhD ❤️I am so grateful for all my mentors, collaborators, friends, and family.

Hello, New York City 🥳

[Soledad Villar @SoledadVillar5]

Super proud of my first PhD student @TeresaNHuang

After her internship at Apple Research NYC this Summer she will join @FlatironCCM as a postdoc this Fall