Sharvaree Vadgama
banner
sharvaree.bsky.social
Sharvaree Vadgama
@sharvaree.bsky.social
PhD student at @amlab.bsky.social

Geometric deep learning + Generative modeling.
๐Ÿ‡ณ๐Ÿ‡ฑ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡ฎ๐Ÿ‡ณ

Organizer @gram-org.bsky.social workshop

๐Ÿ“ Amsterdam/SF
Reposted by Sharvaree Vadgama
We have a postdoc opening on the development of AI methods for accelerating computational fluid mechanics:

werkenbij.uva.nl/en/vacancies/postdoctoral-researcher-in-ai-for-fluid-mechanics-netherlands-14589

Deadline for applications soon โ€“โ€“ 28 Nov โ€“โ€“ e-mail me if you are planning to apply!
Vacancy โ€” Postdoctoral Researcher in AI for Fluid Mechanics
Are you interested in developing AI methods that can make physics simulations orders of magnitude faster? If the answer is yes, please continue reading!
werkenbij.uva.nl
November 7, 2025 at 2:26 PM
Reposted by Sharvaree Vadgama
WiML turns 20! ๐ŸŽ‰

For two decades, WiML has connected, inspired, and supported women around the world who are advancing the field of ML. As we celebrate this incredible milestone, we want to hear your story. ๐Ÿ’œ

โžก๏ธ Share your reflections: shorturl.at/lxWM2

#WiML #WiML20Years #WiML20th
shorturl.at
October 30, 2025 at 1:52 PM
๐Ÿš€ Excited to present our recent work: A scalable equivariant model.

Platonic Transformers ๐Ÿ”น
Check out the thread below for more.๐Ÿ‘‡
There's an increasingly popular argument saying that for 3D point clouds with rotational ambiguity (e.g. molecular data) standard transformers are preferable over equivariant models for compute reasons. With โ€œPlatonic Transformersโ€ we show why this doesn't have to be true. arxiv.org/abs/2510.03511
Platonic Transformers: A Solid Choice For Equivariance
While widespread, Transformers lack inductive biases for geometric symmetries common in science and computer vision. Existing equivariant methods often sacrifice the efficiency and flexibility that ma...
arxiv.org
October 24, 2025 at 3:57 PM
Reposted by Sharvaree Vadgama
More details in @erikjbekkers.bsky.socialโ€™s thread x.com/erikjbekkers... (nitter.net/erikjbekkers...). This has been a great first project for me to jump into for my postdoc in Amsterdam and Iโ€™m excited for the next steps. Great to work with this group of talented people!
October 23, 2025 at 2:35 PM
Reposted by Sharvaree Vadgama
๐Ÿ“ On the Importance of Embedding Norms in Self-Supervised Learning

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

๐Ÿ“œ arxiv.org/abs/2502.09252

๐Ÿงต4 / 8
May 6, 2025 at 2:53 PM
Reposted by Sharvaree Vadgama
Make sure to get your tickets to AABI if you are in Singapore on April 29 (just after #ICLR2025) and interested in probabilistic modeling, inference, and decision-making!

Tickets (free but limited!): lu.ma/5syzr79m
More info: approximateinference.org

#Bayes #MachineLearning #ICLR2025 #AABI2025
April 13, 2025 at 7:43 AM
Reposted by Sharvaree Vadgama
Now, the fantastic @jmtomczak.bsky.social is telling us about probabilistic circuits at GeMSS/Statlearn 2025 @gemssai.bsky.social
March 31, 2025 at 9:42 AM
Reposted by Sharvaree Vadgama
We have just opened a fully-funded PhD position at Cambridge, supervised by me & Vasily Belokurov.

Topic: AI + astronomical imaging (broadly defined).
Deadline: April 16.

Please share with anyone who may be interested!

www.postgraduate.study.cam.ac.uk/courses/dire...
April 2, 2025 at 11:42 AM
Is the list of accepted workshops out? Where can I find it?
March 25, 2025 at 6:22 PM
Reposted by Sharvaree Vadgama
Itโ€™s a green light for the Frugal AI Challenge! ๐Ÿš€
For the next month, we invite all members of the AI community to participate in one of our 3 AI for Climate tasks, with the goal of developing a highly accurate model while consuming as little energy as possible โšก
January 6, 2025 at 5:36 PM
Reposted by Sharvaree Vadgama
ICML 2025 Call for Workshops is out.
icml.cc/Conferences/...
ICML 2025 Call for Workshops
icml.cc
January 4, 2025 at 3:38 AM
Reposted by Sharvaree Vadgama
Exciting news! ๐Ÿš€ The Learning Meaningful Representations of Life ( #LMRL ๐ŸŒŸ) workshop is returning at #ICLR2025! ๐ŸŽ‰

On 27th / 28th April 2025 in Singapore ๐Ÿ‡ธ๐Ÿ‡ฌ, this popular event returns with a fresh organizing team ๐Ÿ‘‡ & bold new ideas ๐Ÿง  to explore bridging AI & life sciences ๐Ÿงฌ
December 19, 2024 at 5:02 PM
I see a few familiar names. โ˜บ๏ธโ˜บ๏ธ
Congrats Anna and Jakub!
Hierarchical VAE with a Diffusion-based VampPrior

Anna Kuzina, Jakub M. Tomczak

Action editor: Arto Klami

https://openreview.net/forum?id=NUkEoZ7Toa

#autoencoders #vampprior #generative
December 19, 2024 at 6:56 PM
Reposted by Sharvaree Vadgama
๐Ÿ”Š Super excited to announce the first ever Frontiers of Probabilistic Inference: Learning meets Sampling workshop at #ICLR2025 @iclr-conf.bsky.social!

๐Ÿ”— website: sites.google.com/view/fpiwork...

๐Ÿ”ฅ Call for papers: sites.google.com/view/fpiwork...

more details in thread below๐Ÿ‘‡ ๐Ÿงต
December 18, 2024 at 7:09 PM
This is very important and I am so glad about the efforts taken in Tรผbingen by Claire. Kudos! ๐Ÿ‘
December 18, 2024 at 11:02 PM
The horses braids are perfect โœจ
December 17, 2024 at 6:49 PM
Incredible ๐ŸŽ‰
December 16, 2024 at 9:29 PM
Reposted by Sharvaree Vadgama
Shar, you are simply amazing! And working you with is a highlight!
@neuripsconf.bsky.social Program Chair spotted ๐Ÿ˜๐Ÿ˜

@jmtomczak.bsky.social Jakub, seeing you work towards making NeurIPS happen, has been awe inspiring. What a mammoth effort!

A proud advisee moment ๐Ÿฅน
December 15, 2024 at 6:32 AM
๐Ÿฅน๐Ÿฅน thank you!
December 15, 2024 at 7:00 AM
@neuripsconf.bsky.social Program Chair spotted ๐Ÿ˜๐Ÿ˜

@jmtomczak.bsky.social Jakub, seeing you work towards making NeurIPS happen, has been awe inspiring. What a mammoth effort!

A proud advisee moment ๐Ÿฅน
December 14, 2024 at 3:30 AM
I am rooting for you all ๐Ÿ’ช๐ŸŽ‰โ˜€๏ธ
December 12, 2024 at 3:22 AM
Loving bsky community. Since I joined, I got to meet a lot of new people especially women in ML/AI!
It's really heart warming to see that there are so many incredible women doing really cool work especially on the days when you face the challenges of working in severely skewed gender ratio groups.
December 12, 2024 at 3:21 AM
Kudos Jakub! ๐ŸŽ‰
What an incredible feat! โœจโœจ
December 11, 2024 at 7:26 AM
Reposted by Sharvaree Vadgama
Inspired by @wimlds.bsky.social , I looked for a "Women in Machine Learning" starter pack and couldn't find one.
So I created one! May have some mistakes. I'll try to do an AI ethics one next. ๐Ÿค—
go.bsky.app/LT6CwNN
December 11, 2024 at 4:02 AM
Reposted by Sharvaree Vadgama
"Women full professors are 19% more likely than men at the same career stage to leave academia, as compared with 6% for women assistant professors and 10% for associates."
Women faculty feel โ€˜pushedโ€™ from academia by poor workplace climate
The gender gap in faculty attrition worsens after tenure, according to a new study
www.science.org
December 9, 2024 at 6:27 AM