Putri van der Linden Profile
Putri van der Linden

@compute_ri

Followers
397
Following
212
Media
2
Statuses
41

PhD Student @ AMLab

Joined December 2019
Don't wanna be here? Send us removal request.
@SharvVadgama
Sharvaree Vadgama @NeurIPS2025 San Diego
5 months
Also, presenting on behalf of @artemmoskalev work on Efficient Geometric deep learning architecture: โฉโฉ Geometric Hyena Networks for Large-scale Equivariant Learning Paper: https://t.co/4QApPn7IxI Thread:
openreview.net
Processing global geometric context while preserving equivariance is crucial when modeling biological, chemical, and physical systems. Yet, this is challenging due to the computational demands of...
@artemmoskalev
Artem Moskalev ๐Ÿ•Š๏ธ
7 months
ICML Spotlight ๐Ÿšจ Equivariance is too slow and expensive, especially when you need global context. It makes us wonder if it even worths the cost, especially in high-dimensional problems? We present Geometric Hyena Networks โ€” a simple equivariant model orders of magnitude more
0
4
11
@SharvVadgama
Sharvaree Vadgama @NeurIPS2025 San Diego
5 months
3. ๐Ÿ’ช Rapidash: Scalable Molecular Modeling Through Controlled Equivariance Breaking Presenting ๐Ÿ’ช๐Ÿš€Rapidash๐Ÿš€ architecture: a flexible architecture allowing for different symmetry-breaking, equivariance-breaking modes through a group convolutional architecture at
2
6
14
@SharvVadgama
Sharvaree Vadgama @NeurIPS2025 San Diego
5 months
2. ๐ŸŒŠControlled Generation with Equivariant Variational Flow Matching Paper: https://t.co/0glGruGgJM Thread:
openreview.net
We derive a controlled generation objective within the framework of Variational Flow Matching (VFM), which casts flow matching as a variational inference problem. We demonstrate that controlled...
@FEijkelboom
Floor Eijkelboom
5 months
Flow Matching (FM) is one of the hottest ideas in generative AI - and itโ€™s everywhere at #ICML2025. But what is it? And why is it so elegant? ๐Ÿค” This thread is an animated, intuitive intro into (Variational) Flow Matching - no dense math required. Let's dive in! ๐Ÿงต๐Ÿ‘‡
3
3
14
@SharvVadgama
Sharvaree Vadgama @NeurIPS2025 San Diego
5 months
1. ๐Ÿง On the Importance of Embedding Norms in Self-Supervised Learning We show that ๐Ÿ”๐Ÿ”Embedding norms play a key role in self-supervised learning (SSL) by - Governing convergence rates during training. -Encoding network confidence โ€” smaller norms correspond to more surprising or
openreview.net
Self-supervised learning (SSL) allows training data representations without a supervised signal and has become an important paradigm in machine learning. Most SSL methods employ the cosine...
1
2
12
@SharvVadgama
Sharvaree Vadgama @NeurIPS2025 San Diego
5 months
๐ŸŽ‰Happy to be in ๐Ÿ‡จ๐Ÿ‡ฆVancouver in the summer for โœจICML2025! Ping me if you want to chat about Symmetries, GDL, Geometric representations + AI4Science, or want to look for the best ramen in town๐Ÿœ! ๐ŸฅExcited to present a few exciting works at the main conference and workshops!
1
6
57
@compute_ri
Putri van der Linden
1 year
Great opportunity to present our latest work on weight sharing via doubly stochastic matrices at @GRaM_org_. Had a blast! Work done with @algarciacast @SharvVadgama Thijs Kuipers @erikjbekkers . You can find it at https://t.co/vo19VDOhTa
4
14
173
@SharvVadgama
Sharvaree Vadgama @NeurIPS2025 San Diego
1 year
0
7
52
@algarciacast
Alejandro Garcรญa
1 year
๐Ÿ” Searching for the Best Framework for GDL+TDL Methods? Look no further! Our latest @GRaM_org_ blog post reveals how the #TopoX suite boosts modularity and optimizes time and memory usage for methods like Equivariant Simplicial Complexes ๐Ÿš€ ๐Ÿ‘‰ Read here https://t.co/O0abzBr9fb
2
16
40
@algarciacast
Alejandro Garcรญa
1 year
๐Ÿค” Ever wondered why Relaxed Group Convolutions take the lead even in ๐Ÿ๐ฎ๐ฅ๐ฅ๐ฒ equivariant tasks? We dive deep into how the equivariance imposed on a network affects its training dynamics ๐Ÿ”Ž ๐Ÿ‘‰ Take a look at our blog post for @GRaM_org_ at https://t.co/epmDhMCuGP
1
19
73
@djjruhe
David Ruhe
1 year
๐Ÿš€ Interested in time series generation?โฒ๏ธExcited to share my @GoogleDeepMind Amsterdam student researcher project: Rolling Diffusion Models! https://t.co/4UXB428ZYY (to appear at ICML 2024) Thanks for the great collaboration @emiel_hoogeboom, @JonathanHeek, @TimSalimans! ๐Ÿงต1/4
11
53
322
@Dafidofff
David Wessels
1 year
๐Ÿฅ  Excited to introduce our latest work on Equivariant Neural Fields (ENFs)! Grounding conditioning variables in geometry ๐Ÿš€ Paper: https://t.co/LQONG1iQ2o Github: https://t.co/yKXZBLDEJU Project Page: https://t.co/lNpz11Z9Hi Details below ๐Ÿ‘‡๐Ÿ‘‡
3
51
226
@GRaM_workshop
Gram Workshop
2 years
๐Ÿ“ข GRaM will now accept papers (both proceedings and extended abstracts) till ๐Ÿ‘๐ซ๐ ๐‰๐ฎ๐ง๐ž ๐Ÿ–๐ฉ๐ฆ ๐”๐“๐‚ !
0
5
15
@SharvVadgama
Sharvaree Vadgama @NeurIPS2025 San Diego
2 years
Final deadline extension!!! Go for ๐Ÿ’ช#GRaM ๐Ÿคฉ !
@GRaM_workshop
Gram Workshop
2 years
๐Ÿ“ข GRaM will now accept papers (both proceedings and extended abstracts) till ๐Ÿ‘๐ซ๐ ๐‰๐ฎ๐ง๐ž ๐Ÿ–๐ฉ๐ฆ ๐”๐“๐‚ !
0
3
12
@SharvVadgama
Sharvaree Vadgama @NeurIPS2025 San Diego
2 years
Go for @GRaM_workshop at #ICML2024 !!
@GRaM_workshop
Gram Workshop
2 years
Let's ๐‘”๐‘’๐‘ก ๐‘”๐‘œ๐‘–๐‘›๐‘” for ๐†๐‘๐š๐Œ ๐ŸŽก!! Time to ๐‘๐‘œ๐‘™๐‘–๐‘ โ„Ž your ๐๐ซ๐จ๐œ๐ž๐ž๐๐ข๐ง๐ ๐ฌ papers and ๐‘Ž๐‘ ๐‘ ๐‘’๐‘š๐‘๐‘™๐‘’ your extended ๐€๐›๐ฌ๐ญ๐ซ๐š๐œ๐ญ๐ฌ! Deadline for submissions: โŒ›๏ธ31st May 11:59pm (AOE)!
0
10
24
@SharvVadgama
Sharvaree Vadgama @NeurIPS2025 San Diego
2 years
@GRaM_workshop Proceedings submission deadline extended to 31st May (AOE) ๐Ÿฅณ. Now you get a couple extra days to polish your brilliant ideas and submit to #GRaM and get it published in โœจPMLR โœจ
2
5
19
@CongLiu202212
Cong Liu
2 years
Are you interested in higher-order message passing on geometric graphs with steerable Clifford representations? Drop by our poster session2 at 16:30 7 May, Halle B #96! #ICLR2024
1
10
57
@SharvVadgama
Sharvaree Vadgama @NeurIPS2025 San Diego
2 years
Come by our poster to learn more about simple+ efficient equivariant architectures! #ICLR2024
@erikjbekkers
Erik Bekkers
2 years
Looking for a simple+powerful *equivariant* graph neural network? Visit ICLR's poster sesh 2 tomorrow 7 May 16:30 CEST, Halle B #246. Imagine this poster but with amazing people around it; At least @SharvVadgama, @davidwromero and me will be there :D, hope to see you too!
0
4
36
@NatashaEve4
Natasha Butt
2 years
Excited to share that our paper โ€œCodeIt: Self-Improving Language Models with Prioritized Hindsight Replayโ€ was accepted into ICML! @blazejmanczak @aukejw Corrado Rainone @davwzha @m_deff @TacoCohen 1/5
1
15
90
@GRaM_workshop
Gram Workshop
2 years
#GRaM template for Blogpost track is up on https://t.co/dVoPiC5MOb . Submit your blogpost on your favorite paper/s or your own in GRaM Workshop blogpost track. Accepted blogpost will be published on our website. Submission deadline 24th May AOE. #ICML2024
gram-workshop.github.io
Geometry-grounded Representation Learning and Generative Modeling
0
5
8
@SharvVadgama
Sharvaree Vadgama @NeurIPS2025 San Diego
2 years
We are very excited to announce that our workshop โ€œ#GRaM: Geometry-grounded Representation learning and generative Modelingโ€ has been accepted to #ICML 2024. We invite papers on the following topics:
2
49
133