Jan-Willem van de Meent
@jwvdm
Followers
3K
Following
3K
Media
49
Statuses
1K
Associate Professor (UHD) at the University of Amsterdam.
Amsterdam, NL
Joined March 2009
🔥 WANTED: Student Researcher to join me,@ValentinDeBort1,@thjashin,@liwenliang,@ArthurGretton in DeepMind London. You'll be working on Multimodal Diffusions for science. Apply here
4
46
308
We have a postdoc opening on the development of AI methods for accelerating computational fluid mechanics: https://t.co/h16I2AUxYY Deadline for applications soon –– 28 Nov –– e-mail me if you are planning to apply!
werkenbij.uva.nl
Are you interested in developing AI methods that can make physics simulations orders of magnitude faster? If the answer is yes, please continue reading!
0
5
9
Cool news: our extended Riemannian Gaussian VFM paper is out! 🔮 We define and study a variational objective for probability flows 🌀 on manifolds with closed-form geodesics. @FEijkelboom @a_ppln @CongLiu202212 @wellingmax @jwvdm @erikjbekkers 🔥 📜 https://t.co/PE6I6YcoTn
2
25
51
Clifford Algebra Neural Networks are undeservedly dismissed for being too slow, but they don't have to be! 🚀Introducing **flash-clifford**: a hardware-efficient implementation of Clifford Algebra NNs in Triton, featuring the fastest equivariant primitives that scale.
6
33
129
We asked the same question: how can we combine the strengths of continuous and discrete approaches? Similar to CDCD, in our work, Purrception, we extend Variational FM to model VQ latents through continuous-discrete transport for image generation :D 👉 https://t.co/KIog9mLNWb
In diffusion LMs, discrete methods have all but displaced continuous ones (🥲). Interesting new trend: why not both? Use continuous methods to make discrete diffusion better. Diffusion duality: https://t.co/KPO56vDygp CADD: https://t.co/CNOIWcUIMo CCDD:
1
13
70
Submit your work on to the EurIPS workshop on on Differentiable Systems and Scientific Machine Learning! Submission deadline: 10 October Notification: 31 October Workshop: 6 or 7 December in Copenhagen
🚨🚨🚨 Call for papers alert 🚨🚨🚨 The "Differentiable Systems and Scientific Machine Learning" workshop at the 1st EurIPS conference is now accepting submissions! Let's explore the intersection of differentiable programming and SciML together. https://t.co/ligvk029Jl
0
0
3
Job alert 🚨 Our team is looking for ML Research Scientist to join Johnson&Johnson research. We work on geometric deep learning and LLMs in drug discovery. 🧬🤓 Drop me a message if you’re interested, or share if you know someone who’s a great fit! Multiple locations available.
0
3
20
We’re excited to introduce the Open Direct Air Capture 2025 dataset, the largest open dataset for discovering advanced materials that capture CO2 directly from the air. Developed by Meta FAIR, @GeorgiaTech, and @cusp_ai, this release enables rapid, accurate screening of carbon
39
106
580
It was a huge pleasure to work with the @AIatMeta and @GeorgiaTech teams to release this new and exciting ODAC25 dataset on CO2 capture materials.
We’re excited to introduce the Open Direct Air Capture 2025 dataset, the largest open dataset for discovering advanced materials that capture CO2 directly from the air. Developed by Meta FAIR, @GeorgiaTech, and @cusp_ai, this release enables rapid, accurate screening of carbon
1
10
99
Generative models excel at images and text, but tabular data remains a challenge.🤔 We introduce 🐈 TabbyFlow 🐈 - a variational flow matching approach with general exponential families for mixed-type tables. Work with @AndresGuzco & @jwvdm accepted to #ICML2025 🎉 👇 1/n
5
25
79
Happens today! 🗓️Tue, July 15 @ 11 AM 📍East Exhibition Hall A-B #E-3512 Unfortunately I was not able to attend, so please DM if you want to chat about hierarchical models, irregular geometries or scalable physical modeling :) @FEijkelboom will present the poster for me on-site
🤹 New blog post! I write about our recent work on using hierarchical trees to enable sparse attention over irregular data (point clouds, meshes) - Erwin Transformer. blog: https://t.co/dClrZ4tOoz paper: https://t.co/EKUH9gJ7o3 Compressed version in the thread below:
2
13
41
@pguptacs is at #ICML2025 this week presenting our work on using ML to find dualities in statistical physics. so far we can rediscover Kramers-Wannier-type duality, and we hope to eventually find completely new examples. https://t.co/3u7qiHaA2e
openreview.net
The notion of duality -- that a given physical system can have two different mathematical descriptions -- is a key idea in modern theoretical physics. Establishing a duality in lattice statistical...
⚖️ A machine learning approach to duality in statistical physics by Prateek Gupta, Andrea Ferrari, @nblqbl 📜 https://t.co/LJUWoTNRko
https://t.co/isc6TOmX8n 🧵2 / 7
1
3
9
Interested in efficient equivariance for long-context? Visit our Geoemtric Hyena poster at ICML! ⭐️ Spotlight⭐️ When: 11 a.m. — 1:30 p.m Wed July 16 Where: East Exhibition Hall A-B #E-3103
ICML Spotlight 🚨 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 — a simple equivariant model orders of magnitude more
0
4
23
Excited to be at #ICML2025 in Vancouver! 🇨🇦 Come chat with me about (Variational) Flow Matching 🌊 - or anything generative modeling, really. Also: I'm currently open to internship opportunities!
2
4
53
Nice primer on flow matching (FM) and variational flow matching (VFM) by Floor Eijkelboom (@feijkelboom)!
Flow Matching (FM) is one of the hottest ideas in generative AI - and it’s everywhere at #ICML2025. But what is it? And why is it so elegant? 🤔 This thread is an animated, intuitive intro into (Variational) Flow Matching - no dense math required. Let's dive in! 🧵👇
0
2
15
🤹 New blog post! I write about our recent work on using hierarchical trees to enable sparse attention over irregular data (point clouds, meshes) - Erwin Transformer. blog: https://t.co/dClrZ4tOoz paper: https://t.co/EKUH9gJ7o3 Compressed version in the thread below:
7
89
522
Very happy to say that our work with @pguptacs and Andrea Ferrari on using machine learning to find physics dualities was accepted at #ICML2025! (Thread describing the idea below...)
Something a little bit different from my usual: with Andrea Ferrari and @pguptacs, we investigated whether we can use machine learning to find *dualities* in statistical physics. https://t.co/ossXGwT3pc A short thread:
6
3
26
🐳 Controlled Generation with Equivariant Variational Flow Matching by @FEijkelboom, @zmheiko, @SharvVadgama, @erikjbekkers, @wellingmax, @canaesseth*, @jwvdm* 📜 soon! 🧵7 / 7
0
3
19
🌊 Exponential Family Variational Flow Matching for Tabular Data Generation by Andrés Guzmán-Cordero*, @FEijkelboom*, @jwvdm 📜 soon! 🧵6 / 7
1
3
16