@ker_weissinger Profile picture

Kerstin Weissinger

@ker_weissinger

📍 Amsterdam 🤸‍♀️ Human Movement Sciences 👩🏻‍⚕️ Occupational Therapy 🏢 Vrije Universiteit Amsterdam

Joined May 2022
Similar User
IrfanRefai 🍉 photo

@refai_irfan

Sauvik Das Gupta photo

@sauvikdasgupta

Margit Bach photo

@bach_margit

Masahiro SHINYA photo

@shinya_masahiro

Brenda van Keeken photo

@bvkeeken

Kerstin Weissinger Reposted

Super hyped to share NeuralDEM -- the first real-time simulation of industrial particulate flows. NeuralDEM replaces Discrete Element Method (DEM) routines and coupled (CFD-DEM) multiphysics simulations. 🧵 📜: arxiv.org/abs/2411.09678 🖥️: nx-ai.github.io/NeuralDEM/


Kerstin Weissinger Reposted

xLSTM is out -- putting LSTM networks on steroids to become a more than serious LLM competitor. How? Via exponential gating and enhanced (cell state) memory capacities. Does it work? Oh, yeah 🚀🚀 arxiv.org/abs/2405.04517


Kerstin Weissinger Reposted

Personal update: last month, I re-joined the group of my mentor @HochreiterSepp and my amazing colleague @gklambauer in Linz, opening my own group "AI for data-driven simulations". We all share the vision to create a large-scale AI ecosystem in Linz. Big news to come soon 🚀

jo_brandstetter's tweet image. Personal update: last month, I re-joined the group of my mentor @HochreiterSepp and my amazing colleague @gklambauer in Linz, opening my own group "AI for data-driven simulations". We all share the vision to create a large-scale AI ecosystem in Linz. Big news to come soon 🚀

Last week, my colleagues and I got the chance to present the work we do at @PULSE_racingNL at the @ISCOMS Together we gave a workshop about Spinal Cord Injury and Functional Electrical Stimulation (FES) and presented our research on improving FES-cycling.

ker_weissinger's tweet image. Last week, my colleagues and I got the chance to present the work we do at @PULSE_racingNL at the @ISCOMS. Together we gave a workshop about Spinal Cord Injury and Functional Electrical Stimulation (FES) and presented our research on improving FES-cycling.

Kerstin Weissinger Reposted

Things began to look very unusual two months ago. Today the charts need no commentary, they speak for themselves. This is the Atlantic.

DrTELS's tweet image. Things began to look very unusual two months ago.
Today the charts need no commentary, they speak for themselves.
This is the Atlantic.

This is so unusual. That's a *huge* amount of energy being transferred to the atmosphere. Expect extreme temperature and storm records. Just the top few metres of our oceans store as much energy as the entirety of our atmosphere. I'm very concerned for later this year into 2024.



Kerstin Weissinger Reposted

Het VU-DreamTeam @PULSE_racingNL is op zoek naar nieuwe studentleden voor aankomend studiejaar. Ik zou het doen als ik student was :-). vu.nl/dreamteams @VU_FGB @Reade_020 @AISS_nl

Janssen_Thomas1's tweet image. Het VU-DreamTeam @PULSE_racingNL  is op zoek naar nieuwe studentleden voor aankomend studiejaar. Ik zou het doen als ik student was :-). <a style="text-decoration: none;" rel="nofollow" target="_blank" href="https://t.co/CYOzZz38sU">vu.nl/dreamteams</a> @VU_FGB @Reade_020 @AISS_nl

Kerstin Weissinger Reposted

Neural PDE solving is growing rapidly. It's time for strong baseline modes and common codebases. PDEArena is our take with more than 20 models and several large-scale PDE problems. It turns out modern U-Nets are amazing 🔥🔥

Excited to opensource PDEArena: a modern, scalable PDE surrogate learning framework. With over 20 models and many different PDE tasks. Blog: microsoft.com/en-us/research… Website: microsoft.github.io/pdearena/ Paper: arxiv.org/abs/2209.15616 Authors: @rejuvyesh, @jo_brandstetter 1/n

rejuvyesh's tweet image. Excited to opensource PDEArena: a modern, scalable PDE surrogate learning framework. With over 20 models and many different PDE tasks.
Blog: <a style="text-decoration: none;" rel="nofollow" target="_blank" href="https://t.co/eCLFZhUEtm">microsoft.com/en-us/research…</a>

Website: <a style="text-decoration: none;" rel="nofollow" target="_blank" href="https://t.co/sEkgqUqkXE">microsoft.github.io/pdearena/</a>
Paper: <a style="text-decoration: none;" rel="nofollow" target="_blank" href="https://t.co/tOkv9FtrGk">arxiv.org/abs/2209.15616</a>
Authors: @rejuvyesh, @jo_brandstetter
1/n


Kerstin Weissinger Reposted

New work on how to construct neural network layers on composite objects of scalars, vectors, bivectors, … --> multivectors! Via Clifford algebras, we generalize convolution and Fourier transforms to multivectors, especially relevant for PDE modeling: arxiv.org/abs/2209.04934


United States Trends
Loading...

Something went wrong.


Something went wrong.