Thuerey Group at TUM's banner
Thuerey Group at TUM's profile picture

Thuerey Group at TUM

@thuereyGroup • 3,093 subscribers

Our focus is to develop numerical methods for physics simulations with deep learning techniques.

Shorts

Congrats to Mario 👏 for the accept of his ICLR paper on "Diffusion Graph Nets", predicting complex distributions of flow states on unstructured meshes Highly efficient, works even if the training data has only a fraction of the flow statistics.

Congrats to Mario 👏 for the accept of his ICLR paper on "Diffusion Graph Nets", predicting complex distributions of flow states on unstructured meshes Highly efficient, works even if the training data has only a fraction of the flow statistics.

24,996 просмотров

Congratulations also to Patrick 👍 for his #ICLR paper on Temporal Difference (TD) learning , in it We solve the decades-old puzzle of why TD can solve complex RL tasks that Gradient Descent cannot.

Congratulations also to Patrick 👍 for his #ICLR paper on Temporal Difference (TD) learning , in it We solve the decades-old puzzle of why TD can solve complex RL tasks that Gradient Descent cannot.

22,074 просмотров

I'm excited to share our paper "Flow Matching for Posterior Inference with Simulator Feedback" 🤩 The key idea is to incorporate physics-constraints with guiding so that the posterior isn't biased. Highly accurate solutions, better than pure learning!

I'm excited to share our paper "Flow Matching for Posterior Inference with Simulator Feedback" 🤩 The key idea is to incorporate physics-constraints with guiding so that the posterior isn't biased. Highly accurate solutions, better than pure learning!

21,204 просмотров

Get ready for the PDE-Transformer: our new NN architecture tailored to scientific tasks. It combines hierarchical processing (UDiT), scalability (SWin) and flexible conditioning mechanisms. The paper shows it outperforming existing SOTA architectures 😁

Get ready for the PDE-Transformer: our new NN architecture tailored to scientific tasks. It combines hierarchical processing (UDiT), scalability (SWin) and flexible conditioning mechanisms. The paper shows it outperforming existing SOTA architectures 😁

13,422 просмотров

I'm happy to announce PhiFlow version 3.0! Just in time for #ICML2024 😀 There are many new features and improvements, such as unstructured meshes, particle processing, improved linear solves and more... Give it a try at:

I'm happy to announce PhiFlow version 3.0! Just in time for #ICML2024 😀 There are many new features and improvements, such as unstructured meshes, particle processing, improved linear solves and more... Give it a try at:

10,211 просмотров