N. Thuerey's research group at TUM
@thuereygroup.bsky.social
Professor @ TUM | Making numerical methods and deep learning play nicely together | Fluids | Computer Graphics
Can AI surrogates outperform their training data? Turns out the answer is yes - with a few caveats 😉 tum-pbs.github.io/emulator-sup... #neurips This surprising behavior leads to interesting and fundamental questions about the role of training data, and about how NN surrogates should be evaluated.
November 26, 2025 at 7:58 PM
Can AI surrogates outperform their training data? Turns out the answer is yes - with a few caveats 😉 tum-pbs.github.io/emulator-sup... #neurips This surprising behavior leads to interesting and fundamental questions about the role of training data, and about how NN surrogates should be evaluated.
Reposted by N. Thuerey's research group at TUM
Can your AI surpass the simulator that taught it? What if the key to more accurate PDE modeling lies in questioning your training data's origins? 🤔
Excited to share my #NeurIPS 2025 paper with @thuereygroup.bsky.social: "Neural Emulator Superiority"!
Excited to share my #NeurIPS 2025 paper with @thuereygroup.bsky.social: "Neural Emulator Superiority"!
November 14, 2025 at 8:45 AM
Can your AI surpass the simulator that taught it? What if the key to more accurate PDE modeling lies in questioning your training data's origins? 🤔
Excited to share my #NeurIPS 2025 paper with @thuereygroup.bsky.social: "Neural Emulator Superiority"!
Excited to share my #NeurIPS 2025 paper with @thuereygroup.bsky.social: "Neural Emulator Superiority"!
Congratulations to Hao, Aleksandra and Bjoern for their NeurIPS paper tum-pbs.github.io/inc-paper/ 👍 It analyzes how hybrid PDE solvers fundamentally and provably benefit from "indirect" (force-based) corrections rather than direct ones. Baking the corrections via INC reduces error growth!
November 25, 2025 at 12:11 PM
Congratulations to Hao, Aleksandra and Bjoern for their NeurIPS paper tum-pbs.github.io/inc-paper/ 👍 It analyzes how hybrid PDE solvers fundamentally and provably benefit from "indirect" (force-based) corrections rather than direct ones. Baking the corrections via INC reduces error growth!
I wanted to highlight that source code and data for our physics-based flow matching (PBFM) algorithm are online now at: github.com/tum-pbs/PBFM/ feel free to give it a try, and we'd be curious to hear how it works for you!
November 6, 2025 at 9:49 AM
I wanted to highlight that source code and data for our physics-based flow matching (PBFM) algorithm are online now at: github.com/tum-pbs/PBFM/ feel free to give it a try, and we'd be curious to hear how it works for you!
I'm happy to report that our collaborative project on 3D sparse-reconstruction and super-resolution with diffusion models, physics constraints and PDE Transformers is online now as preprint arxiv.org/abs/2510.19971 and source code github.com/tum-pbs/spar.... Great work Marc, Luis, Qiang and Luca 👍
October 29, 2025 at 2:37 PM
I'm happy to report that our collaborative project on 3D sparse-reconstruction and super-resolution with diffusion models, physics constraints and PDE Transformers is online now as preprint arxiv.org/abs/2510.19971 and source code github.com/tum-pbs/spar.... Great work Marc, Luis, Qiang and Luca 👍
I'm very excited to introduce P3D: our PDE-Transformer architecture in 3 dimensions by . Demonstrated for unprecedented 512^3 resolutions! That means the Transformer produces over 400 million degrees of freedom in one go 😀 a regime that was previously out of reach: arxiv.org/abs/2509.10186
September 16, 2025 at 7:40 AM
I'm very excited to introduce P3D: our PDE-Transformer architecture in 3 dimensions by . Demonstrated for unprecedented 512^3 resolutions! That means the Transformer produces over 400 million degrees of freedom in one go 😀 a regime that was previously out of reach: arxiv.org/abs/2509.10186
Congratulations to Bjoern for his accepted PoF paper on equivariant GraphNets 👍 doi.org/10.1063/5.02...
the core idea is a very generic and powerful one: we compute a local Eigenbasis from flow features for equivariance. Mathematically it's identical to previous approaches, but faster and simpler 😅
the core idea is a very generic and powerful one: we compute a local Eigenbasis from flow features for equivariance. Mathematically it's identical to previous approaches, but faster and simpler 😅
September 9, 2025 at 7:15 AM
Congratulations to Bjoern for his accepted PoF paper on equivariant GraphNets 👍 doi.org/10.1063/5.02...
the core idea is a very generic and powerful one: we compute a local Eigenbasis from flow features for equivariance. Mathematically it's identical to previous approaches, but faster and simpler 😅
the core idea is a very generic and powerful one: we compute a local Eigenbasis from flow features for equivariance. Mathematically it's identical to previous approaches, but faster and simpler 😅
I also wanted to mention that our paper detailing the differentiable SPH solver by Rene is online now on arxiv: arxiv.org/abs/2507.21684 If you're interested in fast and efficient neighborhoods, differentiable SPH operators and neat first optimization and learning tasks, please take a look!
August 1, 2025 at 7:37 AM
I also wanted to mention that our paper detailing the differentiable SPH solver by Rene is online now on arxiv: arxiv.org/abs/2507.21684 If you're interested in fast and efficient neighborhoods, differentiable SPH operators and neat first optimization and learning tasks, please take a look!
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. Code and paper available at tum-pbs.github.io/pde-transfor...
June 30, 2025 at 7:05 PM
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. Code and paper available at tum-pbs.github.io/pde-transfor...
I'm really excited to share our latest work combining physics priors with probabilistic models: Flow Matching Meets PDEs - A Unified Framework for Physics-Constrained Generation , arxiv.org/abs/2506.08604 , great work by Giacomo and Qiang!
June 17, 2025 at 2:36 PM
I'm really excited to share our latest work combining physics priors with probabilistic models: Flow Matching Meets PDEs - A Unified Framework for Physics-Constrained Generation , arxiv.org/abs/2506.08604 , great work by Giacomo and Qiang!
Have you faced challenges like SPH-based inverse problems, or learning Lagrangian closure models?
For these we’re excited to announce the first public release of DiffSPH , our differentiable Smoothed Particle Hydrodynamics solver.
Code: diffsph.fluids.dev
Short demo: lnkd.in/dYABSeKG
For these we’re excited to announce the first public release of DiffSPH , our differentiable Smoothed Particle Hydrodynamics solver.
Code: diffsph.fluids.dev
Short demo: lnkd.in/dYABSeKG
June 13, 2025 at 2:08 PM
Have you faced challenges like SPH-based inverse problems, or learning Lagrangian closure models?
For these we’re excited to announce the first public release of DiffSPH , our differentiable Smoothed Particle Hydrodynamics solver.
Code: diffsph.fluids.dev
Short demo: lnkd.in/dYABSeKG
For these we’re excited to announce the first public release of DiffSPH , our differentiable Smoothed Particle Hydrodynamics solver.
Code: diffsph.fluids.dev
Short demo: lnkd.in/dYABSeKG
Congratulations to Bernhard for his first #SIGGRAPH paper! Great work 👍 His two-phase Navier-Stokes solver is even more impressive given the fact that it's all done on a regular workstation, and without a GPU. Enjoy the sims in full screen & hi-quality here: youtu.be/nt9BohngvoE
June 4, 2025 at 7:14 PM
Congratulations to Bernhard for his first #SIGGRAPH paper! Great work 👍 His two-phase Navier-Stokes solver is even more impressive given the fact that it's all done on a regular workstation, and without a GPU. Enjoy the sims in full screen & hi-quality here: youtu.be/nt9BohngvoE
I also just recorded a quick overview video for our new PICT solver: youtu.be/GGLidL0oT3s , enjoy! In case you missed it: PICT provides a new fully-differentiable multi-block Navier-Stokes solver for AI and learning tasks in PyTorch, e.g. learning turbulence closure in 3D
Introducing PICT: the differentiable Fluid Solver for AI & machine learning in PyTorch
YouTube video by Nils Thuerey
youtu.be
June 2, 2025 at 12:38 PM
I also just recorded a quick overview video for our new PICT solver: youtu.be/GGLidL0oT3s , enjoy! In case you missed it: PICT provides a new fully-differentiable multi-block Navier-Stokes solver for AI and learning tasks in PyTorch, e.g. learning turbulence closure in 3D
I'd like to highlight PICT, our new differentiable Fluid Solver built for AI & learning: github.com/tum-pbs/PICT
Simulating fluids is hard, and learning 3D closure models even harder: This is where PICT comes in — a GPU-accelerated, fully differentiable fluid solver for PyTorch 🥳
Simulating fluids is hard, and learning 3D closure models even harder: This is where PICT comes in — a GPU-accelerated, fully differentiable fluid solver for PyTorch 🥳
May 28, 2025 at 3:41 PM
I'd like to highlight PICT, our new differentiable Fluid Solver built for AI & learning: github.com/tum-pbs/PICT
Simulating fluids is hard, and learning 3D closure models even harder: This is where PICT comes in — a GPU-accelerated, fully differentiable fluid solver for PyTorch 🥳
Simulating fluids is hard, and learning 3D closure models even harder: This is where PICT comes in — a GPU-accelerated, fully differentiable fluid solver for PyTorch 🥳
I can highly recommend checking out Mario's talk about our Diffusion Graph Net paper from ICLR'25: www.youtube.com/watch?v=4Vx_... , enjoy!
Learning Distributions of Complex Fluid Simulations with Diffusion Graph Networks
YouTube video by Mario Lino
www.youtube.com
May 21, 2025 at 12:58 PM
I can highly recommend checking out Mario's talk about our Diffusion Graph Net paper from ICLR'25: www.youtube.com/watch?v=4Vx_... , enjoy!
I wanted to highlight PBDL's brand-new sections on diffusion models with code and derivations! Great work by Benjamin Holzschuh, with neat Jupyter notebooks 👍 All the way from normalizing flow basics over score matching to denoising & flow matching. E.g., colab.research.google.com/github/tum-p...
May 13, 2025 at 7:19 AM
I wanted to highlight PBDL's brand-new sections on diffusion models with code and derivations! Great work by Benjamin Holzschuh, with neat Jupyter notebooks 👍 All the way from normalizing flow basics over score matching to denoising & flow matching. E.g., colab.research.google.com/github/tum-p...
I wanted to highlight that our project website (with code!) for our progressively-refined training with physics simulations is up now at: kanishkbh.github.io/prdp-paper/ #ICLR25 , the main ideas are: match network approximation and physics accuracy, refine the physics over the course of training.
April 11, 2025 at 2:21 PM
I wanted to highlight that our project website (with code!) for our progressively-refined training with physics simulations is up now at: kanishkbh.github.io/prdp-paper/ #ICLR25 , the main ideas are: match network approximation and physics accuracy, refine the physics over the course of training.
The full PBDL book is available in a single PDF now arxiv.org/pdf/2109.05237, and has grown to 451 pages 😳 Enjoy all the new highlights on generative models, simulation-based constraints and long term stability with diffusion models 😁
March 28, 2025 at 8:23 AM
The full PBDL book is available in a single PDF now arxiv.org/pdf/2109.05237, and has grown to 451 pages 😳 Enjoy all the new highlights on generative models, simulation-based constraints and long term stability with diffusion models 😁
I'm very excited to highlight PBDL v0.3 www.physicsbaseddeeplearning.org, the latest version of our physics-based deep learning "book" 🥳 This version features a huge new chapter on generative AI, covering topics ranging from the derivation, over graph-based inference to physics-based constraints!
March 20, 2025 at 7:36 PM
I'm very excited to highlight PBDL v0.3 www.physicsbaseddeeplearning.org, the latest version of our physics-based deep learning "book" 🥳 This version features a huge new chapter on generative AI, covering topics ranging from the derivation, over graph-based inference to physics-based constraints!
Congratulations to Kanishk and Felix 👍 for their #ICLR'25 paper "Progressively Refined Differentiable Physics" kanishkbh.github.io/prdp-paper/ , the key insight is that training can be accelerated substantially by using fast approximates of the gradient (especially in early phases of training)
February 25, 2025 at 7:06 AM
Congratulations to Kanishk and Felix 👍 for their #ICLR'25 paper "Progressively Refined Differentiable Physics" kanishkbh.github.io/prdp-paper/ , the key insight is that training can be accelerated substantially by using fast approximates of the gradient (especially in early phases of training)
Congratulations to Youssef and Benjamin 👍 for their #ICLR'25 paper on Truncated Diffusion Sampling openreview.net/forum?id=0Fb... It investigates several key questions of generative AI and diffusion for physics simulations to improve accuracy via Tweedie's formula
February 19, 2025 at 1:29 AM
Congratulations to Youssef and Benjamin 👍 for their #ICLR'25 paper on Truncated Diffusion Sampling openreview.net/forum?id=0Fb... It investigates several key questions of generative AI and diffusion for physics simulations to improve accuracy via Tweedie's formula
Reposted by N. Thuerey's research group at TUM
Can AI Help Solve Complex Physics Equations? Meet APEBench, an innovative benchmark suite introduced by our Junior Member Felix Köhler, together with our PIs Rüdiger Westermann and Nils Thuerey as well as co-author Simon Niedermayr. Read more: mcml.ai/news/2025-02...
February 11, 2025 at 10:49 AM
Can AI Help Solve Complex Physics Equations? Meet APEBench, an innovative benchmark suite introduced by our Junior Member Felix Köhler, together with our PIs Rüdiger Westermann and Nils Thuerey as well as co-author Simon Niedermayr. Read more: mcml.ai/news/2025-02...
Congratulations also to Patrick 👍 for his ICLR paper on Temporal Difference (TD) learning openreview.net/forum?id=j3b... , in it We solve the decades-old puzzle of why TD can solve complex RL tasks that Gradient Descent cannot. Our novel theory shows for 2D how TD can counter ill-conditioning 🤗
February 7, 2025 at 2:06 AM
Congratulations also to Patrick 👍 for his ICLR paper on Temporal Difference (TD) learning openreview.net/forum?id=j3b... , in it We solve the decades-old puzzle of why TD can solve complex RL tasks that Gradient Descent cannot. Our novel theory shows for 2D how TD can counter ill-conditioning 🤗
Congrats to Qiang 👏 for the accept of his #ICLR paper on the "ConFIG" optimizer openreview.net/forum?id=APo... Conflict free learning for PINNs, multi task objectives and more! Outperforms all existing optimizers 😁 source code and examples are online at tum-pbs.github.io/ConFIG/
February 3, 2025 at 4:43 AM
Congrats to Qiang 👏 for the accept of his #ICLR paper on the "ConFIG" optimizer openreview.net/forum?id=APo... Conflict free learning for PINNs, multi task objectives and more! Outperforms all existing optimizers 😁 source code and examples are online at tum-pbs.github.io/ConFIG/