3 citations · 5 across the 3 of their papers we have counts for
3 papers
cs.LG2024
Stabilizing Backpropagation Through Time to Learn Complex Physics
Patrick Schnell, Nils Thuerey
Of all the vector fields surrounding the minima of recurrent learning setups, the gradient field with its exploding and vanishing updates appears a poor choice for optimization, of…
cs.LG2022★ 2 cited
Half-Inverse Gradients for Physical Deep Learning
Patrick Schnell, Philipp Holl, Nils Thuerey
Recent works in deep learning have shown that integrating differentiable physics simulators into the training process can greatly improve the quality of results. Although this comb…
cs.LG2022★ 3 cited
Simulating Liquids with Graph Networks
Jonathan Klimesch, Philipp Holl, Nils Thuerey
Simulating complex dynamics like fluids with traditional simulators is computationally challenging. Deep learning models have been proposed as an efficient alternative, extending o…