Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Stuehmer, Jan"'
We introduce a generative model for protein backbone design utilizing geometric products and higher order message passing. In particular, we propose Clifford Frame Attention (CFA), an extension of the invariant point attention (IPA) architecture from
Externí odkaz:
http://arxiv.org/abs/2411.05238
Ensemble forecasts from numerical weather prediction models show systematic errors that require correction via post-processing. While there has been substantial progress in flexible neural network-based post-processing methods over the past years, mo
Externí odkaz:
http://arxiv.org/abs/2407.11050
Simulating large molecular systems over long timescales requires force fields that are both accurate and efficient. In recent years, E(3) equivariant neural networks have lifted the tension between computational efficiency and accuracy of force field
Externí odkaz:
http://arxiv.org/abs/2404.00050
Graph neural networks (GNNs) have been applied to a large variety of applications in materials science and chemistry. Here, we recapitulate the graph construction for crystalline (periodic) materials and investigate its impact on the GNNs model perfo
Externí odkaz:
http://arxiv.org/abs/2302.14102
Autor:
Chavhan, Ruchika, Gouk, Henry, Stuehmer, Jan, Heggan, Calum, Yaghoobi, Mehrdad, Hospedales, Timothy
Contrastive self-supervised learning methods famously produce high quality transferable representations by learning invariances to different data augmentations. Invariances established during pre-training can be interpreted as strong inductive biases
Externí odkaz:
http://arxiv.org/abs/2302.12712
Providing invariances in a given learning task conveys a key inductive bias that can lead to sample-efficient learning and good generalisation, if correctly specified. However, the ideal invariances for many problems of interest are often not known,
Externí odkaz:
http://arxiv.org/abs/2207.08304
Few-shot learning (FSL) is an important and topical problem in computer vision that has motivated extensive research into numerous methods spanning from sophisticated meta-learning methods to simple transfer learning baselines. We seek to push the li
Externí odkaz:
http://arxiv.org/abs/2204.07305
Autor:
Ungureanu, Dorin, Bogo, Federica, Galliani, Silvano, Sama, Pooja, Duan, Xin, Meekhof, Casey, Stühmer, Jan, Cashman, Thomas J., Tekin, Bugra, Schönberger, Johannes L., Olszta, Pawel, Pollefeys, Marc
Mixed reality headsets, such as the Microsoft HoloLens 2, are powerful sensing devices with integrated compute capabilities, which makes it an ideal platform for computer vision research. In this technical report, we present HoloLens 2 Research Mode,
Externí odkaz:
http://arxiv.org/abs/2008.11239
While a wide range of interpretable generative procedures for graphs exist, matching observed graph topologies with such procedures and choices for its parameters remains an open problem. Devising generative models that closely reproduce real-world g
Externí odkaz:
http://arxiv.org/abs/1910.05639
Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work has focused largely on modifying the variational cost function to achi
Externí odkaz:
http://arxiv.org/abs/1909.05063