Zobrazeno 1 - 10
of 800
pro vyhledávání: '"Stefan, Andreas"'
Autor:
Stracke, Nick, Baumann, Stefan Andreas, Susskind, Joshua M., Bautista, Miguel Angel, Ommer, Björn
Text-to-image generative models have become a prominent and powerful tool that excels at generating high-resolution realistic images. However, guiding the generative process of these models to consider detailed forms of conditioning reflecting style
Externí odkaz:
http://arxiv.org/abs/2405.07913
We present further applications of the formalism introduced by the authors in arXiv:2308.10949, which allows embedding of a broad class of generalized LTB models into effective spherically symmetric spacetimes. We focus on regular black hole models,
Externí odkaz:
http://arxiv.org/abs/2405.03554
Autor:
Baumann, Stefan Andreas, Krause, Felix, Neumayr, Michael, Stracke, Nick, Hu, Vincent Tao, Ommer, Björn
In recent years, advances in text-to-image (T2I) diffusion models have substantially elevated the quality of their generated images. However, achieving fine-grained control over attributes remains a challenge due to the limitations of natural languag
Externí odkaz:
http://arxiv.org/abs/2403.17064
Autor:
Hu, Vincent Tao, Baumann, Stefan Andreas, Gui, Ming, Grebenkova, Olga, Ma, Pingchuan, Fischer, Johannes, Ommer, Björn
The diffusion model has long been plagued by scalability and quadratic complexity issues, especially within transformer-based structures. In this study, we aim to leverage the long sequence modeling capability of a State-Space Model called Mamba to e
Externí odkaz:
http://arxiv.org/abs/2403.13802
Autor:
Gui, Ming, Fischer, Johannes S., Prestel, Ulrich, Ma, Pingchuan, Kotovenko, Dmytro, Grebenkova, Olga, Baumann, Stefan Andreas, Hu, Vincent Tao, Ommer, Björn
Monocular depth estimation is crucial for numerous downstream vision tasks and applications. Current discriminative approaches to this problem are limited due to blurry artifacts, while state-of-the-art generative methods suffer from slow sampling du
Externí odkaz:
http://arxiv.org/abs/2403.13788
Autor:
Crowson, Katherine, Baumann, Stefan Andreas, Birch, Alex, Abraham, Tanishq Mathew, Kaplan, Daniel Z., Shippole, Enrico
We present the Hourglass Diffusion Transformer (HDiT), an image generative model that exhibits linear scaling with pixel count, supporting training at high-resolution (e.g. $1024 \times 1024$) directly in pixel-space. Building on the Transformer arch
Externí odkaz:
http://arxiv.org/abs/2401.11605
Based on modifications inspired from loop quantum gravity (LQG), spherically symmetric models have recently been explored to understand the resolution of classical singularities and the fate of the spacetime beyond. While such phenomenological studie
Externí odkaz:
http://arxiv.org/abs/2308.10953
We generalize the existing works on the way (generalized) LTB models can be embedded into polymerized spherically symmetric models in several aspects. We re-examine such an embedding at the classical level and show that a suitable LTB condition can o
Externí odkaz:
http://arxiv.org/abs/2308.10949
Autor:
Omar Ammous, Regina Kampo, Maximilian Wollsching-Strobel, Maximilian Zimmermann, Stefan Andreas, Tim Friede, Doreen Kroppen, Sarah Stanzel, Susanna Salem, Wolfram Windisch, Tim Mathes
Publikováno v:
European Respiratory Review, Vol 33, Iss 173 (2024)
Introduction Adherence to COPD management strategies is complex, and it is unclear which intervention may enhance it. Objectives We aim to evaluate the effectiveness of adherence-enhancing interventions, alone or compared to interventions, for patien
Externí odkaz:
https://doaj.org/article/aa75400d43d74138a0251b14c0ac182f
Publikováno v:
Phys. Rev. D 105, 066023 2022
For classical gravitational systems the lapse function and the shift vector are usually determined by imposing appropriate gauge fixing conditions and then demanding their preservation with respect to the dynamics generated by a canonical Hamiltonian
Externí odkaz:
http://arxiv.org/abs/2112.13860