Zobrazeno 1 - 10
of 1 245
pro vyhledávání: '"Fischer, Johannes"'
Autor:
Fuest, Michael, Ma, Pingchuan, Gui, Ming, Fischer, Johannes S., Hu, Vincent Tao, Ommer, Bjorn
Diffusion Models are popular generative modeling methods in various vision tasks, attracting significant attention. They can be considered a unique instance of self-supervised learning methods due to their independence from label annotation. This sur
Externí odkaz:
http://arxiv.org/abs/2407.00783
Autor:
Şeker, Enes, Thomas, Rijil, von Hünefeld, Guillermo, Suckow, Stephan, Kaveh, Mahdi, Ronniger, Gregor, Safari, Pooyan, Sackey, Isaac, Stahl, David, Schubert, Colja, Fischer, Johannes Karl, Freund, Ronald, Lemme, Max C.
The fields of machine learning and artificial intelligence drive researchers to explore energy-efficient, brain-inspired new hardware. Reservoir computing encompasses recurrent neural networks for sequential data processing and matches the performanc
Externí odkaz:
http://arxiv.org/abs/2406.13549
To plan safely in uncertain environments, agents must balance utility with safety constraints. Safe planning problems can be modeled as a chance-constrained partially observable Markov decision process (CC-POMDP) and solutions often use expensive rol
Externí odkaz:
http://arxiv.org/abs/2405.00644
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
Validating robotic systems in safety-critical appli-cations requires testing in many scenarios including rare edgecases that are unlikely to occur, requiring to complement real-world testing with testing in simulation. Generative models canbe used to
Externí odkaz:
http://arxiv.org/abs/2403.11728
Autor:
Fischer, Johannes S., Gui, Ming, Ma, Pingchuan, Stracke, Nick, Baumann, Stefan A., Ommer, Björn
Recently, there has been tremendous progress in visual synthesis and the underlying generative models. Here, diffusion models (DMs) stand out particularly, but lately, flow matching (FM) has also garnered considerable interest. While DMs excel in pro
Externí odkaz:
http://arxiv.org/abs/2312.07360
Autor:
Arpanaei, Farhad, Zefreh, Mahdi Ranjbar, Hernández, José Alberto, Shariati, Behnam, Fischer, Johannes, Rivas-Moscoso, José Manuel, Jiménez, Filipe, Fernández-Palacios, Juan Pedro, Larrabeiti, David
We propose an algorithm for calculating the optimum launch power over the entire C+L bands by maximizing the cumulative link GSNR of a channel plan built upon multiple modulation formats, with application to dynamic EONs. Exact last-fit spectrum assi
Externí odkaz:
http://arxiv.org/abs/2308.13578