Zobrazeno 1 - 10
of 59 544
pro vyhledávání: '"Rudolf, P"'
Prototype Learning methods provide an interpretable alternative to black-box deep learning models. Approaches such as ProtoPNet learn, which part of a test image "look like" known prototypical parts from training images, combining predictive power wi
Externí odkaz:
http://arxiv.org/abs/2410.08925
Autor:
Liu, Puze, Günster, Jonas, Funk, Niklas, Gröger, Simon, Chen, Dong, Bou-Ammar, Haitham, Jankowski, Julius, Marić, Ante, Calinon, Sylvain, Orsula, Andrej, Olivares-Mendez, Miguel, Zhou, Hongyi, Lioutikov, Rudolf, Neumann, Gerhard, Zhalehmehrabi, Amarildo Likmeta Amirhossein, Bonenfant, Thomas, Restelli, Marcello, Tateo, Davide, Liu, Ziyuan, Peters, Jan
Machine learning methods have a groundbreaking impact in many application domains, but their application on real robotic platforms is still limited. Despite the many challenges associated with combining machine learning technology with robotics, robo
Externí odkaz:
http://arxiv.org/abs/2411.05718
Bilayer graphene twisted at the angle of about 1.1{\deg} better known as magic angle, exhibits ultra-flat moir\'e superlattice bands that are a source of highly-tunable, exotic quantum phenomena. Such phenomena, like superconductivity, correlated Mot
Externí odkaz:
http://arxiv.org/abs/2411.00854
Autor:
Blank, Nils, Reuss, Moritz, Rühle, Marcel, Yağmurlu, Ömer Erdinç, Wenzel, Fabian, Mees, Oier, Lioutikov, Rudolf
A central challenge towards developing robots that can relate human language to their perception and actions is the scarcity of natural language annotations in diverse robot datasets. Moreover, robot policies that follow natural language instructions
Externí odkaz:
http://arxiv.org/abs/2410.17772
Autor:
Skøien, Jon Olav, Lampach, Nicolas, Ramos, Helena, Seljak, Rudolf, Koeble, Renate, See, Linda, van der Velde, Marijn
We develop a flexible approach by combining the Quadtree-based method with suppression to maximize the utility of the grid data and simultaneously to reduce the risk of disclosing private information from individual units. To protect data confidentia
Externí odkaz:
http://arxiv.org/abs/2410.17601
Autor:
Berceanu, Barbu Rudolf
We recall the fundamental theorem of J.F. Ritt, with a stress on the action of the affine group and canonical forms of complex polynomials. Then we give a complete presentation of the monoid $(\mathbb{C}\mbox{[X]},\circ)$. A list of decomposable poly
Externí odkaz:
http://arxiv.org/abs/2410.12447
This work introduces Transformer-based Off-Policy Episodic Reinforcement Learning (TOP-ERL), a novel algorithm that enables off-policy updates in the ERL framework. In ERL, policies predict entire action trajectories over multiple time steps instead
Externí odkaz:
http://arxiv.org/abs/2410.09536
Generative models lack rigorous statistical guarantees for their outputs and are therefore unreliable in safety-critical applications. In this work, we propose Sequential Conformal Prediction for Generative Models (SCOPE-Gen), a sequential conformal
Externí odkaz:
http://arxiv.org/abs/2410.01660
Autor:
Ai, Xian-Yue, Soldatov, Ivan, Oleschko, Leon, Seema, Müller, Martina, Karpitschka, Stefan, Schäfer, Rudolf, Goennenwein, Sebastian T. B.
Combining wide-field magneto-optical Kerr microscopy with a time-lapse analysis scheme allows investigating magnetization fluctuations with high spatial as well as temporal resolution. We here use this technique to study magnetization fluctuations in
Externí odkaz:
http://arxiv.org/abs/2409.15876
Autor:
van Herten, Rudolf L. M., Lagogiannis, Ioannis, Wolterink, Jelmer M., Bruns, Steffen, Meulendijks, Eva R., Dey, Damini, de Groot, Joris R., Henriques, José P., Planken, R. Nils, Saitta, Simone, Išgum, Ivana
Deep learning-based medical image segmentation and surface mesh generation typically involve a sequential pipeline from image to segmentation to meshes, often requiring large training datasets while making limited use of prior geometric knowledge. Th
Externí odkaz:
http://arxiv.org/abs/2409.11837