Zobrazeno 1 - 10
of 85 531
pro vyhledávání: '"Bastian ,"'
Early identification of stroke is crucial for intervention, requiring reliable models. We proposed an efficient retinal image representation together with clinical information to capture a comprehensive overview of cardiovascular health, leveraging l
Externí odkaz:
http://arxiv.org/abs/2411.05597
Autor:
Ehm, Viktoria, Amrani, Nafie El, Xie, Yizheng, Bastian, Lennart, Gao, Maolin, Wang, Weikang, Sang, Lu, Cao, Dongliang, Lähner, Zorah, Cremers, Daniel, Bernard, Florian
Finding correspondences between 3D shapes is an important and long-standing problem in computer vision, graphics and beyond. While approaches based on machine learning dominate modern 3D shape matching, almost all existing (learning-based) methods re
Externí odkaz:
http://arxiv.org/abs/2411.03511
Autor:
Kaur, Ramneet, Samplawski, Colin, Cobb, Adam D., Roy, Anirban, Matejek, Brian, Acharya, Manoj, Elenius, Daniel, Berenbeim, Alexander M., Pavlik, John A., Bastian, Nathaniel D., Jha, Susmit
In this paper, we present a dynamic semantic clustering approach inspired by the Chinese Restaurant Process, aimed at addressing uncertainty in the inference of Large Language Models (LLMs). We quantify uncertainty of an LLM on a given query by calcu
Externí odkaz:
http://arxiv.org/abs/2411.02381
Autor:
Brojatsch, Andrej, Harrach, Bastian
We introduce a computer-assisted proof for uniqueness and global reconstruction for the inverse Robin transmission problem, where the corrosion function on the boundary of an interior object is to be determined from current-voltage measurements on th
Externí odkaz:
http://arxiv.org/abs/2411.00482
Recent advances in LLM have been instrumental in autonomous robot control and human-robot interaction by leveraging their vast general knowledge and capabilities to understand and reason across a wide range of tasks and scenarios. Previous works have
Externí odkaz:
http://arxiv.org/abs/2410.22997
Autor:
Aliberti, Riccardo, Beltrame, Paolo, Budassi, Ettore, Calame, Carlo M. Carloni, Colangelo, Gilberto, Cotrozzi, Lorenzo, Denig, Achim, Driutti, Anna, Engel, Tim, Flower, Lois, Gurgone, Andrea, Hoferichter, Martin, Ignatov, Fedor, Kollatzsch, Sophie, Kubis, Bastian, Kupść, Andrzej, Lange, Fabian, Lusiani, Alberto, Müller, Stefan E., Paltrinieri, Jérémy, Rosàs, Pau Petit, Piccinini, Fulvio, Price, Alan, Punzi, Lorenzo, Rocco, Marco, Shekhovtsova, Olga, Siódmok, Andrzej, Signer, Adrian, Stagnitto, Giovanni, Stoffer, Peter, Teubner, Thomas, Bobadilla, William J. Torres, Ucci, Francesco P., Ulrich, Yannick, Venanzoni, Graziano
We present the results of Phase I of an ongoing review of Monte Carlo tools relevant for low-energy hadronic cross sections. This includes a detailed comparison of Monte Carlo codes for electron-positron scattering into a muon pair, pion pair, and el
Externí odkaz:
http://arxiv.org/abs/2410.22882
Pion-kaon ($\pi K$) final states, often appearing in heavy-particle decays at the precision frontier, are important for Standard-Model tests, to describe crossed channels with exotic states, and for spectroscopy of excited kaon resonances. We constru
Externí odkaz:
http://arxiv.org/abs/2410.21883
Autor:
Rieck, Bastian
This overview article makes the case for how topological concepts can enrich research in machine learning. Using the Euler Characteristic Transform (ECT), a geometrical-topological invariant, as a running example, I present different use cases that r
Externí odkaz:
http://arxiv.org/abs/2410.17760
Autor:
Chen, Jingdi, Zhou, Hanhan, Mei, Yongsheng, Joe-Wong, Carlee, Adam, Gina, Bastian, Nathaniel D., Lan, Tian
Deep Reinforcement Learning (DRL) algorithms have achieved great success in solving many challenging tasks while their black-box nature hinders interpretability and real-world applicability, making it difficult for human experts to interpret and unde
Externí odkaz:
http://arxiv.org/abs/2410.16517