Zobrazeno 1 - 10
of 17 896
pro vyhledávání: '"Benedict, Á"'
Despite the successful application of Temporal Graph Networks (TGNs) for tasks such as dynamic node classification and link prediction, they still perform poorly on the task of dynamic node affinity prediction -- where the goal is to predict 'how muc
Externí odkaz:
http://arxiv.org/abs/2411.03596
Large Language Models (LLMs) are known to hallucinate, whereby they generate plausible but inaccurate text. This phenomenon poses significant risks in critical applications, such as medicine or law, necessitating robust hallucination mitigation strat
Externí odkaz:
http://arxiv.org/abs/2410.17234
Future advanced driver assistance systems and autonomous vehicles rely on accurate localization, which can be divided into three classes: a) viewpoint localization about local references (e.g., via vision-based localization), b) absolute localization
Externí odkaz:
http://arxiv.org/abs/2410.14264
We propose a scalable kinetic Langevin dynamics algorithm for sampling parameter spaces of big data and AI applications. Our scheme combines a symmetric forward/backward sweep over minibatches with a symmetric discretization of Langevin dynamics. For
Externí odkaz:
http://arxiv.org/abs/2410.19780
This paper presents a divergence cleaning formulation for the velocity in the weakly compressible smoothed particle hydrodynamics (SPH) scheme. The proposed hyperbolic/parabolic divergence cleaning, ensures that the velocity divergence, $div(\mathbf{
Externí odkaz:
http://arxiv.org/abs/2410.06038
Autor:
Ebel, Henrik, van Delden, Jan, Lüddecke, Timo, Borse, Aditya, Gulakala, Rutwik, Stoffel, Marcus, Yadav, Manish, Stender, Merten, Schindler, Leon, de Payrebrune, Kristin Miriam, Raff, Maximilian, Remy, C. David, Röder, Benedict, Eberhard, Peter
Data-based methods have gained increasing importance in engineering, especially but not only driven by successes with deep artificial neural networks. Success stories are prevalent, e.g., in areas such as data-driven modeling, control and automation,
Externí odkaz:
http://arxiv.org/abs/2410.18358
Predictive Spliner: Data-Driven Overtaking in Autonomous Racing Using Opponent Trajectory Prediction
Autor:
Baumann, Nicolas, Ghignone, Edoardo, Hu, Cheng, Hildisch, Benedict, Hämmerle, Tino, Bettoni, Alessandro, Carron, Andrea, Xie, Lei, Magno, Michele
Head-to-head racing against opponents is a challenging and emerging topic in the domain of autonomous racing. We propose Predictive Spliner, a data-driven overtaking planner that learns the behavior of opponents through Gaussian Process (GP) regressi
Externí odkaz:
http://arxiv.org/abs/2410.04868
This paper addresses the problem of human-based driver support. Nowadays, driver support systems help users to operate safely in many driving situations. Nevertheless, these systems do not fully use the rich information that is available from sensing
Externí odkaz:
http://arxiv.org/abs/2410.03774
Let $X = G/H$ be an affine homogeneous spherical variety with abelian regular centralizer and no type N roots. In this paper, we formulate a relative geometric Langlands conjecture in the Dolbeault setting for $M = T^*X$. More concretely, we conjectu
Externí odkaz:
http://arxiv.org/abs/2409.15691
Autor:
Haufe, Stefan, Wilming, Rick, Clark, Benedict, Zhumagambetov, Rustam, Panknin, Danny, Boubekki, Ahcène
The use of machine learning (ML) in critical domains such as medicine poses risks and requires regulation. One requirement is that decisions of ML systems in high-risk applications should be human-understandable. The field of "explainable artificial
Externí odkaz:
http://arxiv.org/abs/2409.14590