BACKGROUND
Flow diverters have expanded endovascular treatment options, yet large real-world data about their comparative periprocedural safety in the treatment of unruptured intracranial aneurysms are limited. This study aimed to compare the short-term safety of flow diverters with alternative endovascular techniques....
P. Heesen, Olga Ciobanu-Caraus, S. Feuerriegel et al.· Journal of NeuroIntervention...· 0 citations
Evaluating candidate architectures in neural architecture search (NAS) faces an inherent trade-off: on the one hand, reliable performance labels are limited because training and evaluating architectures is costly; on the other hand, zero-cost proxies (ZCPs) are cheap to compute at large scale but can be noisy. Yet, how...
Pascal Janetzky, Yu-Xin Wang, Michael Klar et al.· 0 citations
NashEval is proposed, a general framework for robust contextual equilibrium learning that frame evaluation as a contextual game between two players, each selecting a distribution over agents as the strategy to receive greater collective preference than the other.
Hao-Rui Ma, Ze-Hua Zang, Jiang-Meng Li et al.· 0 citations
A central goal when designing treatment policies is often to"do no harm", that is, to avoid interventions that improve average outcomes while worsening outcomes for some individuals. A widely used notion for harm is the fraction of negatively affected (FNA), defined as the probability that an intervention decreases an...
Rui-Zi Yan, Dennis Frauen, Maresa Schröder et al.· 0 citations
How often models reward-hack without instructions to do so, how effective and detectable their methods are when hacking is allowed, and how they adapt when an LLM review panel returns its decision and reasons are studied.
Yue Huang, Zhangchen Xu, Yu-Chen Ma et al.· 1 citation
Large language models (LLMs) are rapidly diffusing into multilingual workplaces, where managers and employees rely on them to translate everyday communication. While LLMs can now generate translations with high lexical accuracy, it remains unclear whether they can produce translations that are culturally appropriate...
H. Tenzer, O. Abidi, S. Feuerriegel· Management International Rev...· 0 citations
Evaluating the quality of explanations produced by explainable AI (XAI) methods remains challenging because existing approaches often rely on subjective human judgment, limiting reproducibility, scalability, and comparability between studies. We examine whether LLMs can serve as a reproducible and scalable mechanism to...
Yanfei Hu Fleischhauer, Alona Zharova, Nadja Klein et al.· 0 citations
Multilingual LLM outputs can vary across sociocultural contexts. However, evidence of cultural grounding can be misleading: identity labels may be inferred from explicit or indirect textual cues, while names and wording can reveal the source language. Treating all these signals as evidence of cultural grounding may obs...
Yuanjun Feng, Tanzhou Liu, S. Feuerriegel et al.· 0 citations
This framework is the first to address catastrophic forgetting by leveraging models in CL as their own memory buffers by exploiting an implicit bias of gradient-based neural networks due to which these converge to margin maximization points.
Pascal Janetzky, T. Schlagenhauf, Michael Klar et al.· Proceedings of the 32nd ACM...· 0 citations
Continual learning (CL) aims to incrementally update machine learning models from a stream of data without forgetting previously acquired knowledge. CL is highly relevant in many real-world applications such as manufacturing, where storing historical data for retraining is often infeasible due to volume, governance, or...
Pascal Janetzky, T. Schlagenhauf, Michael Klar et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
