For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases. As models get stronger, standard benchmarks for ...

Klima, Moleküle, Galaxien. Ein Institut. Viele Dimensionen. Alle zwei Jahre lädt das „Heidelberger Institut für Theoretische Studien“ (HITS) ...

Speech Large Language Models (SLLMs) have rapidly expanded, supporting a wide range of tasks. These models are typically evaluated using text prompts, which may not reflect real-world scenarios where ...

Time-series forecasting is crucial for decision making in many domains. The authors propose SHAPformer, a method for accurate and explainable time-series forecasting, delivering explanations in less t...

24. Gulaschprogrammiernacht Get different formats: curl https://cfp.gulas.ch/gpn24/schedule/\?format=table (default) curl https://cfp.gulas.ch/gpn24/schedule/\?format=list 2026-...

KI - Künstliche Intelligenz - Heating systems account for a significant share of residential energy consumption, and rising energy prices call for intelligent, cost-aware control strategies....

Diese Mastodon-Instanz dient als Informations- und Vernetzungsplattform für die Wissenschaftskommunikation von Mitarbeitenden, Einrichtungen und Projekten des KIT.