Publications

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
In-context learning, the ability of large language models to perform tasks using only examples provided in the prompt, has recently …
Andreas Auer, Patrick Podest, Daniel Klotz, Sebastian Böck, Günter Klambauer, Sepp Hochreiter
Paper Code Model (HuggingFace)
Zero-Shot Time Series Forecasting with Covariates via In-Context Learning
Pretrained time series models, capable of zero-shot forecasting, have demonstrated significant potential in enhancing both the …
Andreas Auer, Raghul Parthipan, Pedro Mercado, Abdul Fatir Ansari, Lorenzo Stella, Bernie Wang, Michael Bohlke-Schneider, Syama Sundar Rangapuram
Paper
xLSTM: Extended Long Short-Term Memory
In the 1990s, the constant error carousel and gating were introduced as the central ideas of the Long Short-Term Memory (LSTM). Since …
Maximilian Beck, Korbinian Pöppel, Markus Spanring, Andreas Auer, Oleksandra Prudnikova, Michael Kopp, Günter Klambauer, Johannes Brandstetter, Sepp Hochreiter
Paper Code
A data-centric perspective on the information needed for hydrological uncertainty predictions
Uncertainty estimates are fundamental to assess the reliability of predictive models in hydrology. We use the framework of Conformal …
Andreas Auer, Martin Gauch, Frederik Kratzert, Grey Nearing, Sepp Hochreiter, Daniel Klotz
Paper
xLSTM: Extended Long Short-Term Memory
In the 1990s, the constant error carousel and gating were introduced as the central ideas of the Long Short-Term Memory (LSTM). Since …
Maximilian Beck, Korbinian Pöppel, Markus Spanring, Andreas Auer, Oleksandra Prudnikova, Michael Kopp, Günter Klambauer, Johannes Brandstetter, Sepp Hochreiter
Paper Code
Conformal Prediction for Time Series with Modern Hopfield Networks
To quantify uncertainty, conformal prediction methods are gaining continuously more interest and have already been successfully applied …
Andreas Auer, Martin Gauch, Daniel Klotz, Sepp Hochreiter
Paper Blog Code
VT-KGNN: A Valid Time Knowledge Graph Neural Network
Temporal Knowledge Graphs, a form of a graph-structured knowledge bases, gained increased interest in both academia and industry in the …
Andreas Auer
Download Award