Search Results for author:
Found 5 papers, 1 papers with code
Chronos: Learning the Language of Time Series
We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models.
Adaptive Sampling for Probabilistic Forecasting under Distribution Shift
We present an adaptive sampling strategy that selects the part of the time series history that is relevant for forecasting.
Resilient Neural Forecasting Systems
Common data challenges are data distribution shifts, missing values and anomalies.
Can Pre-training help VQA with Lexical Variations?
However, these models fail to perform well on rephrasings of a question, which raises some important questions like Are these models robust towards linguistic variations?
Bootstrapping NLU Models with Multi-task Learning
A common approach that is adapted in digital assistants when responding to a user query is to process the input in a pipeline manner where the first task is to predict the domain, followed by the inference of intent and slots.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
