<!channel> New release of neuralforecast (v.3.0.1): Features • FEAT: Select basis functions in NBEATS • FEAT: Add flash-attention • FEAT: HuberIQLoss Bug Fixes • FIX: Fix iPython version • FIX: Recurrent predictions • FIX: Fix poor performance with the NegativeBinomial DistributionLoss • FIX: Add exclude_insample_y param to TimeXer for model loading • FIX: Set 2.0.0<=pytorch<=2.6.0 to avoid conflicts with networkx with Python 3.9 • FIX: Create windows once • FIX: Add h_train to RNNs & fix issue with input_size • FIX: Allow static vars only with NBEATSx and exogenous block Thank you to all of the contributors from the community! Make sure to install the latest version to access the latest features and fixes, and keep using neuralforecast and asking your questions here!

Thanks for the update! What do you mean with the Fix: recurrent predictions? Meaning outputting the same predictions over the whole horizon?

See the PR here detailing the fix: https://github.com/Nixtla/neuralforecast/pull/1285

thanks got it