Hi, I need help with a functionality of past_covariates in MLForecast. In order to forecast an horizon of 24 steps, i need to provide at least 1 step of the future value of this past covariate in order to direct forecast the 24 steps. But, in NeuralForecast that is not necessary. Which value i must past as a future value of the past covariate so the functionality of MLForecast matches of the NeuralForecast? -- An example is NHITS with neuralforecast, where i need only to pass the past_covariates to the model (no future values), along with the horizon.

MLForecast doesn't work like that, it always needs the covariates corresponding to a test point. Using past covariates is something I'd generally avoid. Make your assumptions explicit by forecasting these variables and using them as future exogenous.