System identification stops modeling one plant at a time: matching only the input signal cuts a stirred-tank reactor's prediction error from 1.249 to 0.242
A meta model pre-trained offline on synthetic Wiener-Hammerstein systems predicts a new system's output zero-shot from a short input-output context, matches state-of-the-art accuracy on nonlinear identification benchmarks, and cuts an out-of-distribution continuous stirred tank reactor's prediction error from 1.249 to 0.242 by adapting only the input side.