Generalized Energy Band Alignment Model for van der Waals Heterostructures with a Charge Spillage Dipole

∼ 0.9 across type-I, -II, and -III stacks. Machine learning feature analysis confirms that these two descriptors dominate the underlying physics, indicating that the model is near-minimal and broadly transferable. The gLR framework therefore provides both mechanistic insight and a fast and accurate surrogate for high-throughput screening of the vast vdW heterostructure design space.