Encoder-Decoder Manifold Alignment for Idempotent Generation
The study addresses instability in generative models by proposing a new training framework that enforces latent-space consistency between an encoder and decoder. This alignment closes a geometric gap where different manifolds cause repeated model application to drift. By aligning these geometries, the method achieves significantly lower idempotency error, leading to more stable projections and higher quality in image generation and editing tasks.