arXiv Machine Learning
Semantic Latent Alignment for Flow Matching with Invertible Bi-Lipschitz Adapters
Read the original on arXiv Machine Learning →The paper proposes a method for adapting pretrained latent spaces without retraining the encoder or decoder by inserting an invertible bi‑Lipschitz adapter that aligns the latent coordinates to a semantic teacher. This offline alignment preserves the compression and reconstruction properties of the original autoencoder while improving semantic organization. Experiments on two medical imaging datasets show that constrained adaptation enhances feature metrics, seed stability, and counterfactual edit strength, and remains competitive on downstream classification tasks.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.