autoencoders

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencodersarxiv.org

FuseReg replaces the fixed heuristic of selecting encoder layers for representation autoencoders with a regularization that trains on random subsets of layers, making the downstream decoder robust to any fusion. This yields higher reconstruction quality (PSNR) and lowers unguided generation FID by up to 29% on ImageNet‑256, all without changing the pretrained visual encoder.