Metraipolis › archive › dc_c01fd9318014
FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders — arXiv:2609.31620
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31620
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T03:12:51.720Z
- SHA-256 of the archived text
9e36c2fd4941168f0c70de44fcd7422a7daf7f44aeae5eea817483d901f37eda- Stable URL of this page
https://metraipolis.com/documento/dc_c01fd9318014
How to cite
FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders — arXiv:2609.31620 — arXiv (en), https://arxiv.org/abs/2609.31620 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c01fd9318014 (Metraipolis archive dc_c01fd9318014, sha256 9e36c2fd4941168f0c70de44fcd7422a7daf7f44aeae5eea817483d901f37eda)
BibTeX
@misc{dcc01fd9318014,
title = {FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders — arXiv:2609.31620},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31620},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c01fd9318014; sha256 9e36c2fd4941168f0c70de44fcd7422a7daf7f44aeae5eea817483d901f37eda},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31620. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Representation autoencoders (RAEs) reuse features from a pretrained visual encoder as reconstruction and diffusion latents, integrating strong visual representations into image generation. However, RAEs still need to decide which encoder layers form the shared latent space for the generator and pixel decoder. This choice involves a trade-off: shallower layers tend to preserve fine pixel details better, while deeper layers tend to yield better generation metrics. A fixed heuristic layer fusion therefore couples two stages that benefit from different information. We introduce FuseReg, which replaces heuristic feature selection with training over random subsets of encoder layers. We theoretically analyze the underlying mechanism: subset sampling preserves the full-layer latent mean in expectation while explicitly penalizing sensitivity to cross-layer disagreement. On ImageNet-256 with DINOv3-L, a single FuseReg decoder reconstructs from full, sparse, and single-layer fusions without retraining, achieving higher PSNR than decoders specialized to fixed fusions. This flexibility also benefits generation: decoder replacement alone reduces unguided gFID by 27% with an unchanged RAEv2 DiT-XL generator. Applying FuseReg to both stages also reduces unguided gFID by 29% on DiT-Base. The reconstruction and generation benefits also extend to other encoder families. FuseReg narrows the reconstruction-generation gap without additional training cost or architectural changes. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.31620 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T02:50:19.130Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).