SOURCE-LINKED INTELLIGENCE

GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Latent generative models typically follow a two-stage pipeline, training a variational autoencoder for reconstruction and then a generative model on the frozen latent space. Since reconstruction-optimized latents are not necessarily generation-friendly, jointly training both models is an appealing alternative. However, direct end-to-end training remains challenging, as it is prone to latent collapse and faces a generation-reconstruction conflict. We revisit this problem by analyzing how different objectives shape the latent space and identify two key insights. First, the entropy term in the Ku

Read original source ↗ Open in workspace

recordType

paper

region

Global