SOURCE-LINKED INTELLIGENCE

Bridging Reconstruction and Generation: A Latent Distribution Perspective on Evaluation and Improvement

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

In latent generative models, reconstruction quality is often assumed to correlate with generative performance. However, reconstruction FID (rFID) can exhibit weak or even negative correlation with generation FID (gFID). We attribute this discrepancy to a latent distribution mismatch: reconstruction evaluates the decoder on encoder-induced latents, whereas generation uses the same decoder on latents produced by the generative model. To characterize this shift, we introduce generation-aware reconstruction (GAR), which constructs a continuous trajectory from standard reconstruction toward generat

Read original source ↗ Open in workspace

recordType

paper

region

Global