FuseReg: Layer-Fusion Regularization Cuts gFID up to 29% in Representation Autoencoders

USC-PSI-Lab · hf · 2026-09-28

USC PSI Lab proposes FuseReg, tackling the layer-selection trade-off in representation autoencoders (RAEs) for image generation.

Takeaway: training downstream models for layer-fusion robustness narrows the reconstruction-generation gap without touching the pretrained encoder.

Original post →

More from Research

Research channel →