Tag
GenFirst proposes a generation-before-reconstruction strategy to enable stable end-to-end training of latent generative models, avoiding latent collapse and achieving state-of-the-art results in image synthesis and multimodal generation.
Proposes Constraint-Aware Flow Matching, a novel end-to-end framework that aligns the model's learning dynamics with constrained sampling procedure, mitigating distributional shift from projection corrections for high-quality constrained generation.