Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation 事件

Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation arXiv:2606.00514v1 Announce Type: cross Abstract: Generative modeling and self-supervised representation learning (SSL) optimize structurally different objectives: generative training rewards distributional fidelity, while SSL rewards semantic coherence. Yet recent work repeatedly finds that SSL features improve generative training, though the mechanism of this synergy remains unclear. Here, we