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

ArXiv CS.CV2026-06-02NEWSen作者: Hugues Van Assel, Edward De Brouwer, Saeed Saremi, Gabriele Scalia, Aviv Regev
查看原文 →
关系图谱

Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation · 相关技术

相关技术

self-supervised representation learningone-step generationdeep generative modelingFIDWasserstein distanceSinkhorn divergenceSSL