站内快照 · 国内可打开。外网原文可能无法访问。

• 论文公开站arXiv2026年10月2日 22:12

  Embedding Prediction Helps Image Generation

  In diffusion transformers, a class label or a text prompt is embedded once, and the same condition is reused at every denoising step. We ask whether predicted embeddings can serve as this condition instead. Next-Embedding Predictive Autoregression (NEPA) trains a Transformer to p

  原文链接