Saining Xie· @sainingxie · X·· 2026-05-22AI 评分45
AI 导读
来看看 Jas 主导的 RAEv2。通过大量实验，我们发现了一些非常有趣的行为，说明为什么强大的表征编码器对像素解码器至关重要。 剧透：关键不在于爬 FID 的坡；像 ep@fid-k/fdr^k 这样的新指标表明，还有更多值得探索的空间！
正文
check out RAEv2 led by Jas. through extensive exps, we found some really intriguing behaviors showing why strong representation encoders are key for pixel decoders.
spoiler: it’s not about hillclimbing fid; new metrics like ep@fid-k/fdr^k show there’s a lot more left to explore!
In Oct last year, Representation Autoencoders provided an elegant solution to unified tokenization for understanding and generation. Today we make them a bit more simple. a bit more general. Result: >10x faster convergence, better reconstruction, better generation. And yes we test them on T2I and world models :) Introducing RAEv2在 X 查看被引用的帖子
来源：Saining Xie · x.com