Author

Chun-Wei Wang

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

SPAE: Spectrally Guided Autoencoder for Pretrained Visual Latents

SPAE employs a compact bottleneck to distill stable semantic information while suppressing high-frequency components, thereby improving the alignment between DiT-generated latents and encoder latents, and achieves a favorable balance among visual understanding, generation quality, and reconstruction fidelity.

Yibin Huang, Ji-Xiang Hong, Zongzhao Li et al. · 0 citations