Skip to content

Author

Yunqiao Yang

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 Jul 2026

When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities

A Structured Sparse AutoEncoder that enforces concept consistency from both semantic and spatial perspectives in the visual modality is proposed and introduced, and enhances neuronal monosemanticity by this visual structural prior.

Weiduo Liao, Yunqiao Yang, Ying Wei · 0 citations