Skip to content

Author

Wenyu Liang

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.

#artificial intelligence Preprint Aug 2026

Denoising-Aware Inversion: Revealing Privacy Risks in Noise-Protected Text Embeddings

DAEI is proposed, a denoising-aware embedding inversion pipeline that combines a residual denoising autoencoder with generative text inversion where the denoiser is trained in an unsupervised manner using Stein's unbiased risk estimate to enable denoising from noisy observations alone.

Yubo Wang, Shujie Cui, James Bailey et al. · 0 citations