Author

You-Zhi Tu

h-index 8 View on Semantic Scholar

We have 2 of 27 papers

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 Sep 2026

Cross-modal Translation via Conditional Latent Denoising for Video Deepfake Detection

This work proposes a framework called Cross-modal Translation via Conditional Latent Denoising (CTCLD) for video deepfake detection that connects the distinct distributions of heterogeneous modalities in latent spaces, enabling smooth cross-domain information transfer to improve detection performance.

Xin-Zhe Li, You-Zhi Tu, Kong Aik Lee · 0 citations

Preprint Aug 2026

Decoupled Latent Flow Matching for Few-Step Joint Vocal-Accompaniment Separation

Experiments show that latent adversarial refinement can improve perceptual and separation metrics under a reduced sampling budget and apply latent adversarial post-training inspired by Flow2GAN for few-step generation.

Li-Shi Zuo, You-Zhi Tu, Lu Yi et al. · 0 citations