Parameter-matched LoRA placement reveals performance–efficiency trade-offs in cross-dataset deepfake detection
Source Nature 物理科学1d ago
Summary
We index headlines and summaries only. Full content and copyright remain with the original publisher — follow the source link to read it.
Open original- Desk
- Science
- Region
- Global
- Language
- English
- Item ID
- science-0275069a
Comments 0 comments
No comments yet. Be the first.