FADE: Frame-Aware Diffusion-Transformer-based Multi-Concept Erasure for Video Unlearning

arXiv:2610.03980 · cs.CV · Submitted 2026-10-02 · Read on arXiv

cs.CV

Submitted: 2026-10-02

Updated: 2026-10-09

Comments: 29 pages. Code: https://github.com/INTOTHEMILD/FADE

Code: https://github.com/INTOTHEMILD/FADE

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Transformer — 1× in this paper · explained in 2 episodes

Sources

• The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• Unlearning Concepts from Text-to-Video Diffusion Models
• Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
• GPT-4 Technical Report
• Wan: Open and Advanced Large-Scale Video Generative Models
• HunyuanVideo 1.5 Technical Report
• Towards Accurate Generative Models of Video: A New Metric & Challenges
• ModelScope Text-to-Video Technical Report
• Ethical and social risks of harm from Language Models
• T2VUnlearning: A Concept Erasing Method for Text-to-Video Diffusion Models
• Open-Sora: Democratizing Efficient Video Production for All

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models