VisualErase: Dual-Branch Visual Trajectory Redirection for Robust Concept Erasure in Text-to-Image Diffusion Models

arXiv:2610.05000 · cs.CV · Submitted 2026-10-04 · Read on arXiv

cs.CV

Submitted: 2026-10-04

Updated: 2026-10-04

Comments: The project page is https://qianlong0502.github.io/VisualErase-Homepage

Code: https://github.com/Giphy/celeb-detection-oss

Project page: https://qianlong0502.github.io/VisualErase-Homepage

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

Terminology

• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes

Sources

• Classifier-Free Diffusion Guidance
• Decoupled Weight Decay Regularization
• GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
• Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature
• Visual Transformers: Token-based Image Representation and Processing for Computer Vision

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