HyperErase: Scale-Calibrated Hypernetwork for Multi-Concept Erasure in Text-to-Image Models
cs.CV, cs.CR
Submitted: 2026-09-25
Updated: 2026-09-25
Terminology
Sources
- TRACE: Trajectory-Constrained Concept Erasure in Diffusion Models
- ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning
- Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Classifier-Free Diffusion Guidance
- Block-wise LoRA: Revisiting Fine-grained LoRA for Effective Personalization and Stylization in Text-to-Image Generation
- DyME: Dynamic Multi-Concept Erasure in Diffusion Models with Bi-Level Orthogonal LoRA Adaptation
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- Red-Teaming the Stable Diffusion Safety Filter
- FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models
- ActErase: A Training-Free Paradigm for Precise Concept Erasure via Activation Redirection
- FlowErase-OPD: Multi-Concept Erasure via Anchored On-Policy Distillation in Flow Matching Models
- Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?
- Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models
- Closing the Safety Gap: Surgical Concept Erasure in Visual Autoregressive Models
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