ConceptAgent is a black-box multi-agent system that awakens erased concepts in diffusion models by initializing denoising trajectories from surrogate-guided noisy states.
Erasing concepts, steering generations: A comprehensive survey of concept suppression
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A training-free double-projection linear transformation erases target concepts from generative models by computing a proxy projection then applying a constrained update in the left null space of known directions.
SafeRedir achieves robust unlearning of unsafe concepts in image generation models by adaptively redirecting prompt embeddings toward safe semantic regions at inference time via a multi-modal classifier and token delta generator.
citing papers explorer
-
Whispers in the Noise: Surrogate-Guided Concept Awakening via a Multi-Agent Framework
ConceptAgent is a black-box multi-agent system that awakens erased concepts in diffusion models by initializing denoising trajectories from surrogate-guided noisy states.
-
Closed-Form Concept Erasure via Double Projections
A training-free double-projection linear transformation erases target concepts from generative models by computing a proxy projection then applying a constrained update in the left null space of known directions.
-
SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models
SafeRedir achieves robust unlearning of unsafe concepts in image generation models by adaptively redirecting prompt embeddings toward safe semantic regions at inference time via a multi-modal classifier and token delta generator.