ConceptAgent is a black-box multi-agent system that awakens erased concepts in diffusion models by initializing denoising trajectories from surrogate-guided noisy states.
Erased or dormant? rethinking concept erasure through reversibility.arXiv preprint arXiv:2505.16174
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative 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.
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.