A method using attention head vectors detects and suppresses risky content generation in Diffusion Transformers at inference time.
Trasce: Trajectory steering for concept erasure.arXiv preprint arXiv:2412.07658, 2024
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
CoreUnlearn uses a Component Extraction Module and Swap Disentangling Strategy to remove only erasure-critical components from concept embeddings in diffusion models.
citing papers explorer
-
What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers
A method using attention head vectors detects and suppresses risky content generation in Diffusion Transformers at inference time.
-
CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models
CoreUnlearn uses a Component Extraction Module and Swap Disentangling Strategy to remove only erasure-critical components from concept embeddings in diffusion models.
- GEM: Geometric Erasure by Contrastive Velocity Matching in Rectified Flows