FlowErase-RL applies GRPO to reformulate concept erasure in flow matching models as reward optimization using a dynamic dual-path mechanism for target suppression and non-target preservation.
R.a.c.e.: Robust adversarial concept erasure for secure text-to-image diffusion model.ArXiv, abs/2405.16341
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Safety-aligned T2I diffusion models exhibit semantic collapse in text embeddings causing TIFA drops; SAGE regularization restores structured utility while retaining safety.
citing papers explorer
-
FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models
FlowErase-RL applies GRPO to reformulate concept erasure in flow matching models as reward optimization using a dynamic dual-path mechanism for target suppression and non-target preservation.
-
The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models
Safety-aligned T2I diffusion models exhibit semantic collapse in text embeddings causing TIFA drops; SAGE regularization restores structured utility while retaining safety.