AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

GRACE: Adaptive Concept Erasure with Geometry-Guided Retention in Diffusion Models

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Text-to-image (T2I) diffusion models inevitably internalize sensitive or non-compliant concepts from large-scale pretraining data, necessitating post-hoc concept erasure. However, existing erasure methods often lack explicit constraints on parameter updates, leading to over-intervention and unintended semantic drift. In addition, many methods rely on manually crafted counterfactual supervision, such as surrogate prompts, which incurs substantial data construction costs that limit scalability to new concepts. To address these limitations, we propose GRACE, a structured concept erasure framework

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-20T18:22:04.777Z. This is not the publication date.