Hugging Face Trending Papers
Push-Pull Attentional Anchoring for Diffusion Concept Erasure
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computer Vision
Oct 21
Push-Pull Attentional Anchoring for Diffusion Concept Erasure
arXiv:2610.27719v1 Announce Type: new Abstract: Rapid advances in diffusion models have raised concerns about privacy, harmful content, and copyright violations. Concept erasure methods aim to addres...
arXiv AI
Jul 8
TILDE: TILt-based Distributional Erasure for Concept Unlearning
arXiv:2607. 06432v1 Announce Type: cross Abstract: Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and safety regulations, deployed systems must be able to suppress unwanted concepts after training.
arXiv Machine Learning
Jul 28
To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion
arXiv:2607. 23492v1 Announce Type: cross Abstract: Concept erasure techniques (CETs) edit text-to-image diffusion models to erase undesired targets such as NSFW content or copyrighted styles, while preserving model utility on benign concepts.
Hugging Face Trending Papers
Jul 6
Erasing Without Collateral Damage: Precise Concept Removal in Diffusion Models
Training-free concept erasure is an attractive mechanism for controlling text-to-image diffusion models, but precise erasure often comes at the cost of damaging semantically related non-target concepts. Existing value-space methods remove the component of each cross-attention value along the target concept direction, implicitly treating target identity and shared visual structure as the same signal.
arXiv AI
Oct 15
Compositional Concepts Erasing: Disentangling Object-Style via Domain Manifold Unlearning
arXiv:2610.14514v1 Announce Type: cross Abstract: Diffusion models pose significant risks regarding the generation of illicit content and copyright violations. This has catalyzed the development of m...
arXiv Computer Vision
Oct 2
RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models
RASteer is a training‑free method for concept erasure in text‑to‑image diffusion models that retains other concepts. It constructs a retain subspace from concepts to preserve, then removes components aligned with this subspace from the erasure direction using Retain‑Orthogonal Steering (ROS). Overlap‑Adaptive Calibration (OAC) further adjusts the removal of shared components at each layer and denoising step, balancing target erasure with concept preservation. Experiments show RASteer matches or outperforms existing activation steering and weight editing baselines on unsafe‑content, instance, and artistic‑style erasure tasks across multiple backbones and benchmarks.