RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models

arXiv:2610.01969 · cs.CV · Submitted 2026-10-01 · Read on arXiv

cs.CV

Submitted: 2026-10-01

Updated: 2026-10-01

Project page: https://rasteer.cvmlgroup.web.illinois.edu/1

Terminology

• Steering — 47× in this paper · explained in 2 episodes
• Accuracy — 26× in this paper · explained in 1 episode
• Diffusion Model — 24× in this paper · explained in 8 episodes
• Diffusion Models — 20× in this paper · explained in 6 episodes
• Activation Steering — 11× in this paper · explained in 4 episodes
• Alignment — 9× in this paper · explained in 1 episode
• Benchmark — 7× in this paper · explained in 2 episodes
• Calibration — 7× in this paper · explained in 7 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Overlap-Adaptive Calibration — 4× in this paper
• Retain-Orthogonal Steering — 4× in this paper
• Adaptation — 3× in this paper · explained in 1 episode
• Transformer — 3× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 2× in this paper
• Embeddings — 2× in this paper · explained in 2 episodes
• Inference-Time Steering — 2× in this paper · explained in 2 episodes
• Latent Diffusion Model — 2× in this paper · explained in 2 episodes
• Latent Diffusion Models — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment Scores — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• CVF International Conference on Computer Vision — 1× in this paper
• Continual Learning — 1× in this paper · explained in 2 episodes
• Diffusion Process — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Machine Unlearning — 1× in this paper · explained in 2 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Regret — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• LoRA: Low-Rank Adaptation of Large Language Models
• On Effects of Steering Latent Representation for Large Language Model Unlearning
• Mass-Editing Memory in a Transformer
• Red-Teaming the Stable Diffusion Safety Filter
• Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression
• SteerDiff: Steering towards Safe Text-to-Image Diffusion Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models