arXiv Machine Learning
Jul 7
MANCE: Manifold Aware Concept Erasure
arXiv:2607. 03973v1 Announce Type: new Abstract: Concept erasure aims to remove a target concept from a representation while preserving the other information encoded in it.
MANCE: Manifold Aware Concept Erasure
Concept erasure aims to remove a target concept from a representation while preserving the other information encoded in it. This is difficult because representations encode many concepts that are often correlated with the erasure target, so removing the target risks damaging them.
Related stories
arXiv Computation and Language
Sep 1
Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings
arXiv:2606.03695v2 Announce Type: replace Abstract: As language models are increasingly deployed in real-world applications, the ability to erase specific knowledge from them becomes critical for saf...
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 Computer Vision
Sep 14
GRACE: Adaptive Concept Erasure with Geometry-Guided Retention in Diffusion Models
GRACE is a new framework for concept erasure in text-to-image diffusion models that uses a semantically weighted sensitive subspace to guide localized interventions and lightweight subspace-constrained adapters to avoid global semantic disruption. It replaces manual counterfactual prompts with an automatically decoupled safe-anchor mechanism and controls intervention strength through an energy-driven dynamic gating system. Experiments show GRACE improves NSFW reduction by 17.86% over five state-of-the-art methods while also reducing target CLIP Score and FID, indicating stronger concept suppression with better preservation of generative quality.
arXiv Machine Learning
Jul 10
AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate
arXiv:2607. 08337v1 Announce Type: new Abstract: Diffusion unlearning is essential for mitigating the generation of harmful or copyrighted content in text-to-image models.
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 9
AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate
Diffusion unlearning is essential for mitigating the generation of harmful or copyrighted content in text-to-image models. Current diffusion unlearning techniques determine the model update direction by either using alternatives of the target concept as an anchor or using empty prompts.
arXiv AI
3d ago
Learning What to Forget: Distributional Unlearning for LLM Representation Spaces
arXiv:2609.38929v1 Announce Type: new Abstract: Machine learning systems increasingly face the need to remove the influence of entire data domains, such as toxic language, harmful behavior, or topica...
arXiv Computer Vision
6d ago
Open Vocabulary Domain Unlearning
arXiv:2609.31356v1 Announce Type: new Abstract: Vision-Language Models (VLMs) exhibit remarkable zero-shot generalization, yet they often encode unwanted or hazardous stylistic domains such as ideali...
arXiv Computer Vision
2d ago
RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models
arXiv:2610.01969v1 Announce Type: new Abstract: Concept erasure aims to remove a target concept, such as a copyrighted style, a recognizable character, or unsafe content, from a pretrained text-to-im...
arXiv AI
Sep 4
EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders
EraseSAE is a framework for surgical concept erasure in text-to-video diffusion models. It uses a Partitioned Convolutional Sparse Autoencoder to decompose activations into interpretable sparse features, a contrastive attribution mechanism to isolate concept-specific kernels, and timestep‑resolved masks to confine erasure to active regions. Experiments show precise removal with minimal quality loss, outperforming existing methods.
arXiv Machine Learning
Jun 5
Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance
arXiv:2606. 06320v1 Announce Type: new Abstract: Machine unlearning aims to remove targeted knowledge from a trained model while preserving its general capabilities.