arXiv:2606. 24192v1 Announce Type: cross Abstract: Unlearning has emerged as a key technique to mitigate harmful content generation in diffusion models.
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.
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:2512. 02657v2 Announce Type: replace-cross Abstract: Real-world deployment of text-to-image diffusion models requires continual concept removal as new privacy, copyright, or safety obligations arise over time.
arXiv:2604. 05634v2 Announce Type: replace Abstract: Machine unlearning (MU) has become a critical technique for GenAI models' safe and compliant operation.
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:2504. 21072v2 Announce Type: replace-cross Abstract: The expansion of text-to-image diffusion models has raised concerns about harmful outputs, from fabricated depictions of public figures to sexually explicit imagery.
arXiv:2606. 31699v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated features can serve as controllable intervention points.
arXiv:2606. 07688v1 Announce Type: cross Abstract: Generative recommendation formulates next-item prediction as autoregressive generation over semantic ID (SID) sequences derived from users' historical interactions, making modern recommender systems structurally similar to large language models (LLMs).
arXiv:2601. 22651v2 Announce Type: replace-cross Abstract: Training-data attribution for vision generative models aims to identify which training data influenced a given output.
arXiv:2607. 10580v1 Announce Type: cross Abstract: AI models are increasingly trained on personal images scraped from social media and public platforms, often without consent, leading to serious privacy violations, such as unauthorized facial recognition and targeted advertising.
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:2511. 20196v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) can inadvertently memorize privacy-sensitive information during training.