Related papers: Sparse Autoencoder as a Zero-Shot Classifier for C…

Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transformer image encoders and to small-scale diffusion models.…

Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, and privacy violations. In scalable applications,…

Robust concept removal for text-to-image (T2I) and text-to-video (T2V) models is essential for their safe deployment. Existing methods, however, suffer from costly retraining, inference overhead, or vulnerability to adversarial attacks.…

Large-scale text-to-image (T2I) diffusion models have revolutionized image generation, enabling the synthesis of highly detailed visuals from textual descriptions. However, these models may inadvertently generate inappropriate content, such…

Diffusion Transformers (DiTs) are a powerful yet underexplored class of generative models compared to U-Net-based diffusion architectures. We propose TIDE-Temporal-aware sparse autoencoders for Interpretable Diffusion transformErs-a…

Large-scale text-to-image (T2I) diffusion models deliver remarkable visual fidelity but pose safety risks due to their capacity to reproduce undesirable content, such as copyrighted ones. Concept erasure has emerged as a mitigation…

Large-scale text-to-image diffusion models have become the backbone of modern image editing, yet text prompts alone do not offer adequate control over the editing process. Two properties are especially desirable: disentanglement, where…

Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. These concepts, termed as the "implicit concepts", could be unintentionally learned during training and then be…

Large-scale text-to-image (T2I) diffusion models have achieved remarkable generative performance about various concepts. With the limitation of privacy and safety in practice, the generative capability concerning NSFW (Not Safe For Work)…

Text-to-Image (T2I) models have demonstrated impressive capabilities in generating high-quality and diverse visual content from natural language prompts. However, uncontrolled reproduction of sensitive, copyrighted, or harmful imagery poses…

Concept erasure in Text-To-Image (T2I) diffusion models is vital for safe content generation, but existing inference-time methods face significant limitations. Feature-correction approaches often cause uncontrolled over-correction, while…

Text-to-Image (T2I) models have made remarkable progress in generating high-quality, diverse visual content from natural language prompts. However, their ability to reproduce copyrighted styles, sensitive imagery, and harmful content raises…

Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive. We introduce SAEmnesia, a supervised sparse…

Text-to-image (T2I) diffusion models often exhibit gender bias, particularly by generating stereotypical associations between professions and gendered subjects. This paper presents SAE Debias, a lightweight and model-agnostic framework for…

Recent advances in text-to-image diffusion models have demonstrated remarkable generation capabilities, yet they raise significant concerns regarding safety, copyright, and ethical implications. Existing concept erasure methods address…

Despite the remarkable progress in text-to-image generative models, they are prone to adversarial attacks and inadvertently generate unsafe, unethical content. Existing approaches often rely on fine-tuning models to remove specific…

Generating images from text has become easier because of the scaling of diffusion models and advancements in the field of vision and language. These models are trained using vast amounts of data from the Internet. Hence, they often contain…

Text-to-image diffusion models have demonstrated the underlying risk of generating various unwanted content, such as sexual elements. To address this issue, the task of concept erasure has been introduced, aiming to erase any undesired…

Diffusion models, while powerful, can inadvertently generate harmful or undesirable content, raising significant ethical and safety concerns. Recent machine unlearning approaches offer potential solutions but often lack transparency, making…

Concept erasure in text-to-image diffusion models is crucial for mitigating harmful content, yet existing methods often compromise generative quality. We introduce Semantic Surgery, a novel training-free, zero-shot framework for concept…