Related papers: Sparse Autoencoder as a Zero-Shot Classifier for C…
Text-to-image (T2I) diffusion models have achieved widespread success due to their ability to generate high-resolution, photorealistic images. These models are trained on large-scale datasets, like LAION-5B, often scraped from the internet.…
As text-to-image diffusion models grow increasingly prevalent, the ability to remove specific concepts-mostly explicit content and many copyrighted characters or styles-has become essential for safety and compliance. Existing unlearning…
Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack…
We propose DeCoDi, a debiasing procedure for text-to-image diffusion-based models that changes the inference procedure, does not significantly change image quality, has negligible compute overhead, and can be applied in any diffusion-based…
Recent advances in text-to-image (T2I) diffusion models have seen rapid and widespread adoption. However, their powerful generative capabilities raise concerns about potential misuse for synthesizing harmful, private, or copyrighted…
Modern Text-to-Image (T2I) Diffusion models have revolutionized image editing by enabling the generation of high-quality photorealistic images. While the de facto method for performing edits with T2I models is through text instructions,…
Diffusion models (DMs) have become the new trend of generative models and have demonstrated a powerful ability of conditional synthesis. Among those, text-to-image diffusion models pre-trained on large-scale image-text pairs are highly…
Sparse Autoencoders (SAEs) have been successfully used to probe Large Language Models (LLMs) and extract interpretable concepts from their internal representations. These concepts are linear combinations of neuron activations that…
Recent text-to-image models have achieved impressive results in generating high-quality images. However, when tasked with multi-concept generation creating images that contain multiple characters or objects, existing methods often suffer…
Text-to-image (T2I) models exhibit a significant yet under-explored "brand bias", a tendency to generate contents featuring dominant commercial brands from generic prompts, posing ethical and legal risks. We propose CIDER, a novel,…
Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, controllable concepts. On the one hand, these approaches…
Erasing specific concepts from text-to-image diffusion models is essential for avoiding the generation of copyrighted and explicit content. Closed-form concept erasure methods offer a fast alternative to backpropagation-based techniques,…
Existing unlearning algorithms in text-to-image generative models often fail to preserve the knowledge of semantically related concepts when removing specific target concepts: a challenge known as adjacency. To address this, we propose FADE…
In this paper we propose a new generative model of text, Step-unrolled Denoising Autoencoder (SUNDAE), that does not rely on autoregressive models. Similarly to denoising diffusion techniques, SUNDAE is repeatedly applied on a sequence of…
Diffusion models have demonstrated remarkable image generation capabilities, but also pose risks in privacy and fairness by memorizing sensitive concepts or perpetuating biases. We propose a novel \textbf{concept erasure} method for…
Due to the recent success of diffusion models, text-to-image generation is becoming increasingly popular and achieves a wide range of applications. Among them, text-to-image editing, or continuous text-to-image generation, attracts lots of…
Continual learning enables large language models to adapt to evolving tasks without retraining from scratch, yet catastrophic forgetting remains a central obstacle. Among continual learning methods, regularization-based approaches are…
Large-scale text-to-image models have demonstrated amazing ability to synthesize diverse and high-fidelity images. However, these models are often violated by several limitations. Firstly, they require the user to provide precise and…
Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be naturally understood as topic models. We propose a continuous…
Text-to-Image (T2I) has been prevalent in recent years, with most common condition tasks having been optimized nicely. Besides, counterfactual Text-to-Image is obstructing us from a more versatile AIGC experience. For those scenes that are…