相关论文: Finding DoRI: Discovery of Retained Images in Diff…

Diffusion models, known for their tremendous ability to generate high-quality samples, have recently raised concerns due to their data memorization behavior, which poses privacy risks. Recent methods for memory mitigation have primarily…

Personalized retrieval and segmentation aim to locate specific instances within a dataset based on an input image and a short description of the reference instance. While supervised methods are effective, they require extensive labeled data…

With the rapid advancements of large-scale text-to-image diffusion models, various practical applications have emerged, bringing significant convenience to society. However, model developers may misuse the unauthorized data to train…

Can we localize the weights and mechanisms used by a language model to memorize and recite entire paragraphs of its training data? In this paper, we show that while memorization is spread across multiple layers and model components,…

Diffusion-based algorithms have emerged as promising techniques for weight generation. However, existing solutions are limited by two challenges: generalizability and local target assignment. The former arises from the inherent lack of…

Diffusion-based image generative models produce high-fidelity images through iterative denoising but remain vulnerable to memorization, where they unintentionally reproduce exact copies or parts of training images. Recent memorization…

The widespread use of diffusion models has led to an abundance of AI-generated data, raising concerns about model collapse -- a phenomenon in which recursive iterations of training on synthetic data lead to performance degradation. Prior…

Generative latent diffusion models have been established as state-of-the-art in data generation. One promising application is generation of realistic synthetic medical imaging data for open data sharing without compromising patient privacy.…

Recently, the strong latent Diffusion Probabilistic Model (DPM) has been applied to high-quality Text-to-Image (T2I) generation (e.g., Stable Diffusion), by injecting the encoded target text prompt into the gradually denoised diffusion…

The correspondence between input text and the generated image exhibits opacity, wherein minor textual modifications can induce substantial deviations in the generated image. While, text embedding, as the pivotal intermediary between text…

Subject-driven text-to-image diffusion models empower users to tailor the model to new concepts absent in the pre-training dataset using a few sample images. However, prevalent subject-driven models primarily rely on single-concept input…

The success of recent text-to-image diffusion models is largely due to their capacity to be guided by a complex text prompt, which enables users to precisely describe the desired content. However, these models struggle to effectively…

Despite the empirical advances of deep learning across a variety of learning tasks, our theoretical understanding of its success is still very restricted. One of the key challenges is the overparametrized nature of modern models, enabling…

Text-to-image diffusion models have shown impressive capabilities in generating realistic visuals from natural-language prompts, yet they often struggle with accurately binding attributes to corresponding objects, especially in prompts…

Tabular data generation has attracted significant research interest in recent years, with the tabular diffusion models greatly improving the quality of synthetic data. However, while memorization, where models inadvertently replicate exact…

Restoring low-resolution text images presents a significant challenge, as it requires maintaining both the fidelity and stylistic realism of the text in restored images. Existing text image restoration methods often fall short in hard…

In the rapidly evolving landscape of artificial intelligence, generative models such as Generative Adversarial Networks (GANs) and Diffusion Models have become cornerstone technologies, driving innovation in diverse fields from art creation…

As large-scale text-to-image generation models have made remarkable progress in the field of text-to-image generation, many fine-tuning methods have been proposed. However, these models often struggle with novel objects, especially with…

Generative models, particularly text-to-image (T2I) diffusion models, play a crucial role in medical image analysis. However, these models are prone to training data memorization, posing significant risks to patient privacy. Synthetic chest…

As humans, we can remember certain visuals in great detail, and sometimes even after viewing them once. What is even more interesting is that humans tend to remember and forget the same things, suggesting that there might be some general…