相关论文: DuMo: Dual Encoder Modulation Network for Precise …
Removing undesired concepts from large-scale text-to-image (T2I) and text-to-video (T2V) diffusion models while preserving overall generative quality remains a major challenge, particularly as modern models such as Stable Diffusion v3,…
The rapid progress of generative models has made synthetic image detection an increasingly critical task. Most existing approaches attempt to construct a single, universal discriminative space to separate real from fake content. However,…
Recent advances in large-scale text-to-image generation models have led to a surge in subject-driven text-to-image generation, which aims to produce customized images that align with textual descriptions while preserving the identity of…
Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this, unlearning methods have been developed to erase these…
Memorization in large-scale text-to-image diffusion models poses significant security and intellectual property risks, enabling adversarial attribute extraction and the unauthorized reproduction of sensitive or proprietary features. While…
Diffusion models have achieved unprecedented success in image generation but pose increasing risks in terms of privacy, fairness, and security. A growing demand exists to \emph{erase} sensitive or harmful concepts (e.g., NSFW content,…
With the rapid progress of diffusion-based content generation, significant efforts are being made to unlearn harmful or copyrighted concepts from pretrained diffusion models (DMs) to prevent potential model misuse. However, it is observed…
Autoregressive (AR) models have achieved unified and strong performance across both visual understanding and image generation tasks. However, removing undesired concepts from AR models while maintaining overall generation quality remains an…
Scene text image super-resolution (STISR) aims to simultaneously increase the resolution and legibility of the text images, and the resulting images will significantly affect the performance of downstream tasks. Although numerous progress…
Text-to-image diffusion models have achieved remarkable success in generating high-quality and diverse images. Building on these advancements, diffusion models have also demonstrated exceptional performance in text-guided image editing. A…
Diffusion based text-to-image models are trained on large datasets scraped from the Internet, potentially containing unacceptable concepts (e.g., copyright-infringing or unsafe). We need concept removal techniques (CRTs) which are i)…
Image Generation models are a trending topic nowadays, with many people utilizing Artificial Intelligence models in order to generate images. There are many such models which, given a prompt of a text, will generate an image which depicts…
Text-to-Image (T2I) generation is a popular AI-generated content (AIGC) technology enabling diverse and creative image synthesis. However, some outputs may contain Not Safe For Work (NSFW) content (e.g., violence), violating community…
Recent success of text-to-image (T2I) generation and its increasing practical applications, enabled by diffusion models, require urgent consideration of erasing unwanted concepts, e.g., copyrighted, offensive, and unsafe ones, from the…
Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attractive in this setting because they apply a single deterministic edit to the cross-attention…
Mixture of Experts (MoE) has become a mainstream architecture for building Large Language Models (LLMs) by reducing per-token computation while enabling model scaling. It can be viewed as partitioning a large Feed-Forward Network (FFN) at…
Modern over-parameterized deep models are highly data-dependent, with large scale general-purpose and domain-specific datasets serving as the bedrock for rapid advancements. However, many datasets are proprietary or contain sensitive…
Existing concept erasure methods for text-to-image diffusion models commonly rely on fixed anchor strategies, which often lead to critical issues such as concept re-emergence and erosion. To address this, we conduct causal tracing to reveal…
Text-to-image (T2I) models face significant safety risks from adversarial induction, yet current concept erasure methods often cause collateral damage to benign attributes when suppressing selected neurons entirely. This occurs because…
Deep learning has shown significant value in medical image registration for motion correction, however, current techniques are either limited by the type and range of motion they can handle, or require iterative inference and/or retraining…