Related papers: Empty SPACE: Cross-Attention Sparsity for Concept …
Diffusion models have shown impressive results in generating high-quality conditional samples using guidance techniques such as Classifier-Free Guidance (CFG). However, existing methods often require additional training or neural function…
Post-hoc unlearning has emerged as a practical mechanism for removing undesirable concepts from large text-to-image diffusion models. However, prior work primarily evaluates unlearning through erasure success; its impact on broader…
Text-to-image diffusion models have achieved unprecedented proficiency in generating realistic images. However, their inherent tendency to memorize and replicate training data during inference raises significant concerns, including…
Driven by the scalable diffusion models trained on large-scale datasets, text-to-image synthesis methods have shown compelling results. However, these models still fail to precisely follow the text prompt involving multiple objects,…
Text-to-image diffusion models have achieved remarkable progress, yet their use raises copyright and misuse concerns, prompting research into machine unlearning. However, extending multi-concept unlearning to large-scale scenarios remains…
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…
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…
As powerful generative models, text-to-image diffusion models have recently been explored for discriminative tasks. A line of research focuses on adapting a pre-trained diffusion model to semantic segmentation without any further training,…
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.…
The recent proliferation of diffusion models has made style mimicry effortless, enabling users to imitate unique artistic styles without authorization. In deployed platforms, this raises copyright and intellectual-property risks and calls…
Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward…
Text-to-image diffusion models have demonstrated remarkable capabilities in generating high-quality images, yet their tendency to reproduce undesirable concepts, such as NSFW content, copyrighted styles, or specific objects, poses growing…
Studies have been conducted to prevent specific concepts from being generated from pretrained text-to-image generative models, achieving concept erasure in various ways. However, the performance evaluation of these studies is still largely…
While large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities, there are significant concerns about their potential misuse for generating unsafe content, violating copyright, and perpetuating…
We are witnessing rapid progress in automatically generating and manipulating 3D assets due to the availability of pretrained text-image diffusion models. However, time-consuming optimization procedures are required for synthesizing each…
We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution (SR). Specifically, by employing our time-aware encoder, we can achieve promising restoration…
Concept erasing has recently emerged as an effective paradigm to prevent text-to-image diffusion models from generating visually undesirable or even harmful content. However, current removal methods heavily rely on manually crafted text…
The proliferation of text-to-image diffusion models has raised significant privacy and security concerns, particularly regarding the generation of copyrighted or harmful images. In response, concept erasure (defense) methods have been…
Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotations. Despite considerable progress, existing state-of-the-art unsupervised trackers often…
Ensuring that neural models used in real-world applications cannot infer sensitive information, such as demographic attributes like gender or race, from text representations is a critical challenge when fairness is a concern. We address…