Related papers: Minimalist Concept Erasure in Generative Models

Evaluating generative models for synthetic medical imaging is crucial yet challenging, especially given the high standards of fidelity, anatomical accuracy, and safety required for clinical applications. Standard evaluation of generated…

Many segmentation tasks, such as medical image segmentation or future state prediction, are inherently ambiguous, meaning that multiple predictions are equally correct. Current methods typically rely on generative models to capture this…

Concept erasure aims to remove specified features from an embedding. It can improve fairness (e.g. preventing a classifier from using gender or race) and interpretability (e.g. removing a concept to observe changes in model behavior). We…

Adaptive and flexible image editing is a desirable function of modern generative models. In this work, we present a generative model with auto-encoder architecture for per-region style manipulation. We apply a code consistency loss to…

We present Thinking with Generated Images, a novel paradigm that fundamentally transforms how large multimodal models (LMMs) engage with visual reasoning by enabling them to natively think across text and vision modalities through…

End-to-end generative methods are considered a more promising solution for image restoration in physics-based vision compared with the traditional deconstructive methods based on handcrafted composition models. However, existing generative…

Neuromorphic vision sensors offer low latency and high dynamic range, but their deployment in public spaces raises severe data protection concerns. Recent Event-to-Video (E2V) models can reconstruct high-fidelity intensity images from…

Recent advances in generative modeling have led to an increased interest in the study of statistical divergences as means of model comparison. Commonly used evaluation methods, such as the Frechet Inception Distance (FID), correlate well…

The recent proliferation of photorealistic images created by generative models has sparked both excitement and concern, as these images are increasingly indistinguishable from real ones to the human eye. While offering new creative and…

Generative models such as denoising diffusion models are quickly advancing their ability to approximate highly complex data distributions. They are also increasingly leveraged in scientific machine learning, where samples from the implied…

A multitude of prevalent pre-trained models mark a major milestone in the development of artificial intelligence, while fine-tuning has been a common practice that enables pretrained models to figure prominently in a wide array of target…

Text-to-image diffusion models may generate harmful or copyrighted content, motivating research on concept erasure. However, existing approaches primarily focus on erasing concepts from text prompts, overlooking other input modalities that…

Concept erasure has emerged as a key research direction for ensuring safe and ethical image synthesis in Text-to-Image (T2I) models. While existing studies have explored concept erasure across multiple concepts, they typically assume only a…

Pruning-based unlearning has recently emerged as a fast, training-free, and data-independent approach to remove undesired concepts from diffusion models. It promises high efficiency and robustness, offering an attractive alternative to…

Diffusion models have achieved impressive advancements in various vision tasks. However, these gains often rely on increasing model size, which escalates computational complexity and memory demands, complicating deployment, raising…

Text-to-image generative models have made significant advancements in recent years; however, accurately capturing intricate details in textual prompts-such as entity missing, attribute binding errors, and incorrect relationships remains a…

Diffusion models (DMs) have achieved remarkable success in text-to-image generation, but they also pose safety risks, such as the potential generation of harmful content and copyright violations. The techniques of machine unlearning, also…

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…

Image recognition systems have demonstrated tremendous progress over the past few decades thanks, in part, to our ability of learning compact and robust representations of images. As we witness the wide spread adoption of these systems, it…

The impressive capability of modern text-to-image models to generate realistic visuals has come with a serious drawback: they can be misused to create harmful, deceptive or unlawful content. This has accelerated the push for machine…