Related papers: Redistribute Ensemble Training for Mitigating Memo…

Diffusion models are a class of generative models that have demonstrated remarkable success in tasks such as image generation. However, one of the bottlenecks of these models is slow sampling due to the delay before the onset of trajectory…

Recent advances in text-to-image diffusion models have enabled the generation of diverse and high-quality images. While impressive, the images often fall short of depicting subtle details and are susceptible to errors due to ambiguity in…

Diffusion models are popular tools for generating new data samples, using a forward process that adds noise to data and a reverse process to denoise and produce samples. However, when the data distribution consists of n points, empirical…

Text-to-image diffusion models allow seamless generation of personalized images from scant reference photos. Yet, these tools, in the wrong hands, can fabricate misleading or harmful content, endangering individuals. To address this…

The ambiguity between generalization and memorization in TTI diffusion models becomes pronounced when prompts invoke culturally shared visual references, a phenomenon we term multimodal iconicity. These are instances in which images and…

Personalizing text-to-image diffusion models involves integrating novel visual concepts from a small set of reference images while retaining the model's original generative capabilities. However, this process often leads to overfitting,…

The recent success of denoising diffusion models has significantly advanced text-to-image generation. While these large-scale pretrained models show excellent performance in general image synthesis, downstream objectives often require…

Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computational resources. Continual learning would allow for…

We systematically study a wide variety of generative models spanning semantically-diverse image datasets to understand and improve the feature extractors and metrics used to evaluate them. Using best practices in psychophysics, we measure…

While learned image compression (LIC) focuses on efficient data transmission, generative image compression (GIC) extends this framework by integrating generative modeling to produce photo-realistic reconstructed images. In this paper, we…

Diffusion models power leading generative AI, but when and how they memorize training data, especially on low-dimensional manifolds, remains unclear. We find memorization emerges gradually, not abruptly: as data become scarce, diffusion…

We introduce Diffusion Active Learning, a novel approach that combines generative diffusion modeling with data-driven sequential experimental design to adaptively acquire data for inverse problems. Although broadly applicable, we focus on…

Although diffusion models have demonstrated remarkable generative capabilities, existing style transfer techniques often struggle to maintain identity while achieving high-quality stylization. This limitation becomes particularly critical…

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 this paper, we consider the problem of fine-grained image retrieval in an incremental setting, when new categories are added over time. On the one hand, repeatedly training the representation on the extended dataset is time-consuming. On…

Diffusion models have exhibited remarkable capabilities in text-to-image generation. However, their performance in image-to-text generation, specifically image captioning, has lagged behind Auto-Regressive (AR) models, casting doubt on…

Knowledge distillation has been used to transfer knowledge learned by a sophisticated model (teacher) to a simpler model (student). This technique is widely used to compress model complexity. However, in most applications the compressed…

Generative models such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) have shown promise in sequential recommendation tasks. However, they face challenges, including posterior collapse and limited…

Machine learning models struggle with generalization when encountering out-of-distribution (OOD) samples with unexpected distribution shifts. For vision tasks, recent studies have shown that test-time adaptation employing diffusion models…

Predicting future states in uncertain environments, such as wildfire spread, medical diagnosis, or autonomous driving, requires models that can consider multiple plausible outcomes. While diffusion models can effectively learn such…