Diffusion LLMs have emerged as a promising alternative to conventional autoregressive LLMs, offering significant potential for improved runtime efficiency. However, existing diffusion models lack the ability to provably enforce user-specified formal...
Methods based on diffusion backbones have recently revolutionized novel view synthesis (NVS). However, those models require pretrained 2D diffusion checkpoints (e.g., Stable Diffusion) as the basis for geometrical priors. Since such checkpoints requi...
We propose a diffusion-based approach for Text-to-Image (T2I) generation with interactive 3D layout control. Layout control has been widely studied to alleviate the shortcomings of T2I diffusion models in understanding objects' placement and relation...
While diffusion models can successfully generate data and make predictions, they are predominantly designed for static images. We propose an approach for efficiently training diffusion models for probabilistic spatiotemporal forecasting, where genera...
We propose Latent-Shift -- an efficient text-to-video generation method based on a pretrained text-to-image generation model that consists of an autoencoder and a U-Net diffusion model. Learning a video diffusion model in the latent space is much mor...
This paper introduces ITA-MDT, the Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On (IVTON), designed to overcome the limitations of previous approaches by leveraging the Masked Diffusion Transformer (MDT)...
The introduction of diffusion models has brought significant advances to the field of audio-driven talking head generation. However, the extremely slow inference speed severely limits the practical implementation of diffusion-based talking head gener...
By embedding discrete representations into a continuous latent space, we can leverage continuous-space latent diffusion models to handle generative modeling of discrete data. However, despite their initial success, most latent diffusion methods rely...
Uncovering the opacity of diffusion-based generative models is urgently needed, as their applications continue to expand while their underlying procedures largely remain a black box. With a critical question -- how can the diffusion generation proces...
NGC288 is a globular cluster with a well-developed blue horizontal branch covering the u-jump that indicates the onset of diffusion. It is therefore well suited to study the effects of diffusion in blue horizontal branch (HB) stars. We compare observ...
Diffusion models with large-scale pre-training have achieved significant success in the field of visual content generation, particularly exemplified by Diffusion Transformers (DiT). However, DiT models have faced challenges with quadratic complexity...
We propose that the liquidity of an asset includes two components: liquidity jump and liquidity diffusion. We show that liquidity diffusion has a higher correlation with crypto wash trading than liquidity jump and demonstrate that treatment on wash t...
Diffusion distillation models effectively accelerate reverse sampling by compressing the process into fewer steps. However, these models still exhibit a performance gap compared to their pre-trained diffusion model counterparts, exacerbated by distri...
Recent advances in text-to-video generation have demonstrated the utility of powerful diffusion models. Nevertheless, the problem is not trivial when shaping diffusion models to animate static image (i.e., image-to-video generation). The difficulty o...
We present On-device Sora, the first model training-free solution for diffusion-based on-device text-to-video generation that operates efficiently on smartphone-grade devices. To address the challenges of diffusion-based text-to-video generation on c...
We present On-device Sora, the first model training-free solution for diffusion-based on-device text-to-video generation that operates efficiently on smartphone-grade devices. To address the challenges of diffusion-based text-to-video generation on c...
Diffusion models have achieved great success in synthesizing high-quality images. However, generating high-resolution images with diffusion models is still challenging due to the enormous computational costs, resulting in a prohibitive latency for in...
Diffusion models have achieved remarkable success in various generative tasks, but training them remains highly resource-intensive, often requiring millions of images and many days of GPU computation. From a data-centric perspective addressing this l...
Diffusion MRI (dMRI) provides the ability to reconstruct neuronal fibers in the brain, $\textit{in vivo}$, by measuring water diffusion along angular gradient directions in q-space. High angular resolution diffusion imaging (HARDI) can produce better...
We approximate the price of the American put for jump diffusions by a sequence of functions, which are computed iteratively. This sequence converges to the price function uniformly and exponentially fast. Each element of the approximating sequence...