Renewal-anomalous-heterogeneous files are solved. A simple file is made of Brownian hard spheres that diffuse stochastically in an effective 1D channel. Generally, Brownian files are heterogeneous: the spheres' diffusion coefficients are distributed...
FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral) (⭐ 1895)
The dynamics of spreading of the minority opinion in public debates (a reform proposal, a behavior change, a military retaliation) is studied using a diffusion reaction model. People move by discrete step on a landscape of random geometry shaped by...
We examine an unexpected but significant source of positive public health messaging during the COVID-19 pandemic -- K-pop fandoms. Leveraging more than 7 million tweets related to mask-wearing and K-pop between March 2020 and December 2021, we analyz...
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model (⭐ 1281)
Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures. (⭐ 22844)
Generating realistic 3D scenes is challenging due to the complexity of room layouts and object geometries.We propose a sketch based knowledge enhanced diffusion architecture (SEK) for generating customized, diverse, and plausible 3D scenes. SEK condi...
Hashtags serve as identity markers and connection tools in online queer communities. Recently, the Western-origin #wlw (women-loving-women) hashtag has risen in the Chinese lesbian community on RedNote, coinciding with user migration triggered by the...
This project uses a pre-trained Stable Diffusion model (via AUTOMATIC1111’s WebUI) on Google Colab to generate highly realistic portraits from text prompts. The specific focus here is on creating a photo-realistic portrait of a smiling woman in warm sunlight,…
Fashion image editing aims to modify a person's appearance based on a given instruction. Existing methods require auxiliary tools like segmenters and keypoint extractors, lacking a flexible and unified framework. Moreover, these methods are limited i...
Recent advancements in graph diffusion models (GDMs) have enabled the synthesis of realistic network structures, yet ensuring fairness in the generated data remains a critical challenge. Existing solutions attempt to mitigate bias by re-training the...
Chain-of-Thought (CoT) reasoning improves multi-step mathematical problem solving in large language models but remains vulnerable to exposure bias and error accumulation, as early mistakes propagate irreversibly through autoregressive decoding. In th...
Burdzy and Chen (1998) proved results on weak convergence of multidimensional normally reflected Brownian motions. We generalize their work by considering obliquely reflected diffusion processes. We require weak convergence of domains, which is stron...
Diffusion-based Portrait and Animal Animation (⭐ 854)
Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content. They tend to synthesize quasi-static videos, ignoring the n...
This paper presents a novel approach to audio restoration, focusing on the enhancement of low-quality music recordings, and in particular historical ones. Building upon a previous algorithm called BABE, or Blind Audio Bandwidth Extension, we introduc...
Audio bandwidth extension involves the realistic reconstruction of high-frequency spectra from bandlimited observations. In cases where the lowpass degradation is unknown, such as in restoring historical audio recordings, this becomes a blind problem...
This paper presents some findings from a study researching the diffusion and adoption of online retailing in Saudi Arabia. Although the country has the largest and fastest growing ICT marketplace in the Arab region, e-commerce activities have not pro...
Despite the fact that Saudi Arabia is a leading producer of oil and natural gas, a member of G-20, has the largest and fastest growth of ICT marketplaces in the Arab region, and is very wealthy, online retailing activities are not progressing at the...
The debate on the Information Society shows large agreement on the assumption that the promised benefits will fully display only if the diffusion of ICTs and the Internet will involve all the actors of the socio-economic system. Accordingly, specia...