GitHub

Latent Diffusion Models for Unconditional Image Generation

This project provides a complete pipeline for latent diffusion models, covering image dataset encoding into latents, training three different models with two distinct noise schedules, and sampling ...

China's Z.ai claims it trained a model using only Huawei hardware

Chinese outfit Zhipu AI claims it trained a new model entirely using Huawei hardware, and that it’s the first company to ...
IEEE

D3PM: Dual-Stream Denoising Diffusion Probabilistic Model for Change Detection in Multimodal Remote Sensing Images

Abstract: Detecting land cover changes from multitemporal and multimodal remote sensing images acquired by different sensors at the same location is a complex yet highly valuable task. Recently, ...
GitHub

GD-Retriever: Controllable Generative Text-Music Retrieval with Diffusion Models

1 Centre for Digital Music, Queen Mary University of London, U.K. 2 Music & Audio Machine Learning Lab, Universal Music Group, London, U.K. Multimodal contrastive models have achieved strong ...
IEEE

High-Capacity Image Steganography Via Latent Diffusion Models

Abstract: Generative steganography has recently attracted considerable attention due to its superior security properties. However, most existing approaches suffer from limited hiding capacity. To ...