Výsledky vyhledávání - "Cai, MingHong"

Report

DebiasDiff: Debiasing Text-to-image Diffusion Models with Self-discovering Latent Attribute Directions

Autor: Jiang, Yilei, Li, Weihong, Zhang, Yiyuan, Cai, Minghong, Yue, Xiangyu

While Diffusion Models (DM) exhibit remarkable performance across various image generative tasks, they nonetheless reflect the inherent bias presented in the training set. As DMs are now widely used in real-world applications, these biases could perp

Externí odkaz: http://arxiv.org/abs/2412.18810

Zobrazit plný text záznamu

Report

DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation

Autor: Cai, Minghong, Cun, Xiaodong, Li, Xiaoyu, Liu, Wenze, Zhang, Zhaoyang, Zhang, Yong, Shan, Ying, Yue, Xiangyu

Sora-like video generation models have achieved remarkable progress with a Multi-Modal Diffusion Transformer MM-DiT architecture. However, the current video generation models predominantly focus on single-prompt, struggling to generate coherent scene

Externí odkaz: http://arxiv.org/abs/2412.18597

Zobrazit plný text záznamu

Report

EEG-EMG FAConformer: Frequency Aware Conv-Transformer for the fusion of EEG and EMG

Autor: He, ZhengXiao, Cai, Minghong, Li, Letian, Tian, Siyuan, Dai, Ren-Jie

Motor pattern recognition paradigms are the main forms of Brain-Computer Interfaces(BCI) aimed at motor function rehabilitation and are the most easily promoted applications. In recent years, many researchers have suggested encouraging patients to pe

Externí odkaz: http://arxiv.org/abs/2409.18973

Zobrazit plný text záznamu