-
The Chinese University of Hong Kong
- Sha Tin, Hong Kong, China
- https://gaoruiyuan.com/
- @ruiyuan_gao
Highlights
- Pro
Starred repositories
Open-MAGVIT2: Democratizing Autoregressive Visual Generation
A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。
【大模型】3小时完全从0训练一个仅有26M的小参数GPT,最低仅需2G显卡即可推理训练!
Ring attention implementation with flash attention
Minimal implementation of scalable rectified flow transformers, based on SD3's approach
Official implementation of 'Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields'
NVIDIA Linux open GPU kernel module source
✨✨Latest Advances on Multimodal Large Language Models
📊 A simple command-line utility for querying and monitoring GPU status
A modular differential gaussian rasterization library.
This repository is dedicated to Track 2 of the W-CODA 2024 Workshop, "Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving," held at ECCV 2024.
[ICLR 2024 Spotlight] SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors
VideoTetris: Towards Compositional Text-To-Video Generation
Official implementation of the paper “MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes”
Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation
Official PyTorch implementation of TrackDiffusion (https://arxiv.org/abs/2312.00651)
[CVPR 2024] Official implementation of "Towards Realistic Scene Generation with LiDAR Diffusion Models"
web看图小工具,可快速浏览多个文件夹的图片,支持显示坐标和复制路径,可以远程部署 解决搞深度学习看图费劲的痛点
A customised jail with action and filter file for Fail2Ban. This jail is based on the recidive jail but makes use of a simple text file to enable extended and permanent bans.
Download weibo images and videos.