yujiaaoyu
Follow
Stars
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
GAL-DAWN: An Novel Graph Algorithm Library based on DAWN, CUDA/C
MAPLE: Masked Pseudo-Labeling autoEncoder for Semi-supervised Point Cloud Action Recognition.
MiniMind：3小时完全从0训练一个仅有26M的极小参数语言模型！最低仅需2G显卡即可推理训练！
Explainable Person Re-Identification with Attribute-guided Metric Distillation
Two lines of js realize automatic html translation. No need to change the page, no language configuration file, no API key, SEO friendly!
OSAI: Your AI-powered OS assistant. Rename files, manage environment variables, set reminders, and control your system through natural language commands for Windows Macos and Linux. Streamline your…
SGS, is a user-friendly, collaborative and versatile browser for visualizing single-cell and spatial multiomics data.
Awesome LLMs on Device: A Comprehensive Survey
This is the official reproduction of FancyVideo.
Video-Inpaint-Anything: This is the inference code for our paper CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility.
An open source task scheduling library ASRT (Async Runtime) written in modern C tailored for embedded linux systems.
Offical Code of MICCAI'24 early accepted paper "LGRNet: Local-Global Reciprocal Network for Uterine Fibroid Segmentation in Ultrasound Videos"
Next-Generation Interactive Intelligent Programming Assistant
Collecting personality-indicative data for role-playing agents.
A curated list of awesome papers related to adversarial attacks and defenses for information retrieval. If I missed any papers, feel free to open a PR to include them! And any feedback and contribu…
Cocos simplifies game creation and distribution with Cocos Creator, a free, open-source, cross-platform game engine. Empowering millions of developers to create high-performance, engaging 2D/3D gam…
[CVPR 2024] Official code for "Text-Driven Image Editing via Learnable Regions"
A multimodal agent framework for solving complex tasks
This is the public code repository of paper 'Comprehensive Assessment of Jailbreak Attacks Against LLMs'
kight is a static analysis tool for c/c programs.
WordGPT是一款可以结合个人知识库或联网查询资料快速生成高质量论文、简历、博客、新闻稿、产品描述、故事、邮件、剧本、诗歌、工作汇报，及思维导图、文章配图等内容，同时可以进行各种语言的翻译，还能根据文本生成PPT的的工具。