Stars
微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。
Blind&Invisible Watermark ，图片盲水印，提取水印无须原图！
Official Code for ICCV 2025 paper — Beyond Isolated Words: Diffusion Brush for Handwritten Text-Line Generation
[ICCV 2025] HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets
Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜
Make Large Multimodal Models excel in object detection, ICCV 2025
Here is a series of face generators based on StyleGAN2
LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.
JS逆向系列教程，模拟登录，AES、RSA、DES加密等，持续更新，欢迎 star！
✍ WeChat Markdown Editor | 一款高度简洁的微信 Markdown 编辑器：支持 Markdown 语法、自定义主题样式、内容管理、多图床、AI 助手等特性
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥
Mu-L / code-box
Forked from 027xiguapi/code-box本插件可以用于CSDN/知乎/脚本之家/博客园等网站,实现无需登录一键复制代码;支持选中代码;或者代码右上角按钮的一键复制;解除关注博主即可阅读全文提示;去除登录弹窗;去除跳转APP弹窗.
A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint Space
YOLO-UniOW: Efficient Universal Open-World Object Detection
[NeurIPS24] VisMin: Visual Minimal-Change Understanding
Image Textualization: An Automatic Framework for Generating Rich and Detailed Image Descriptions (NeurIPS 2024)
efinance 是一个可以快速获取基金、股票、债券、期货数据的 Python 库，回测以及量化交易的好帮手！🚀🚀🚀
A research repo for experiments about Reinforcement Finetuning
A straightforward method for training your LLM, from downloading data to generating text.
A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.