Stars
本科华五，曾赴美qs50读博，某兄弟院校副教授，校园门卫亭女性主理人，为防止炸号的备份平台，是本人。
Fast and memory-efficient exact attention
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Spec-driven development (SDD) for AI coding assistants.
Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"
UCAS国科大2024课程《GPU架构与编程》大作业1，编写pointnet的cuda推理程序。
Record danmaku during bilibili live
📄 Configuration files that enhance Cursor AI editor experience with custom rules and behaviors
PathDiff: Histopathology Image Synthesis with Unpaired Mask and Text - ICCV 2025.
Algorithm templates for programming contests in Python3.
Recommend new arxiv papers of your interest daily according to your Zotero libarary.
Official code for Score-Based Generative Models for PET Image Reconstruction (MELBA)
Official implementation of Cold-Diffusion for different transformations in pytorch.
Harmonization of multi-site imaging data with ComBat
Official repository of my book "A Hands-On Guide to Fine-Tuning LLMs with PyTorch and Hugging Face"
Dual-Prompt-Enhanced Multiorgan Segmentation Model for Total-Body PET Images
English Thesis template for sino-foreign cooperation project of CUG and iit
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A pytorch-based deep learning framework for multi-modal 2D/3D medical image segmentation
MOOSE (Multi-organ objective segmentation) a data-centric AI solution that generates multilabel organ segmentations to facilitate systemic TB whole-person research.The pipeline is based on nn-UNet …
🍚 Vue.js高仿饿了么外卖App课程源码 http://coding.imooc.com/class/74.html
Large single page application with 45 pages built on vue2 + vuex. 基于 vue2 + vuex 构建一个具有 45 个页面的大型单页面应用
厦门大学course平台第三方客户端，一个Electron+Vue3作为前端，Python作为本地后端的桌面端软件