My learning notes/codes for ML SYS.

Eye-gaze Guided Vision Transformer

📚 从零开始的大语言模型原理与实践教程

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

implement of "Multimodal Information Interaction for Medical Image Segmentation."

A light llama-like llm inference framework based on the triton kernel.

LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.

【A common used C++ & Python DAG framework】 一个通用的、无三方依赖的、跨平台的、收录于awesome-cpp的、基于流图的并行计算框架。欢迎star & fork & 交流

✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models

Estimate gaze on computer screen

Record radiologists' eye gaze when they are labeling images.

医学影像数据集列表 『An Index for Medical Imaging Datasets』

Liver Tumor Segmentation Challenge

Material for gpu-mode lectures

MICCAI 2024/2025: nnUNet incorporating additional baselines as SAMed️, Mamba Variants, and MedNeXT to establish a benchmark for segmentation challenges.

CUMT新闻后端

更适合矿大宝宝体质的选课互助网站

一个基于Flutter的多语言文物检索app

CUMT计算机设计大赛作品代码

一个简单的RAG项目

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.

图像中文描述+视觉注意力

[ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"

SimpleMindMap（思绪思维导图）：一个强大的Web思维导图。A powerful web mind map.

Code of paper “Knowledge Decomposition and Replay: A Novel Cross-modal Image-Text Retrieval Continual Learning Method”

An minimal Seq2Seq example of Automatic Speech Recognition (ASR) based on Transformer

Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.

A high-throughput and memory-efficient inference and serving engine for LLMs

how to learn PyTorch and OneFlow