Maximum weighted matching for Boost.org graph module

maximum cardinality matching by Edmonds' algorithm, an implementation based on union find data structure

The Edmonds Blossom (aka the Blossom Algorithm), written in Swift

AGT course project on maximum matching in bipartite and general graphs

A C++ implementation of the blossom algorithm for maximum matching in general graphs.

An implementation of the blossom algorithm for constructing maximum matchings on graphs.

A ReScript implementation of the blossom maximum-matching algorithm.

A distributed blossom algorithm for minimum-weight perfect matching

A Python implementation of Edmond's blossom algorithm to find maximum matchings in general graphs

A C++ implementation of Edmonds' blossom algorithm to find maximum matchings in general graphs

My solutions to Google's Foobar Challenge for coding data structures and algorithms. Includes my solution code, unit tests, background notes, design notes, and references.

Advance algorithm implementations

A python implementation of Edmonds blossom algorithm for maximum-cardinality matching.

C++ implementation of algorithms for finding perfect matchings in general graphs

基于Qwen2+SFT+DPO的医疗问答系统，项目中使用了自定义的 SFTTrainer/DPOTrainer/TRPOTrainer用于训练，其次，项目还调用各种知识库工具（neo4j, milvus, LDA, 等）进行自动化训练数据生成。另外，使用 vllm 用于推理和部署训好的模型, 该模型会通过 vllm API 来接入一个基于 embedder + Reranker 的 RAG …

Benchmarking LLMs Clinical Skills for Patient-Centered Diagnostics and Documentation

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition

Deep and online learning with spiking neural networks in Python

A transformer-based weakly supervised computational pathology method for clinical-grade diagnosis and molecular state revelation of gliomas

Prov-GigaPath: A whole-slide foundation model for digital pathology from real-world data

Open source tools for computational pathology - Nature BME

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

A research toolkit for particle swarm optimization in Python

基于ChatGLM-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning等

LightSeq: A High Performance Library for Sequence Processing and Generation

财务管理系统