分享 GitHub 上有趣、入门级的开源项目。Share interesting, entry-level open source projects on GitHub.

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

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。

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

A list of all named GANs!

StyleGAN - Official TensorFlow Implementation

Context engineering is the new vibe coding - it's the way to actually make AI coding assistants work. Claude Code is the best for this so that's what this repo is centered around, but you can apply…

Vector (and Scalar) Quantization, in Pytorch

Best practice and tips & tricks to write scientific papers in LaTeX, with figures generated in Python or Matlab.

A PyTorch Library for Multi-Task Learning

A deep matching model library for recommendations & advertising. It's easy to train models and to export representation vectors which can be used for ANN search.

solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

A simple pip-installable Python tool to generate your own HTML citation world map from your Google Scholar ID.

A parallel framework for population-based multi-agent reinforcement learning.

A novel approach for synthesizing tabular data using pretrained large language models

OpenCE (Open Context Engineering): A community toolkit to implement, evaluate, and combine LLM context strategies (RAG, ACE, Compression). Evolved from the `ACE-open` reproduction.

[ECIR'24] Implementation of "Large Language Models are Zero-Shot Rankers for Recommender Systems"

LibRerank is a toolkit for re-ranking algorithms. There are a number of re-ranking algorithms, such as PRM, DLCM, GSF, miDNN, SetRank, EGRerank, Seq2Slate.

[RelKD'24] Mamba4Rec: Towards Efficient Sequential Recommendation with Selective State Space Models

Code for paper "Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models"

Official Repo for InSTA: Towards Internet-Scale Training For Agents

Official Code for paper "Towards Efficient and Effective Unlearning of Large Language Models for Recommendation" (Frontiers of Computer Science 2024)

code for RIM

Official Code for paper "FLIP: Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction" (RecSys 2024)

Code for InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation

SimCSE

The pytorch implementation of paper: A Graph-Enhanced Click Model for Web Search