Forward-Looking Active REtrieval-augmented generation (FLARE)

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieval Results in RAG Systems (WWW 2025)

Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs (ACL 2024)

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

[Preprint] Learning to Filter Context for Retrieval-Augmented Generaton

Mastering Applied AI, One Concept at a Time

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

An annotated implementation of the Transformer paper.

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

LLM+RAG for QA

High accuracy RAG for answering questions from scientific documents with citations

An Improved Langchain RAG Tutorial (v2) with local LLMs, database updates, and testing.

A PyTorch implementation of the Transformer model in "Attention is All You Need".

Repository for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions, ACL23

This is the repo for the survey of LLM4IR.

Transformer: PyTorch Implementation of "Attention Is All You Need"

Minimal, clean example of lstm neural network training in python, for learning purposes.

Go to https://github.com/pytorch/tutorials - this repo is deprecated and no longer maintained

An IPython Notebook tutorial on deep learning for natural language processing, including structure prediction.

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

2024年计算机保研夏令营&冬令营通知

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

2024年保研经验贴和相关物料

A library for exploaring the domain adapatation probelm in the alignment of LLMs

PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.

PyTorch implementations of Generative Adversarial Networks.