Awesome LLM compression research papers and tools.

Empowering RAG with a memory-based data interface for all-purpose applications!

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

机器学习工程师、算法工程师、软件工程师、数据科学家-面试指南 | Interview guide for MLE, SDE, DS

Membenchmark repository

The official implementation of the paper "Self-Updatable Large Language Models by Integrating Context into Model Parameters"

Source code and demo for memory bank and SiliconFriend

This repository introduce a comprehensive paper list, datasets, methods and tools for memory research.

Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025)

Official repository of DialSim

Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation

Native Multimodal Models are World Learners

Open-source unified multimodal model

Optimize prompts, code, and more with AI-powered Reflective Text Evolution

"Paper2Slides: From Paper to Presentation in One Click"

Codebase for "How Alignment Shrinks the Generative Horizon"

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

SGLang is a fast serving framework for large language models and vision language models.

Official PyTorch implementation for "Large Language Diffusion Models"

MemGen: Weaving Generative Latent Memory for Self-Evolving Agents

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

A PyTorch native platform for training generative AI models

A-MEM: Agentic Memory for LLM Agents

The code for NeurIPS 2025 paper "A-MEM: Agentic Memory for LLM Agents"

Code and documentation to train Stanford's Alpaca models, and generate the data.

Supercharge Your LLM with the Fastest KV Cache Layer

Fast and memory-efficient exact attention

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL