GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

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

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

[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers

Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

✨✨[NeurIPS 2025] VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

A library for advanced large language model reasoning

【TMM 2025🔥】 Mixture-of-Experts for Large Vision-Language Models

Next-Token Prediction is All You Need

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.

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

Fully open data curation for reasoning models

VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

Render any git repo into a single static HTML page for humans or LLMs

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

UltraRAG 2.0: Less Code, Lower Barrier, Faster Deployment! MCP-based low-code RAG framework, enabling researchers to build complex pipelines to creative innovation.

Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".

Scalable RL solution for advanced reasoning of language models

Emu Series: Generative Multimodal Models from BAAI

ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Experts via Clustering

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

Implementing DeepSeek R1's GRPO algorithm from scratch

A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.

An Open Large Reasoning Model for Real-World Solutions

A flexible framework powered by ComfyUI for generating personalized Nobel Prize images.

👻 Experimental library for scraping websites using OpenAI's GPT API.