Lists (1)
Sort Name ascending (A-Z)
Stars
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
🤗 smolagents: a barebones library for agents that think in code.
verl: Volcano Engine Reinforcement Learning for LLMs
Awesome machine learning for combinatorial optimization papers.
fay是一个帮助数字人(2.5d、3d、移动、pc、网页)或大语言模型(openai兼容、deepseek)连通业务系统的mcp框架。
All NLP you Need Here. 目前包含15个NLP demo的pytorch实现(大量代码借鉴于其他开源项目,原先是自己玩的,后来干脆也开源出来)
VisJudgeBench: A comprehensive benchmark for aesthetics and quality assessment of visualizations, featuring 3,090 expert-annotated samples with six-dimensional quality scores.
SimpleAICV:pytorch training and testing examples.
🌟100+ 原创 LLM / RL 原理图📚,《大模型算法》作者巨献!💥(100+ LLM/RL Algorithm Maps )
自动化上传视频到社交媒体:抖音、小红书、视频号、tiktok、youtube、bilibili
Next paradigm for LLM Agent. Unify plan and action through recursive code generation for adaptive, human-like decision-making.
This is a continuously updated handbook for readers to easily track the latest Text-to-SQL techniques in the literature and provide practical guidance for researchers and practitioners.
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
🔥[NeurIPS'25] DeepFund: Pilot for Your Next Fund Investment
Continuously updated paper list on advancements in Data Agents. Companion repo to our paper "A Survey of Data Agents: Emerging Paradigm or Overstated Hype?"
Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Solve Visual Understanding with Reinforced VLMs
This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.
OLMoE: Open Mixture-of-Experts Language Models
OpenSeek aims to unite the global open source community to drive collaborative innovation in algorithms, data and systems to develop next-generation models that surpass DeepSeek.