Stars
Tongyi Deep Research, the Leading Open-source Deep Research Agent
使用LangGraph+DeepSeek-R1+FastAPI+Gradio实现一个带有记忆功能的流量包推荐智能客服web端用例,同时也支持gpt大模型、国产大模型(OneApi方式)、Ollama本地开源大模型、阿里通义千问大模型
基于大模型搭建的聊天机器人，同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入，可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。
Agent0 Series: Self-Evolving Agents from Zero Data
Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI.
A modular high-level library to train embodied AI agents across a variety of tasks and environments.
Ongoing research training transformer models at scale
NEO Series: Native Vision-Language Models from First Principles
[ACMMM-25] Official repo of "RemoteSAM: Towards Segment Anything for Earth Observation"
Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch
Solve Visual Understanding with Reinforced VLMs
Code for the paper "Evaluating Large Language Models Trained on Code"
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Fully open reproduction of DeepSeek-R1
A high-throughput and memory-efficient inference and serving engine for LLMs
Official implementation of paper "Query2Label: A Simple Transformer Way to Multi-Label Classification".
[NeurIPS 2020] Released code for Interventional Few-Shot Learning
[Lumina Embodied AI] 具身智能技术指南 Embodied-AI-Guide
deep learning for image processing including classification and object-detection etc.
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Code for "Leveraging Bilateral Correlations for Multi-Label Few-Shot Learning" in TNNLS 2024.
Ready-to-use code and tutorial notebooks to boost your way into few-shot learning for image classification.
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
The new spin-off of Visual Language Navigation.
A curated list for vision-and-language navigation. ACL 2022 paper "Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions"