Lists (5)
Stars
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
Minimal reproduction of DeepSeek R1-Zero
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI
PWM: Policy Learning with Large World Models
An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.
official repo for AGNOSTOS, a cross-task manipulation benchmark, and X-ICM method, a cross-task in-context manipulation (VLA) method
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。
High-Fidelity 3D Shape Generation via Scalable Geometric Refinement
AgentEvolver: Towards Efficient Self-Evolving Agent System
"AnyTool: Universal Tool-Use Layer for AI Agents"
Model Context Protocol(MCP) 编程极速入门
A Minecraft MCP Server powered by Mineflayer API. It allows to control a Minecraft character in real-time, allowing AI assistants to build structures, explore the world, and interact with the game …
Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).
[ICLR 2024] Official code of the paper "Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts.
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题
Benchmarking Knowledge Transfer in Lifelong Robot Learning
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
"RAG-Anything: All-in-One RAG Framework"
Official implementation of paper on Nature Machine Intelligence: "Preserving and Combining Knowledge in Robotic Lifelong Reinforcement Learning"
Codes of CTPG accompanying the paper "Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidance"(NeurIPS 2024).
Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"