Lists (3)
Stars
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
A minimal implementation of DeepMind's Genie world model
Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots
[RSS'25] This repository is the implementation of "NaVILA: Legged Robot Vision-Language-Action Model for Navigation"
Low-level locomotion policy training in Isaac Lab
[RSS 2024] NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
InternRobotics' open platform for building generalized navigation foundation models.
A modular high-level library to train embodied AI agents across a variety of tasks and environments.
Benchmarking Knowledge Transfer in Lifelong Robot Learning
[ICCV 2025] Official Implementation for "Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition"
a light-weight metadata parser for safetensors files
A universal Stable-Diffusion toolbox
RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.
Official implementation of the paper: "NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance"
MemU is an open-source memory framework for AI companions
An open-source AI agent that brings the power of Gemini directly into your terminal.
Qwen Code is a coding agent that lives in the digital world.
[CoRL 2025] UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations
本仓库包含对 Claude Code v1.0.33 进行逆向工程的完整研究和分析资料。包括对混淆源代码的深度技术分析、系统架构文档，以及重构 Claude Code agent 系统的实现蓝图。主要发现包括实时 Steering 机制、多 Agent 架构、智能上下文管理和工具执行管道。该项目为理解现代 AI agent 系统设计和实现提供技术参考。
Copilot Chat extension for VS Code