Search

Tactile Sensing • Data Collection • IL/RL/VLA/WM • Manipulation • Simulation • Open Source

A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.

📚这个仓库是在arxiv上收集的有关VLN，VLA，World Model，SLAM，Gaussian Splatting,非线性优化等相关论文。每天都会自动更新！issue区域是最新10篇论文

Awesome collection of resources and papers on Diffusion Models for Robotic Manipulation.

A Pure Rust based LLM, VLM, VLA, TTS, OCR Inference Engine, powering by Candle & Rust. Alternate to your llama.cpp but much more simpler and cleaner..

A comprehensive list of excellent research papers, models, datasets, and other resources on Vision-Language-Action (VLA) models in robotics.

Galaxea's open-source VLA repository

🌐 Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future

RealMirror, a comprehensive, open-source embodied AI VLA platform.

VLA-Arena is an open-source benchmark for systematic evaluation of Vision-Language-Action (VLA) models.

Collects papers on autonomous driving E2E learning, VLM/VLA and Hybrid systems, with organized research branches and trends in these fields.

本项目旨在为致力于进入VLA(Vision-Language-Action)领域的算法工程师提供一份全中文、实战导向的学习/面试手册。 不同于通用的 CV/NLP 面试指南，本项目聚焦于 Robotics 特有的挑战

[ICLR 2026] Towards Unified Latent VLA for Whole-body Loco-manipulation Control

Tensor's VLA Training Infrastructure for Real-World Robotics in PyTorch

Elegant VLA-RL library

A Curated List of Vision-Language-Action (VLA) and World Action Models (WAM) Research and Beyond

[CVPR 2026] Official implementation of "ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models"

[RSS26'] Welcome to Psi-Zero, a Humanoid VLA towards Universal Humanoid Intelligence.

🤖🧠👾 Graph VLA with Control Barrier Function in Dual-Arm Robotics Manipulation

One framework to evaluate any VLA model on any robot simulation benchmark.

Mano-P: Open-source GUI-VLA agent for edge devices. #1 on OSWorld (specialized, 58.2%). Runs locally on Apple M4 Mac mini/MacBook — no data leaves your device.Mano-P 是一个开源 GUI-VLA 项目，支持在 Mac mini/MacBook 上或通过算力棒本地运行推理，实现纯视觉驱动的跨平台 GUI 自动化操作。数据完全本地处理，支持复杂多步骤任务规划与执行。

An all-in-one VLA engineering platform for embodied AI — from data to real-robot deployment.

从零到一搭建一台具身智能机器人:深入强化学习、World-Model、VLA 等智能决策方法的工程落地,贯穿仿真环境、控制器、运动规划、感知系统等技能树模块,并在真实项目中跑通"决策—控制—感知"完整链路。

FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST. Also support llm e.g, qwen3.6-27B

A unified inference runtime for VLA models.

The official repository of Qwen-VLA

Toolkit for collecting, merging, auditing, visualizing, and publishing RGB/RGB-D LeRobot VLA datasets.

From Vision-Language-Action Models to a Real-World Robot Learning Stack

Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark.

HEI ReBot Lift is a LeRobot/ReBot-based dual-arm mobile robot with a lifting platform, omnidirectional chassis, three-view vision, and a VR + MuJoCo + Pinocchio IK teleoperation pipeline. It supports teleoperation, data recording, ACT/VLA training, and policy deployment.