BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx

starVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

[IROS 2025 Award Finalist] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model

Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

Code to Hand, Zero to Hero

The world's first open-source multimodal creative assistant This is a substitute for Canva and Manus that prioritizes privacy and is usable locally.

Building General-Purpose Robots Based on Embodied Foundation Model

Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence

[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents

RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

Galaxea's first VLA release

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

The Simulation Framework from AgiBot

[CVPR 2025] Official implementation of "GenManip: LLM-driven Simulation for Generalizable Instruction-Following Manipulation"

An All-in-one robot manipulation learning suite for policy models training and evaluation on various datasets and benchmarks.

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environments.

A comprehensive list of papers about Robot Manipulation, including papers, codes, and related websites.

🦾 A Dual-System VLA with System2 Thinking

RoboBrain 2.0: Advanced version of RoboBrain. See Better. Think Harder. Do Smarter. 🎉🎉🎉

[RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions

A Zsh theme

Spatial Sparse Convolution Library

GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer