MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It represents a rare attempt to scale embodied AI with such a massive real-world trajectory dataset from a major manufacturer, though code and weights are not yet public.
Who it is for
- Robotics researchers
- Embodied AI practitioners
- Xiaomi ecosystem developers
- Industrial automation engineers
Use cases
- General-purpose robot manipulation in household or factory settings
- Zero-shot deployment of learned motor skills
- Research on scaling laws for robot learning
- Benchmarking vision-language-action models
Strengths
- Trained on over 100K hours of real-world trajectories, far exceeding typical datasets
- Claims out-of-the-box usability for embodied tasks
- Linked to a published citation indicating formal research backing
Considerations
- Code and model weights are not yet released (expected July 2026)
- No technical details, benchmarks, or evaluation results provided
- Unclear real-world performance outside controlled conditions
README quick start
Xiaomi-Robotics-1
Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories
Our latest robot foundation model, pre-trained on over 100K hours of real-world trajectories, brings scaling to embodied intelligence—and is ready to use out of the box.
🚀 Coming soon — July 16, 2026
Code and model weights will be released soon. Stay tuned.
Citation
If you find this work useful, please consider citing:
@article{xiaomi2026robotics1,
title={Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories},
author={Xiaomi Robotics},
journal={arXiv preprint},
year={2026}
}
Description
Code for Xiaomi-Robotics-1
Related repositories
Similar projects matched by category, topics, and programming language.
xuchonglang
Featured
investing-for-beginners
A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.
Krishnagangwal
Featured
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.