Xiaomi Open-Sources VLA Robot Foundation Model
XiaomiRobotics · hf · 2026-07-20
Xiaomi Robotics released Xiaomi-Robotics-1, a Vision-Language-Action (VLA) foundation model designed to perform various mobile manipulation tasks directly in unseen environments and adapt to new tasks with minimal fine-tuning.
The paper employs a two-stage training approach:
- Pre-training: Utilizes over 100,000 hours of real-world manipulation trajectories collected via UMI devices, which are converted into natural language state-transition descriptions using an automated annotation pipeline.
- Post-training: Aligns the model more closely with specific robot embodiments and common human instruction formats.
Experiments show the model scales effectively with data volume and model size, outperforming existing methods on multiple simulation benchmarks. It achieves a 57.6% success rate on RoboCasa365 (beating the previous 46.6%) and scores 20.07 on RoboDojo (up from 13.07). Code and model weights will be released.
Related event: Xiaomi Open-Sources VLA Robotics Foundation Model(3 posts)→
More from Embodied
- ROS names Alejandro Hernández Cordero new project lead, eyes 2027 release — ___Mufasaa · 2026-10-27
- ROS Meetup coming to Google's NYC office Oct 29 with speakers from Tangent, Cohesive Robotics, Intrinsic — kscottz · 2026-10-27
- Tesla officially expands robotaxi service area across much of Houston, Texas — Polymarket · 2026-10-27
- Walden Robotics teaches robots to call for help, blending remote assist with autonomy — adnothing · 2026-10-27
- Folding-screen hinges: dozens of ultra-precise parts, one grain of sand can kill the panel — BenBajarin · 2026-10-27
- No π0 weights changed: Motoniq layer lifts real-robot precision fitting from 0/10 to 9/10 — hbouammar · 2026-10-27