Home
OmniXtreme Humanoid Robot Architecture Unveiled: Flow Matching Tackles High-Dynamic Movement Challenges
Unitree has officially released and open-sourced its humanoid robot motion control architecture, named OmniXtreme, accompanied by a technical paper authored by its founder, Wang Xingxing. This architecture comprehensively addresses the challenges of motion fidelity loss and physical instability when executing extensive motion libraries in highly dynamic environments, such as stage performances for humanoid robots.

The OmniXtreme architecture employs a two-stage training framework. The first stage, Scalable Flow-based Pretraining, distills complex, high-dynamic skills—including backflips, martial arts, and street dance—from various expert strategies into a unified model. It learns motion trajectories through generative flow matching, effectively overcoming the gradient conflicts typical in multi-task reinforcement learning. The second stage, Actuation-Aware Post-Training, incorporates residual reinforcement learning and detailed torque-speed envelope modeling. This allows the robot to autonomously adjust its actions based on real-time motor physical limits and regenerative power dynamics.
Experimental results indicate that this architecture achieved a 96.36% success rate for backflips on the Unitree G1 hardware platform, with end-to-end inference latency reduced to 10 milliseconds. The open-source release of OmniXtreme not only showcases the strong scalability of flow matching technology in embodied AI but also signifies a shift for humanoid robots from replicating isolated skills to possessing general, high-fidelity mobility. It establishes a crucial technical framework for the industry to develop robust control systems in complex real-world environments.
Related article
Google IO 2026 unveils voice interaction with Gmail inbox
Google continues to integrate AI into your inbox. At the IO 2026 developer conference on Tuesday, the company expanded its Gmail "AI Inbox" feature with conversational AI, allowing users to ask questions about their inbox content rather than relying
iFlytek Debuts AI Glasses with GlassClaw Assistant for 4299 CNY
As AI large models increasingly move into edge-side hardware, the smart wearable market has gained a significant new player. On May 28, iFLYTEK officially launched its "iFLYTEK AI Glasses" at the BEYOND Expo 2026 in Macao, marking a deeper integratio
Lei Jun confirms Xiaomi's desktop AI agent MiClaw in development, MiMo-V2-Pro launches across all platforms
At the 2026 China Development High-level Forum, Xiaomi Group's Lei Jun confirmed that the long-awaited desktop version of the AI agent "MiClaw" (crab) is now on the development roadmap. Xiaomi had already launched a limited closed beta for the mobile
Related Special Topic Recommendations
Comments (0)
0/500
Unitree has officially released and open-sourced its humanoid robot motion control architecture, named OmniXtreme, accompanied by a technical paper authored by its founder, Wang Xingxing. This architecture comprehensively addresses the challenges of motion fidelity loss and physical instability when executing extensive motion libraries in highly dynamic environments, such as stage performances for humanoid robots.

The OmniXtreme architecture employs a two-stage training framework. The first stage, Scalable Flow-based Pretraining, distills complex, high-dynamic skills—including backflips, martial arts, and street dance—from various expert strategies into a unified model. It learns motion trajectories through generative flow matching, effectively overcoming the gradient conflicts typical in multi-task reinforcement learning. The second stage, Actuation-Aware Post-Training, incorporates residual reinforcement learning and detailed torque-speed envelope modeling. This allows the robot to autonomously adjust its actions based on real-time motor physical limits and regenerative power dynamics.
Experimental results indicate that this architecture achieved a 96.36% success rate for backflips on the Unitree G1 hardware platform, with end-to-end inference latency reduced to 10 milliseconds. The open-source release of OmniXtreme not only showcases the strong scalability of flow matching technology in embodied AI but also signifies a shift for humanoid robots from replicating isolated skills to possessing general, high-fidelity mobility. It establishes a crucial technical framework for the industry to develop robust control systems in complex real-world environments.
Google IO 2026 unveils voice interaction with Gmail inbox
Google continues to integrate AI into your inbox. At the IO 2026 developer conference on Tuesday, the company expanded its Gmail "AI Inbox" feature with conversational AI, allowing users to ask questions about their inbox content rather than relying
iFlytek Debuts AI Glasses with GlassClaw Assistant for 4299 CNY
As AI large models increasingly move into edge-side hardware, the smart wearable market has gained a significant new player. On May 28, iFLYTEK officially launched its "iFLYTEK AI Glasses" at the BEYOND Expo 2026 in Macao, marking a deeper integratio
Lei Jun confirms Xiaomi's desktop AI agent MiClaw in development, MiMo-V2-Pro launches across all platforms
At the 2026 China Development High-level Forum, Xiaomi Group's Lei Jun confirmed that the long-awaited desktop version of the AI agent "MiClaw" (crab) is now on the development roadmap. Xiaomi had already launched a limited closed beta for the mobile











