Back to feed
News Story
APriority83
量子位
1 sources

Om AI Open-Sources On-Device Native Model VLX-Seek 1.5, Secures Hundreds of Millions in Funding

Om AI announced a funding round of hundreds of millions of yuan and open-sourced the world's first on-device native model, VLX-Seek 1.5. The model is designed from the architecture level for edge environments, aiming to achieve precise perception of the physical world, contrasting with cloud-based approaches. This move is seen as a significant advancement in physical AI, potentially driving large-scale adoption of on-device intelligence.

SynthePulse Insight · AI deep readingMembers

On-Device Native: The Next Paradigm for Physical AI? The Route Debate Behind Om AI's VLX-Seek 1.5 Open Source and Funding

Version 1 · 1 source

While global giants bet on cloud-based large models, Om AI has surpassed NVIDIA and Google in multiple benchmarks with a 3B-parameter model, securing hundreds of millions in funding. Will on-device native become the key to scaling physical AI? This article dissects its technical route, benchmark data, and commercial strategy.

  • Om AI completed a funding round of hundreds of millions of yuan, led by Qianhai Mother Fund, and open-sourced the world's first on-device native model, VLX-Seek 1.5.
  • VLX-Seek 1.5 uses a streaming multimodal architecture, incorporating on-device compute, latency, and power as constraints from the model design stage, unlike post-training compression for deployment.
  • The 3B version achieves 57.5 on LVIS Mean, a 13.4% improvement over LocateAnything-3B; RefDrone F1 reaches 73.2, a 40% improvement.
Open section navigationPhysical AI Route Map: On-Device Native Fills a Gap

Physical AI Route Map: On-Device Native Fills a Gap

Global competition in physical AI models revolves around 'how to make AI understand and act in the physical world,' with multiple routes: NVIDIA Cosmos pursues cloud-based world models, Physical Intelligence explores cloud-based general robot policy models, Google Gemini Robotics advances cloud-based VLA, and Tesla Optimus emphasizes model-hardware closed loops. These routes answer different questions, but none specifically address 'how to make AI models adapt to on-device environments from inception.'

Om AI's self-developed VLX on-device streaming multimodal model series emphasizes the 'on-device native' route: not relying on cloud compute, not tied to a single hardware platform, and incorporating on-device compute, latency, power, and deployment cost as constraints from the design stage. This is fundamentally different from the transfer deployment of 'train large models then compress for deployment'—the latter is 'making powerful models run on devices,' while the former is 'if AI is born on devices, what should it look like?'

The value of on-device native lies in faster response, lower cost, and greater autonomy, enabling physical AI to enter factories, homes, drone inspections, and other scenarios. Robots cannot always rely on cloud brains because network latency, data transmission costs, and privacy issues are unacceptable in real-world settings.

Free for now

Read the full analysis

3 more sections of analysis, plus the full takeaway

Loading

Credibility boundary

This article's information primarily comes from reports by QbitAI, which are second-hand accounts. The funding amount, benchmark data, and product deployments are as claimed by the source and have not been independently verified. The benchmark comparison models and specific conditions are not fully disclosed, and there is potential for selective presentation.

Primary report

量子位

Primary source