WeRide Introduces WITT, a Physical AI Cognitive Foundation Model Built on Atomic Physical Facts
WeRide introduced WITT, a Physical AI Cognitive Foundation Model designed to transform real-world operational data into trusted facts for autonomous driving systems. The model leverages Atomic Physical Facts to improve AI cognition and reduces token costs by up to 98% while delivering up to 200 times greater data-processing efficiency than general-purpose models. WITT operates through four core capabilities—Fact Extraction, Fact Reasoning, Fact Verification, and Fact Curation—creating a pipeline that improves training and evaluation within the company's Physical AI architecture.
Key figures
- Fleet size
- more than 3,000
- Cities deployed
- more than 40
- Countries active
- 12
- Token cost reduction
- up to 98%
- Dynamic tags per request
- more than 100
- Vehicle programs selected
- close to 30
- Data processing efficiency
- up to 200x
- Daily video processing minutes
- 10000
AI analysis
The rest of the AI analysis, red flags and sentiment are part of Signal8 Pro.
AI-generated analysis of a public disclosure. Not investment advice; verify against the original document.