Event
Spirit AI open-sources Spirit-v1.5 robotic foundation model
Key points
- Spirit AI released Spirit-v1.5 as an official VLA robotic foundation model implementation with model architecture, inference wrapper, RoboChallenge integration and model checkpoints.
- The repository says Spirit-v1.5 ranked first on the RoboChallenge Table30 benchmark as of January 11, 2026, and links the Hugging Face model release.
- The release matters because it gives Spirit AI a first-party model artifact behind its embodied-intelligence stack and provides a public benchmark path for the Moz1 product story.
Company context
Develops embodied AI systems and robots built around a Vision-Language-Action (VLA) model, focusing on real-world task execution across industrial and service environments.
Context
- Company
- Spirit AI
- Segment
- Humanoid
- Event type
- Research Publication
- Geography
- Hangzhou · China