XPeng and Others Release GroundingPI Model
The story so far
XPeng Group, in collaboration with Peking University, Hong Kong University, and others, released the GroundingPI pre-trained model, which scored 73.68 in a comprehensive evaluation of 34 perception benchmarks, surpassing GPT-6 Astra's 71.54. The model, with a scale of about 4 billion parameters, adopts a 'perception-first' technical approach, demonstrating higher data processing efficiency and stronger scene generalization capabilities in robot simulation tasks, significantly reducing teaching costs while maintaining stability. The research is currently in the prototype stage; the simulation results have already directly addressed two core issues in quantitative deployment.
AI-written from the reports · Updated 14 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- ITHome · AIXPeng, in collaboration with Peking University, Hong Kong University, and others, has released the GroundingPI pre-trained model, with its perception module scoring over GPT-6 Astra.
The GroundingPI model jointly released by Xpeng, Peking University, Hong Kong University, etc., scored 73.68 in a comprehensive evaluation of 34 perception benchmarks, surpassing GPT-6 Astra's 71.54. The model, with a parameter size of about 4 billion, adopts a 'perception-first' technical approach, demonstrating higher data processing efficiency and stronger scene generalization capabilities in robotic simulation tasks, significantly reducing teaching costs while maintaining stability.