Pistis Technical Report
Unveiling a scalable post-training framework and new multimodal benchmarks for the Qwen-based Pistis architecture.
We introduce the Pistis model family, comprising 27B- and 9B-parameter multimodal large language models built on Qwen3.6 and Qwen3.5, respectively, and developed through a general and scalable post-training framework. The framework first establishes a strong foundation through la...
ArXiv CS.AI
Source
Generated insight by OnAirToday AI
The introduction of the Pistis model family highlights an intensifying race to refine multimodal capabilities through specialized, scalable post-training frameworks. By leveraging high-performing Qwen foundations, these models demonstrate how architectural modularity can accelerate the development of state-of-the-art AI systems.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.