Stabilizing Reinforcement Learning with LLMs: Formulation and Practices Paper โข 2512.01374 โข Published 7 days ago โข 78
Qwen2.5-Omni Collection End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 โข 7 items โข Updated Jul 21 โข 160
Qwen1.5 Collection Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. โข 55 items โข Updated Jul 21 โข 211