Tag: qwen

All the articles with the tag "qwen".

• From GRPO to GSPO: Group-Based Policy Optimization for LLMs

  28 May, 2026

  A complete walkthrough of Group Relative Policy Optimization (GRPO) and Group Sequence Policy Optimization (GSPO) — the policy-gradient algorithms behind DeepSeek-R1 and Qwen3. Full math, the failure mode that motivated GSPO, the MoE story, and a side-by-side comparison.