热点
"OctoThinker" 相关文章
Shanghai Jiao Tong Researchers Propose OctoThinker for Reinforcement Learning-Scalable LLM Development
MarkTechPost@AI 2025-07-03T01:05:53.000000Z
RL不只Qwen玩得转！“中期训练”让Llama一夜进化，OctoThinker横空出世
PaperWeekly 2025-07-01T12:03:48.000000Z