[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-student-model":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"92333446-0896-4f98-afe3-016c36354c21","student model","student-model",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"b38c56a6-e7f3-45fb-b100-d37e7b3ed417","reinforcement-aware-distillation-llm-reasoning-zh","強化感知蒸餾，想把推理一起學進去","這篇論文提出強化感知知識蒸餾，目標不是只壓縮答案，而是把 LLM 的推理行為一起轉移給學生模型。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780646589500-0me6.png","zh","2026-06-05T08:02:33.908932+00:00"]