[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-knowledge-distillation":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"f1843b78-7dc8-406a-a348-0c1d70c4dae3","knowledge distillation","knowledge-distillation",1,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"37bb5c43-947c-48da-a02c-091da7b99319","reinforcement-aware-distillation-llm-reasoning-en","Reinforcement-aware distillation for LLM reasoning","This paper proposes reinforcement-aware knowledge distillation to improve LLM reasoning, but the abstract provides no benchmark numbers.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780646587562-pbu3.png","en","2026-06-05T08:02:34.575637+00:00"]