[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-dpo":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"f7281a13-34a6-4489-b848-e4b120c75959","DPO","dpo",2,null,[11,20],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"72828ff9-cbfb-4e10-81b2-9c4c9544b7f1","how-to-build-vintage-llm-testbed-5-steps-zh","5 步建出 1930 截止 LLM 測試台","用 5 個步驟建立一個 1930 截止的 LLM 測試台，驗證歷史推理與無污染泛化。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777945255070-tzh6.png","zh","2026-05-05T01:40:31.318037+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":16,"image_url":25,"cover_image":25,"language":18,"created_at":26},"d3ac3e85-c296-4015-94f0-559222351ea3","rubric-based-dpo-visual-preference-tuning-zh","用 rubric 讓視覺偏好訓練更精準","rDPO 用每個圖文任務的專屬 rubric 取代粗粒度偏好訊號，讓視覺偏好最佳化更細緻，並在過濾與 benchmark 上帶來提升。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776233216658-4juh.png","2026-04-15T06:06:32.083225+00:00"]