[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-rubric":3},{"tag":4,"articles":9},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":8},"38e3102f-67aa-4e83-9c7e-cd7dacdda101","rubric",1,null,[10],{"id":11,"slug":12,"title":13,"summary":14,"category":15,"image_url":16,"cover_image":16,"language":17,"created_at":18},"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。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776233216658-4juh.png","zh","2026-04-15T06:06:32.083225+00:00"]