[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-reward-modeling":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"89b4e129-fc9b-4a75-9893-9140fabbfeb5","reward modeling","reward-modeling",1,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"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"]