[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-rubric-rewards":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"26d55019-e635-4c49-a106-3cd63ae4f27e","rubric rewards","rubric-rewards",1,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"b6739170-e7c9-4e98-b99b-a54670dafe59","rubric-based-dpo-visual-preference-tuning-en","Rubric-Based DPO for Visual Preference Tuning","rDPO uses instance-specific rubrics to make visual preference optimization more fine-grained, improving filtering and benchmark results.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776233209863-ruys.png","en","2026-04-15T06:06:32.705067+00:00"]