[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"topic-en-rubric-based-dpo-for-visual-preference-tuning":3},{"cluster":4,"timeline":16},{"id":5,"slug":6,"title":7,"pinned":8,"status":9,"summary":10,"category":11,"language":12,"created_at":13,"merged_into":14,"article_count":15,"first_seen_at":13,"last_updated_at":13},"9aed1e69-89ed-4cf3-9417-89eef0a58358","rubric-based-dpo-for-visual-preference-tuning","Rubric-Based DPO for Visual Preference Tuning",false,"active","rDPO uses instance-specific rubrics to make visual preference optimization more fine-grained, improving filtering and benchmark results.","research","en","2026-07-05T09:03:58.184362+00:00",null,1,[17],{"id":18,"slug":19,"title":7,"summary":10,"category":11,"image_url":20,"cover_image":20,"published_at":21,"is_canonical_seed":22},"b6739170-e7c9-4e98-b99b-a54670dafe59","rubric-based-dpo-visual-preference-tuning-en","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776233209863-ruys.png","2026-04-15T06:06:32.614+00:00",true]