[{"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},"05451495-1e4d-4e70-855f-f92e68a1a699","how-to-build-vintage-llm-testbed-5-steps-en","How to Build a Vintage LLM Testbed in 5 Steps","Build a 1930-cutoff LLM testbed to study historical reasoning and contamination-free generalization.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777945253760-2l44.png","en","2026-05-05T01:40:33.098256+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":16,"image_url":25,"cover_image":25,"language":18,"created_at":26},"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.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776233209863-ruys.png","2026-04-15T06:06:32.705067+00:00"]