[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-negative-samples":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"6217d5d2-1a3a-48db-a754-e67c777db05d","negative samples","negative-samples",1,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"d1bbd868-15d4-459c-9e2b-2626c779b4ef","prerl-training-llms-in-pre-train-space-en","PreRL: Training LLMs in pre-train space","PreRL shifts reinforcement learning from P(y|x) to P(y), using reward-driven updates in pre-train space to improve reasoning and exploration.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776319621187-aig1.png","en","2026-04-16T06:06:38.24406+00:00"]