[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-tsallis-loss":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"1c93dfe6-8377-4080-b290-22f0e1a4df6d","Tsallis loss","tsallis-loss",2,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"dbcae3bd-5f14-4baf-9604-0011f7382732","tsallis-loss-reasoning-model-training-en","Tsallis loss for faster reasoning-model training","A Tsallis-loss continuum may help reasoning models escape cold-start stalls faster than RLVR, with tradeoffs between speed, noise, and stability.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777443011556-1zy3.png","en","2026-04-29T06:09:38.777932+00:00"]