[{"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},"8e6e5e5b-c51f-495e-a596-203fb64c71eb","tsallis-loss-reasoning-model-training-zh","Tsallis loss 讓推理模型更快脫困","這篇論文用 Tsallis q-logarithm 搭出一條損失函數光譜，想解決推理模型在冷啟動時卡住的問題。它把 RLVR 和 latent trajectory 的 log-marginal-likelihood 串成可調參的連續體。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777443006073-083j.png","zh","2026-04-29T06:09:37.277494+00:00"]