[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-generalization":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":9},"df98642b-f381-4474-a0c8-a6c4c45ff29f","generalization",3,"泛化描述模型在未見資料、不同分佈或更長推理條件下仍能維持表現的能力。這個主題常連到邊界穩定性、Hessian 光譜、訓練動態，以及 LLM 在換地圖、拉長序列時的失效模式。","Generalization is the ability of a model to keep working on unseen data, shifted distributions, or longer reasoning paths. Here it connects training stability, Hessian-spectrum sharpness, and LLM failures on new maps or longer sequence lengths.",[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"7fb8a4e6-2e67-41e8-8631-a9b482935aea","edge-of-stability-generalization-en","Generalization at the Edge of Stability: 1 Paper on Why","A new paper links chaotic, high-learning-rate training to generalization via a “sharpness dimension” built from the Hessian spectrum.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776837837398-ubbj.png","en","2026-04-22T06:03:36.883776+00:00"]