[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-catastrophic-forgetting":3},{"tag":4,"articles":11,"peer_article_count":35},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"19976ff4-6433-42d3-afcc-da60454d663f","catastrophic forgetting","catastrophic-forgetting",3,"災難性遺忘描述模型在持續學習時，學新任務就快速失去舊知識的現象。它影響安全強化學習、長序列 4D 重建、線上適應與多階段訓練，關鍵在於如何保住既有能力又能吸收新資料。","Catastrophic forgetting is the tendency of a model to lose earlier skills or representations when it learns new tasks. It matters in continual learning, safe RL, long-sequence 4D reconstruction, and online adaptation, where retaining past behavior is as important as fitting new data.",[12,21,28],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"5cf69bca-6c4c-46e0-a4b7-b0a59835c548","prevent-catastrophic-forgetting-llm-fine-tuning-en","How to Prevent Catastrophic Forgetting in LLM Fine-Tuning","Use Anchored Weight Decay to reduce prior-task drift during LLM fine-tuning.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780730282480-iwp2.png","en","2026-06-06T07:17:32.623791+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":17,"image_url":26,"cover_image":26,"language":19,"created_at":27},"9383f93b-9272-4bd3-81b9-1b3e84f4663e","fixing-llm-forgetting-es-fine-tuning-en","Fixing LLM forgetting in ES fine-tuning","This paper shows LLM fine-tuning with evolution strategies can drift, and anchored weight decay can curb it.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780604273180-xa1x.png","2026-06-04T20:17:26.230817+00:00",{"id":29,"slug":30,"title":31,"summary":32,"category":17,"image_url":33,"cover_image":33,"language":19,"created_at":34},"6d5e16bb-336f-4137-8522-f5bd1af9fb87","fast-spatial-memory-elastic-test-time-training-en","Fast Spatial Memory for Long 4D Sequences","A new 4D reconstruction model uses elastic test-time training to reduce forgetting and memory bottlenecks in long-sequence spatial learning.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775714630113-ifls.png","2026-04-09T06:03:35.037362+00:00",4]