[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-continual-learning":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"14db0e77-3264-43f8-841f-5c1c7e45360b","continual learning","continual-learning",7,"持續學習研究關注模型在資料流、任務切分與環境變動下，如何保留舊知識並吸收新資訊。它牽涉災難性遺忘、測試時更新、安全控制與長期部署，對串流系統、RL 與 LLM 適應都很關鍵。","Continual learning studies how models retain prior knowledge while adapting to new data in streams, task splits, and changing environments. It connects to catastrophic forgetting, test-time updates, safe RL, and long-running deployment for systems that must keep learning.",[12,21,28,35],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"13b6551e-f990-4e6b-aa8d-e410b134df43","task-boundaries-can-skew-continual-learning-results-en","Task boundaries can skew continual learning results","A new paper shows that how you split a stream into tasks can change continual learning results, even when the data, model, and budget stay fixed.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777010808102-k8tq.png","en","2026-04-24T06:06:31.283203+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":17,"image_url":26,"cover_image":26,"language":19,"created_at":27},"89d74343-03a7-4325-88e0-14029dab320d","safe-continual-rl-changing-environments-en","Safe Continual RL for Changing Real-World Systems","This paper studies how to keep RL controllers safe while they adapt to non-stationary systems—and shows why existing methods still fall short.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776838195882-6v8v.png","2026-04-22T06:09:33.432376+00:00",{"id":29,"slug":30,"title":31,"summary":32,"category":17,"image_url":33,"cover_image":33,"language":19,"created_at":34},"b65aeb57-d1b7-4cdd-adb9-464b8cfbfe0a","in-place-ttt-llms-adapt-at-inference-en","In-Place TTT Lets LLMs Adapt at Inference","A new test-time training setup lets LLMs update fast weights in place, aiming for better long-context adaptation without full retraining.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775628426736-0dm6.png","2026-04-08T06:06:33.249426+00:00",{"id":36,"slug":37,"title":38,"summary":39,"category":40,"image_url":41,"cover_image":41,"language":19,"created_at":42},"15c2f00f-4c48-4580-a13e-74626eb520f7","five-ai-infra-frontiers-bessemer-2026-en","Five AI Infra Frontiers Bessemer Expects for 2026","Bessemer’s 2026 AI infra roadmap points to memory, continual learning, RL, inference, and world models as the next big build areas.","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775164380914-xfye.png","2026-04-02T21:12:40.223864+00:00"]