[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-a16a4f36-cb00-4f14-a394-80d49075a323":3},{"id":4,"title":5,"summary":6,"original_url":7,"source_id":8,"tags":9,"published_at":23,"created_at":24,"modified_at":25,"is_published":26,"publish_type":27,"image_url":13,"view_count":28},"a16a4f36-cb00-4f14-a394-80d49075a323","上海AI Lab 发布 Intern-S2-Preview-397B：把「记忆」与「思考」拆开，397B 跑出万亿模型效果","WAIC 2026 开幕当天，上海人工智能实验室发布书生系列新成员 Intern-S2-Preview-397B。这不是又一份参数堆料，而是一次底座架构级转向——放弃「一切都在 Transformer 里」的传统路径，把「知识承载」与「推理计算」拆成两条独立但可协同的引擎。\n\n新架构核心是一对组件：**Memory Decoder** 把专业知识做成可插拔外部记忆模块，按需挂载到基座；**Mobius** 是全新推理主干，通过反向残差连接让深层隐状态访问浅层知识，用动态隐空间推理替代 Token。结果相当硬：在分子设计、材料结构生成等科学任务上，397B 的 Intern-S2-Preview 追平了实验室此前的万亿参数模型，端到端推理效率提升约 4 倍。\n\n配套 **InternBootcamp** 把电路设计、金融建模等真实任务变成「行动—反馈」式交互场景，让模型在试错中内化领域逻辑；「书生·端砚」已落地生命科学、关键材料、半导体、核聚变、量子、地球气象六大领域。当参数扩张撞上算力与能耗天花板，「记忆—推理解耦 + 任务级 RL」给了科学智能体一条不靠纯堆参数也能往前走的样本。","https:\u002F\u002Fwww.qbitai.com\u002F2026\u002F07\u002F452942.html","3bd971a8-3897-43d9-84ac-43879efd2f94",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"7ac06d8e-b074-4147-abfc-ffaa4c6b8744","ai-efficiency",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"a8002d98-9df1-4ab9-94d4-a7625af634c4","china-ai",{"id":18,"name":19,"slug":19,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",{"id":21,"name":22,"slug":22,"description":13,"color":13},"7e89b5cc-57db-4f37-bc6d-28919a73931c","model-release","2026-07-18T02:00:00Z","2026-07-18T02:16:57.341954Z","2026-07-18T02:16:57.341963Z",true,"agent",5]