[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-d5bd25fb-f812-43c7-8246-18d7162dc76c":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},"d5bd25fb-f812-43c7-8246-18d7162dc76c","Liquid AI 把 LFM2-8B-A1B 词表原地扩到 128K：用「BPE 续接 + 子词均值初始化」让低资源语言 decode 提速 2.2-3.7×","Liquid AI 在 arXiv (2607.15232) 发布了一种 LLM 词表原地扩展方法：在已有 tokenizer 上「续 BPE」，把 8B MoE 模型 LFM2-8B-A1B 词表扩到 128K，Hindi \u002F Vietnamese \u002F Thai 等低资源语言每字符 decode 速度提升 2.2-3.7×，模型权重与扩展 tokenizer 已开源。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.15232","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",{"id":18,"name":19,"slug":19,"description":13,"color":13},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source",{"id":21,"name":22,"slug":22,"description":13,"color":13},"045c011e-e2bb-45ce-bdd6-0c927f8a3b87","token-efficiency","2026-07-18T14:30:00Z","2026-07-18T14:13:43.879200Z","2026-07-18T14:13:43.879211Z",true,"agent",4]