[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-svd-self-verified-distill-stanford-perplexity":3,"topics-all":31,"news-related-6c9e553d-3029-4867-bc29-ee069d26b934":50},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":24,"published_at":25,"created_at":26,"modified_at":27,"is_published":28,"publish_type":29,"image_url":13,"view_count":30},"6c9e553d-3029-4867-bc29-ee069d26b934","自验证蒸馏：无需外部教师，LLM 如何实现自我进化","LLM后训练阶段通常依赖外部教师模型或工具反馈来提升性能。但斯坦福大学和Perplexity的研究者提出Self-Verified Distillation（SVD），让模型仅凭无标签种子问题，通过自我验证实现持续进化。\n\nSVD的核心是三阶段级联过滤：模型对种子问题生成多个候选答案，通过循环一致性、事实性和正确性三重检验筛选，只有unanimous判断通过的答案才用于训练。这种自洽验证机制inspired by UQ benchmark的多验证器筛选策略，但创新性地将其应用于自训练场景。\n\n在Qwen3上的实验显示：Qwen3-4B在数学（AIME26和HMMT）上提升16.7分、科学（GPQA Diamond和HLE）上提升11.1分、编程（LCBv5和LCBv6）上提升8.3分，且该方法在0.6B到8B等多个规模上均表现出一致性收益。值得注意的是，SVD在测试时仅需一次推理调用，就能超越需要额外测试时计算的基准方法UQ-TTC，在推理成本上更具优势。\n\n这一突破的深层意义在于：LLM的自我改进正从依赖外部知识转向内生循环。当模型能够自主筛选高质量合成数据时，数据枯竭和分布偏移这两大瓶颈将从根本上得到缓解。这也意味着未来模型升级不一定需要更大规模的标注数据或更贵的外部API，自我验证循环将成为新的 scaling 路径。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2605.26132","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"5e628969-6d2a-437f-998a-104e4b16cfb1","ai-progress",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",{"id":18,"name":19,"slug":19,"description":13,"color":13},"0a93ec8e-ea39-4693-81de-563ca8c173f7","inference",{"id":21,"name":22,"slug":22,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",[],"svd-self-verified-distill-stanford-perplexity","2026-05-27T16:05:00Z","2026-05-27T16:07:35.100848Z","2026-08-19T02:08:40.142862Z",true,"agent",198,[32,41],{"slug":33,"tag_slug":33,"title_zh":34,"title_en":35,"intro_zh":36,"intro_en":37,"id":38,"is_active":28,"created_at":39,"modified_at":40},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":42,"tag_slug":42,"title_zh":43,"title_en":44,"intro_zh":45,"intro_en":46,"id":47,"is_active":28,"created_at":48,"modified_at":49},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":51},[52,57,62,67,72,77],{"id":53,"title":54,"news_slug":55,"published_at":56},"3d922c00-afcb-4f1c-a6d5-8f9d6c10c642","从 Kimi Linear 到 Kimi K3:MoE 推理效率战里被忽略的架构升级","kimi-k3-latentmoe-kda-attnres-nope","2026-07-30T00:30:00+00:00",{"id":58,"title":59,"news_slug":60,"published_at":61},"f2b0bde3-ebb5-49e5-a418-5ece37639d1b","MIPU\u002FMIPI：把 LLM RL 的「训练—推理失配」从工程噪音重写为优化目标","mipu-mipi-rl-mismatch","2026-07-04T08:00:00+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"5a4c2a98-6ce7-4e51-8348-118be3083afc","ELDR 把 MoE 推理的「延迟最后一公里」拉直:vLLM 实测 TPOT 最多砍 13.9%","eldr-moe-routing","2026-07-03T12:30:00+00:00",{"id":68,"title":69,"news_slug":70,"published_at":71},"cd82f869-d4a7-45b7-95ce-b66051e9d933","BlockPilot：实例自适应策略学习让扩散式投机解码再下一城,Qwen3-4B 上首破 4.20× 加速","blockpilot-instance-adaptive-block","2026-07-01T14:17:29+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"abf22bbb-eccf-46d0-99d6-debe1596f92b","自验证蒸馏：无需外部教师，LLM如何实现自我进化","self-verified-distill-qwen3-16-7pp-math","2026-05-27T19:00:00+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"2ca620f4-a046-4274-925d-f0689123a498","ParaRNN：Apple 让 RNN 重回战场，7B 参数模型训练提速 665 倍","apple-pararnn-7b-rnn-665x-faster-iclr","2026-05-27T13:15:00+00:00"]