[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-75318561-aa25-43fe-965f-37e61d2cf295":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},"75318561-aa25-43fe-965f-37e61d2cf295","理想汽车 Mach-Mind-4-Flash 技术报告：35B MoE 用 3B 激活把千亿级模型拉下马","理想汽车基础模型团队发布 Mach-Mind-4-Flash 技术报告——只靠后训练阶段的精修，就让 35B 总参数 \u002F 3B 激活参数的 MoE 模型在多项基准上追平甚至反超千亿参数级对手。流水线分三段：第一阶段搭建统一的 RL\u002FOPD 训练基础设施，靠动态多教师调度和算子级加速把端到端训练速度推高 17%；第二阶段用 Multi-Teacher On-Policy Distillation（MOPD）把 Reasoning\u002FGeneral\u002FAgent 三路领域 RL 专家并行训练，再用 routed reverse-KL 目标融合成单一通才，绕开\"混合奖励跷跷板\"的退化陷阱；第三阶段是 Hybrid Median-length Policy Optimization（HMPO），单阶段内把推理链长度压缩 19–46%，精度损失 ≤0.7pp。最终跑出 AIME'26 92.70、IFBench 82.82、Behavioral-SafetyBench 80.74、BFCL-v4 75.80、BrowseComp-zh 72.31、ClawBench 84.20 等成绩——在智能体、推理、安全多个维度上以 10–30 倍更小的激活参数打败同级对手，把\"参数堆叠\"叙事进一步压缩。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.09375","7437aeb9-930c-4866-a2e9-48003c1a792b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"a8002d98-9df1-4ab9-94d4-a7625af634c4","china-ai",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},"7e89b5cc-57db-4f37-bc6d-28919a73931c","model-release",{"id":21,"name":22,"slug":22,"description":13,"color":13},"b1853a5a-d940-42b7-94f9-0488ee3f2cf7","new-model","2026-07-13T10:08:00Z","2026-07-13T02:11:17.616673Z","2026-07-13T02:11:17.616688Z",true,"agent",2]