[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-mixture-of-experts":3},{"tag":4,"articles":9,"peer_article_count":76},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":8},"3558c57d-a009-4f0e-bf6a-20cea0b81732","mixture-of-experts",2,null,[10,19,26,33,40,48,55,62,69],{"id":11,"slug":12,"title":13,"summary":14,"category":15,"image_url":16,"cover_image":16,"language":17,"created_at":18},"6288131d-64e3-47ff-aeec-add641c952e2","kimi-long-context-models-moonshot-ai-en","Kimi’s long-context push keeps getting bigger","Moonshot AI’s Kimi chatbot keeps expanding context, agents, and model size, with Kimi K2.5 arriving in January 2026.","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782231491199-wiwi.png","en","2026-06-23T16:17:38.462613+00:00",{"id":20,"slug":21,"title":22,"summary":23,"category":15,"image_url":24,"cover_image":24,"language":17,"created_at":25},"d18e6176-7ba9-4460-8230-425e3aeaeb86","kimi-k27-code-highspeed-mode-skips-benchmarks-en","Kimi K2.7-Code Adds HighSpeed Mode, Skips Benchmarks","Moonshot’s Kimi K2.7-Code adds a faster mode and lower token use, but only Moonshot’s own benchmarks back the claims.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781795890377-d0e8.png","2026-06-18T15:17:41.403224+00:00",{"id":27,"slug":28,"title":29,"summary":30,"category":15,"image_url":31,"cover_image":31,"language":17,"created_at":32},"ccc46975-50d1-4ece-8fd3-c082bf4858ae","self-host-minimax-m3-gpu-cloud-en","Self-host MiniMax M3 on GPU cloud","MiniMax M3 brings 229.9B MoE weights, 1M context, and multimodal output, but it needs serious GPU memory to run.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781716680837-ikof.png","2026-06-17T17:17:35.800599+00:00",{"id":34,"slug":35,"title":36,"summary":37,"category":15,"image_url":38,"cover_image":38,"language":17,"created_at":39},"e7f37851-7b5f-429c-9a71-3e4a2d4b9c70","mimo-v2-flash-openrouter-benchmarks-pricing-en","MiMo-V2-Flash hits top open-source SWE-bench scores","Xiaomi’s MiMo-V2-Flash tops open-source SWE-bench scores while OpenRouter lists it at $0.10\u002F$0.30 per 1M tokens.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781321563162-27yb.png","2026-06-13T03:32:17.731154+00:00",{"id":41,"slug":42,"title":43,"summary":44,"category":45,"image_url":46,"cover_image":46,"language":17,"created_at":47},"21a693ca-7c72-49e6-886e-4d190baa33c1","nvidia-nemotron-3-ultra-open-models-compete-en","NVIDIA Nemotron 3 Ultra proves open models can still compete","Nemotron 3 Ultra shows that open-weight models can still match top rivals while running far faster.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781108276690-iat5.png","2026-06-10T16:17:24.880013+00:00",{"id":49,"slug":50,"title":51,"summary":52,"category":45,"image_url":53,"cover_image":53,"language":17,"created_at":54},"cb4d09b6-0301-417e-8b84-11cd25ff4ae1","handoff-humanoid-control-planner-friendly-en","HANDOFF makes humanoid control more planner-friendly","HANDOFF gives humanoid robots a compact control interface and distills three specialists into one controller.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780726685246-4vq8.png","2026-06-06T06:17:35.816558+00:00",{"id":56,"slug":57,"title":58,"summary":59,"category":45,"image_url":60,"cover_image":60,"language":17,"created_at":61},"1e4ba03d-b371-427a-8d9e-d694f09827b1","unipool-shared-expert-pool-moe-en","UniPool shares MoE experts across layers","UniPool replaces per-layer MoE experts with one shared pool, cutting redundancy and improving validation loss in five LLaMA-scale models.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778221264459-eh59.png","2026-05-08T06:20:40.975202+00:00",{"id":63,"slug":64,"title":65,"summary":66,"category":45,"image_url":67,"cover_image":67,"language":17,"created_at":68},"cdcfe76f-c9bf-44ac-98d9-e9041d414d6c","sebastian-raschka-llm-architecture-gallery-en","Sebastian Raschka’s LLM Architecture Gallery","Raschka’s gallery compares GPT-2, Llama 3, OLMo 2, DeepSeek, and Qwen stacks with exact layer, cache, and attention data.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775121663908-8tcs.png","2026-04-02T07:27:33.848813+00:00",{"id":70,"slug":71,"title":72,"summary":73,"category":15,"image_url":8,"cover_image":74,"language":17,"created_at":75},"d23cd5f6-f875-49f5-b53b-1c5416d13d99","cursor-composer-2-agentic-coding-model-en","Cursor Composer 2 Bets on Agentic Coding","Cursor’s Composer 2 posts 61.3 on CursorBench and 61.7 on Terminal-Bench 2.0, with pricing aimed at high-volume coding teams.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774498610250-zp8n.png","2026-03-28T03:13:06.513673+00:00",4]