华为盘古首次露出，昇腾原生72B MoE架构，SuperCLUE千亿内模型并列国内第一
"混合专家模型" 相关文章
The Rise of Mixture-of-Experts: How Sparse AI Models Are Shaping the Future of Machine Learning
消息称DeepSeek R2下月发：成本较GPT降97%、华为芯片性能不输英伟达
Qwen3强势来袭：推理力爆表、语言超百种、智能体协作领先，引领AI开源大模型
消息称DeepSeek R2下月发：成本较GPT降97%、华为芯片性能不输英伟达
Alibaba Qwen Team Just Released Qwen3: The Latest Generation of Large Language Models in Qwen Series, Offering a Comprehensive Suite of Dense and Mixture-of-Experts (MoE) Models
Multimodal Models Don’t Need Late Fusion: Apple Researchers Show Early-Fusion Architectures are more Scalable, Efficient, and Modality-Agnostic
Meta公布MoE架構開發的Llama 4 開源4000億、1090億參數的Maverick
消息称蚂蚁集团采用阿里、华为等国产芯片训练 AI：性能匹敌英伟达 H800，成本降低 20%
Observations About LLM Inference Pricing
DeepSeek开源放大招：FlashMLA让H800算力狂飙！曝光低成本秘笈
月之暗面 Kimi 开源 Moonlight：30 亿 / 160 亿参数混合专家模型
一次推理解决复合问题：基于MoE的大语言模型知识模块可扩展融合推理架构MeteoRA
Lex Fridman 五小时聊 DeepSeek：一文看懂 DeepSeek 的创新与2025 AI 趋势
Autonomy-of-Experts (AoE): A Router-Free Paradigm for Efficient and Adaptive Mixture-of-Experts Models
DeepSeek V3 and the actual cost of training frontier AI models
Noteworthy AI Research Papers of 2024 (Part One)
Researchers from Tsinghua University Propose ReMoE: A Fully Differentiable MoE Architecture with ReLU Routing
中国人工智能进步速度引美媒关注 AI模型将成为新的技术标签
DeepSeek-VL2 AI 视觉模型开源：支持动态分辨率、处理科研图表、解析各种梗图等
