长文本生成迎来新突破：拓元智慧推出 DrDiff ，实现效率与质量双提升
"混合专家" 相关文章
为MoE解绑：全新「专家即服务」推理架构发布，超细粒度扩展锐减37.5%成本
为MoE解绑：全新「专家即服务」推理架构发布，超细粒度扩展锐减37.5%成本
FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
MoGU: Mixture-of-Gaussians with Uncertainty-based Gating for Time Series Forecasting
H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs
Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning
No Title
How to Train Really Large Models on Many GPUs?
你的桌面，就是好莱坞：阿里万相2.2如何掀起视频创作革命
[推广] Kimi k2 online
【深度学习】图解Transformer和MoE的差别
Qwen1.5-MoE: Matching 7B Model Performance with 1/3 Activated Parameters
单卡即可微调大模型！内存占用仅1/8，性能依然拉满 | ICML 2025
原生多模态模型的标度律：重新思考架构选择与训练效率
原生多模态模型的标度律：重新思考架构选择与训练效率
苹果提出原生多模态Scaling Law！早融合+MoE，性能飙升秘密武器
探秘Transformer系列之（21）--- MoE
SYMBOLIC-MOE: Mixture-of-Experts MoE Framework for Adaptive Instance-Level Mixing of Pre-Trained LLM Experts
ByteDance AI Introduces Doubao-1.5-Pro Language Model with a ‘Deep Thinking’ Mode and Matches GPT 4o and Claude 3.5 Sonnet Benchmarks at 50x Cheaper
