文章预览
LG - 机器学习 CV - 计算机视觉 CL - 计算与语言 RO - 机器人 1、[LG] What Machine Learning Tells Us About the Mathematical Structure of Concepts 2、[CL] Nexus:Specialization meets Adaptability for Efficiently Training Mixture of Experts 3、[CV] Eagle:Exploring The Design Space for Multimodal LLMs with Mixture of Encoders 4、[CL] ReMamba:Equip Mamba with Effective Long-Sequence Modeling 5、[CL] Dolphin:Long Context as a New Modality for Energy-Efficient On-Device Language Models 摘要:机器学习告诉我们概念的数学结构、专门化与适应性相结合高效训练混合专家、利用编码器混合探索多模态LLM的设计空间、为 Mamba 配备有效的长序列建模能力、长上下文作为高能效设备端语言模型的新模态 1、[LG] What Machine Learning Tells Us About the Mathematical Structure of Concepts J Otsuka [Kyoto University] 机器学习告诉我们概念的数学结构 要点: 本文探讨了哲学、认知科学和机
………………………………