无归一化Transformer:用Dynamic Tanh (DyT)取代层归一化(Layer Normalization, LN)
论文Transformers without Normalization的研究证明了Transformer可以 […]
无归一化Transformer:用Dynamic Tanh (DyT)取代层归一化(Layer Normalization, LN) Read More »
论文Transformers without Normalization的研究证明了Transformer可以 […]
无归一化Transformer:用Dynamic Tanh (DyT)取代层归一化(Layer Normalization, LN) Read More »
论文Learning from Reward-Free Offline Data: A Case for Pl
论文Lossless Compression of Vector IDs for Approximate Ne
采用非对称数字系统(ANS)和波列树(Wavelet Trees)的无损压缩方法,对近似最近邻搜索(ANNS)中的向量ID和图结构进行优化 Read More »
近年来,机器人技术和具身人工智能(AI)领域取得了显著进展,特别是在模仿学习(Imitation Learni
DINO-WM:基于预训练视觉特征,可实现零样本(Zeor-shot)规划的世界模型(World Model ) Read More »
论文MetaMorph: Multimodal Understanding and Generation vi
MetaMorph:实现视觉理解与生成统一的多模态模型 Read More »
论文Large Concept Models: Language Modeling in a Sentence
大型概念模型(Large Concept Models, LCM):在语言与模态无关的嵌入空间中进行概念级推理 Read More »