Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets Abstract: Real-wor l d document question
LATE CHUNKING: CONTEXTUAL CHUNK EMBEDDINGS USING LONG-CONTEXT EMBEDDING MODELS Abstract Many use cases require retrieving smaller portions of text, an
论文链接:AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE ViT:把图像看成 patch token 序列,而不是像素网格或卷积特征图,然后直接用标准Transformer Encoder 做全局建