AI 新視界 AI WorldviewAI 新視界 AI Worldview
申請帳號 / 登入

最新動態

來源原文的標題與連結,未經本站改寫;英文標題附機器翻譯。已排除與 AI 無關的條目;主題由本站地端模型自動分類,可能分錯。

  1. 定位、判斷、閱讀:基於知識點索引的開放領域多模態文件問答角色專化工具代理機器翻譯Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QA

    arXiv:2610.13128v1 Announce Type: new Abstract: Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-augmented agents gi

    論文基準arXiv cs.AI · 10/13 下午12:00 · 當天共 36 則
    展開同日其他 35 則
  2. 多串注意力殘差機器翻譯Multi-Stream Attention Residuals

    arXiv:2610.13630v1 Announce Type: new Abstract: Attention Residuals (AttnRes) enables content-dependent retrieval over network depth, which can be viewed as single-stream softmax attention along the depth axis. Inspired

    論文基準arXiv cs.CL · 10/13 下午12:00 · 當天共 24 則
    展開同日其他 23 則