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

研究與工具

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. 僅在有益時檢索:用於選擇性檢索增強機器翻譯的代理式強化學習機器翻譯Retrieve What Helps, Only When It Helps: Agentic Reinforcement Learning for Selective Retrieval-Augmented Machine Translation

    arXiv:2610.19528v1 Announce Type: new Abstract: Retrieving external knowledge can improve large language model (LLM) translation by providing supplementary information such as idiom interpretations and terminology. Howe

    論文基準arXiv cs.CL · 10/15 下午12:00 · 當天共 27 則
    展開同日其他 26 則
  2. CUSE:結合反事實引導與在策略自我蒸餾的細粒度多模態遺忘機器翻譯CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation

    arXiv:2610.14763v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can reproduce sensitive, copyrighted, or unsafe information from their training data. Effective unlearning must remove target info

    論文基準arXiv cs.AI · 10/15 下午12:00 · 當天共 33 則
    展開同日其他 32 則