KAP方法巧妙填补了大模型知识选择与运行时耗能之间的空白，让知识密集型推理更高效。
arXiv:2607.24260v1 Announce Type: new Abstract: Modern LLM systems increasingly rely on knowledge-selection processes that produce high-value structur…
如何从非结构化数据中发现因果？本文提出利用领域知识增强因果发现的新方法，突破传统局限。
arXiv:2607.09348v1 Announce Type: new Abstract: Causal discovery from unstructured data is a challenging yet underexplored task in high-expertise doma…
用LLM给高危驾驶场景打标注，构建知识增强数据集，为自动驾驶安全研究提供高价值资源。
arXiv:2607.07103v1 Announce Type: new Abstract: Safe autonomous driving requires both rapid responses to common high-risk events and deeper reasoning …
免训练实体识别新方法，先定位再排序，显著提升知识型视觉问答表现
arXiv:2606.23881v1 Announce Type: new Abstract: Knowledge-Based Visual Question Answering (KB-VQA) requires grounding visual queries to external knowl…
层次化多模态检索为新闻图片生成知识增强描述，解决传统方法缺乏上下文细节的痛点。
arXiv:2606.18553v1 Announce Type: new Abstract: Traditional image captioning methods often struggle to generate comprehensive, context-rich descriptio…
融合外部知识与视觉感知的KG-ViP框架，让多模态大模型在视觉问答中更精准、更可解释。
arXiv:2601.11632v3 Announce Type: replace Abstract: Multi-modal Large Language Models (MLLMs) for Visual Question Answering (VQA) often suffer from du…
提出KAME双架构协同，实时语音对话AI兼顾流畅交互与深度知识，突破现有模型语义瓶颈
arXiv:2510.02327v2 Announce Type: replace-cross Abstract: Real-time speech-to-speech (S2S) models excel at generating natural, low-latency conversatio…
面向法律领域的细粒度声明级RAG基准，评估模型事实检索与推理能力的新方法。
arXiv:2605.21071v1 Announce Type: new Abstract: The rapid progress of large language models (LLMs) is shifting semantic search toward a question-answe…
全面梳理RAG在NLP领域的研究进展，涵盖方法、应用与未来方向，适合研究人员和从业者快速了解前沿。
arXiv:2407.13193v4 Announce Type: replace Abstract: Large language models (LLMs) have achieved strong empirical performance in various fields, benefit…