2 papers were presented at this group meeting.
| Paper and research focus | Presenter | Publication | Resources |
|---|---|---|---|
Noise-powered Multi-modal Knowledge Graph Representation FrameworkSNAG 方法借助引入噪声增强多模态知识图谱表示能力,基于 Transformer 架构与任务特定训练目标,有效支持 MKGC 和 MMEA 任务,提升了模型鲁棒性,为多模态知识图谱表示学习提供新思路。 | International Conference on Computational Linguistics 2025-01 | Not available | |
Towards conversational diagnostic artificial intelligence谷歌发布了基于大语言模型的医疗 AI 模型 – AMIE,它不仅能独立完成疑难病症的鉴别诊断,还能在“对话中”完成问诊、共情、决策,甚至在严格双盲试验中被真实患者与医生一致评为优于人类医生。 | Nature 2025-04 | Not available |