中国科学院计算技术研究所机构知识库

浏览/检索结果: 共3条，第1-3条

帮助

已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择期刊影响因子升序期刊影响因子降序题名升序题名降序提交时间升序提交时间降序WOS被引频次升序WOS被引频次降序发表日期升序发表日期降序作者升序作者降序
	Low-Latency PIM Accelerator for Edge LLM Inference 期刊论文 IEEE COMPUTER ARCHITECTURE LETTERS, 2025, 卷号: 24, 期号: 2, 页码: 321-324 作者:  Wang, Xinyu;  Sun, Xiaotian;  Li, Wanqian;  Min, Feng;  Zhang, Xiaoyu;  Zhang, Xinjiang;  Han, Yinhe;  Chen, Xiaoming 收藏  |  浏览/下载：9/0  |  提交时间：2025/12/03 Random access memory  Low latency communication  Engines  Bandwidth  Vectors  Registers  Quantization (signal)  Energy efficiency  Hardware  Computational modeling  Large language model inference  processing-in-memory  edge accelerator
	KG-EGV: A Framework for Question Answering with Integrated Knowledge Graphs and Large Language Models 期刊论文 ELECTRONICS, 2024, 卷号: 13, 期号: 23, 页码: 23 作者:  Hou, Kun;  Li, Jingyuan;  Liu, Yingying;  Sun, Shiqi;  Zhang, Haoliang;  Jiang, Haiyang 收藏  |  浏览/下载：22/0  |  提交时间：2025/06/25 knowledge graph  large language model  question answering  evidence retrieval  multi-role reasoning  answer verification  ODQA  graph-based inference
	Introspection unit in memory network: Learning to generalize inference in OOV scenarios 期刊论文 NEUROCOMPUTING, 2020, 卷号: 379, 页码: 30-40 作者:  Yang, Qichuan;  He, Zhiqiang;  Zhan, Zhiqiang;  Zhang, Yang;  Li, Rang;  Hu, Changjian 收藏  |  浏览/下载：86/0  |  提交时间：2020/12/10 Memory network  Out of vocabulary  Introspection unit  Language inference