HuggingFace Daily Papers· Zhiyu Li, Zeyu Zhang, Linyun Liu, Yiwei Bu, Chenyang Xi, Xichong Zhang, Yi Yu, Yu Yu, Zhichen Liu, Yuxiao Yi, Chunyu Li, Haoran Liu, Zhenkai Ding, Le Zhou, Juncheng Zhang, Boyu Chen, Zehao Lin, Guorui Li, Renyu Fu, Ji Li, Youyang Xia, Jiajun Shen, Harvey Li, Jingsong Zhou, Helan Hu, Tong Shen, Tianxiao Xu, Chenye Han, Weijie Li, Zhongquan Zhou, Hongming Xu, Yuekeng Li, Erenkai Zhu, Peng Yu, Wenhao Li, Jingyi Kang, Xixuan Hao, Xuzhou Zhu, Can Chen, Jiawei Liu, Chen Jiang, Tao Jiang, Fangwei Xiang, Zepeng Yao, Kai Chen, Guang Yang, Mingfei Lu, Chunhui Li, Zhengxuan Jiang, Bo Tang, Shiyu Zhan, Yihang Sun, Jie Chu, Wenjun Xiong, Zhenxiang Hua, Chen Lin, Detong Su, Dongyu Deng, Qiuping Ding, Guofeng Ding, Si Chen, Guohua Wen, Xu Chen, Zhi-Qin John Xu, Ying-Cong Chen, Ningyu Zhang, Haofen Wang, Muning Wen, Haotian Chen, Wentao Zhang, Xuanhe Zhou, Rita Zhang, Junchi Yan, Feiyu Xiong·· 7 天前精选AI 评分65
MemT-1.0：迈向记忆原生进化
MemT-1.0: Towards Memory-Native Evolution
AI 导读
MemT-1.0是一种新型记忆基础模型架构，将记忆内化为模型计算的一部分。该模型采用Gated DeltaNet-2和Mixture-of-Storage技术，在128K上下文长度下实现1.86倍端到端推理加速和66倍持久存储减少，同时保持与检索增强方法相竞争的性能。研究团队发布了MemT-1.0-Nano和MemT-1.0-Flash模型，并通过34B tokens训练数据进行了全面评估。
推荐理由
将记忆内化为模型计算能力，MemT-1.0 在128K上下文下实现1.86倍推理加速和66倍存储减少。
来源：HuggingFace Daily Papers · arxiv.org