MemT 1.0 Opens the Source for Memory-Native AI Models
MemTensor released and open-sourced MemT 1.0, a family of memory-native foundation models comprising MemT-1.0-Nano and MemT-1.0-Flash. The architecture uses Gated DeltaNet-2 and Mixture-of-Storage to maintain updating internal memory states that participate in generation, with author-reported gains in long-history inference efficiency, storage reduction, and agentic task success. External text-memory systems still retain an advantage for precise recall from long histories, according to the reports.
MemT 1.0 directly integrates continuously updated memory into model computation rather than relying only on external retrieval, offering an open-source approach to reducing long-history KV-cache costs and reusing procedural experience in agent tasks.
Computer Science > Computation and Language
arXiv:2610.26825 (cs)
[Submitted on 19 Oct 2026]
Title:MemT-1.0: Towards Memory-Native Evolution
Authors: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
View a PDF of the paper titled MemT-1.0: Towards Memory-Native Evolution, by Zhiyu Li and 73 other authors
Some source content is omitted. Continue reading on the original site.
#MemTensor#MemT-1.0-Nano#MemT-1.0-Flash#Gated DeltaNet-2#Mixture-of-Storage#Qwen3.6-35B-A3B#DeepSeek-V4-Flash#MemOS