LooM: Loop-Invariant Memory for Causal Encoder-Decoder Language Models

Lele Yang, Muxi Diao, Zhonghao Yan, Jiankang Chen, Bin Wen, Tingting Gao, Wentao Zhang, Kongming Liang, Zhanyu Ma, Weiran Xu

Reuses a fixed memory bank while decoder layers repeat their reads. Each token writes its local cache once, allowing different recurrent-depth budgets without increasing the stored cache size.

First public: November 4, 2026 · Added to this list: November 9, 2026