Interdomain Attention: Beyond Token-Level Key-Value Memory
Softmax attention-based transformers and recurrent memory-based models (e.g., state space models (SSMs)) form the foundation of modern sequence models. Hybrid architectures aim to combine the expressivity from attention and the computational efficiency from recurrent memory, yet so far common…
By Naoki Kiyohara, Harrison Bo Hua Zhu, Riccardo El Hassanin, Zhuo Sun, Wenlong Chen, Samir Bhatt, Yingzhen LiarXiv - stat.ML
Read the full story
Originally published by arXiv - stat.ML on Oct 22, 2026.
Comments
Sign in to join the discussion.