Shared Phase and Retention Control for Efficient Adaptive Spectral Recurrence
As new evidence arrives, a sequence model must update what it remembers and how memory influences predictions. While Transformers incur computation and cache costs scaling with context length, fixed-state recurrent models offer constant-memory inference. However, linear and spectral recurrences traditionally rely on st...
Wen-Tao Wang, Heng-Yu Zhong, Yun-Han Jiang et al.
· 0 citations