Bilinear Input Modulation for Mamba: Koopman Bilinear Forms for Memory Retention and Multiplicative Computation

April 19, 2026 ยท Grace Period ยท + Add venue

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Hiroki Fujii, Masaki Yamakita arXiv ID 2604.17221 Category eess.SY: Systems & Control (EE) Cross-listed cs.LG, math.DS Citations 0
Abstract
Selective State Space Models (SSMs), notably Mamba, employ diagonal state transitions that limit both memory retention and bilinear computational capacity. We propose a factorized bilinear input modulation that augments the SSM with a state-input product, interpretable as a finite-dimensional Koopman bilinear form. After introducing a shared state across channels (Coupled SSM), the modulation admits two implementations. Coupled Bilinear Input Modulation (Coupled-BIM) retains the full bilinear product at the cost of sequential computation, while Coupled Gated Modulation (Coupled-GM) linearizes it into a gate modulation that is compatible with the parallel scan. Experiments on a multiple input-delay pendulum (memory retention) and NARMA-10 (bilinear computation) reveal a clear dissociation. Coupled-GM substantially improves memory retention but not bilinear computation, while Coupled-BIM improves both. A pathway ablation confirms that the two downstream routes of the bilinear signal serve complementary roles. The improvement is statistically robust, with Coupled-BIM consistently outperforming all other variants on bilinear computation. Furthermore, only Coupled-BIM benefits from increasing the SSM state dimension, while coupling or gate modulation alone show no improvement, establishing the bilin-ear mechanism as uniquely capable of exploiting larger state spaces.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Systems & Control (EE)