AI RESEARCH
mGRADE: Minimal Recurrent Gating Meets Delay Convolutions for Lightweight Sequence Modeling
arXiv CS.LG
•
ArXi:2507.01829v2 Announce Type: replace Multi-timescale sequence modeling relies on capturing both local fast dynamics and global slow context; yet, maintaining these capabilities under the strict memory constraints common to edge devices remains an open challenge. Current State-of-the-Art models with constant memory footprints trade off long-range selectivity and high-precision modeling of fast dynamics. To overcome this trade-off within a fixed memory budget, we propose mGRADE (minimally Gated Recurrent Architecture with Delay Embedding), a hybrid-memory system that.