AI RESEARCH
Once-for-All Channel Mixers (HYPERTINYPW): Generative Compression for TinyML
arXiv CS.LG
•
ArXi:2603.24916v1 Announce Type: new Deploying neural networks on microcontrollers is constrained by kilobytes of flash and SRAM, where 1x1 pointwise (PW) mixers often dominate memory even after INT8 quantization across vision, audio, and wearable sensing. We present HYPER-TINYPW, a compression-as-generation approach that replaces most d PW weights with generated weights: a shared micro-MLP synthesizes PW kernels once at load time from tiny per-layer codes, caches them, and executes them with standard integer operators.