4 papers
Right In-Place (RiP) Convolution: A Simple, General, and Near-Optimal Strategy for Memory-Efficient CNN Inference
Opegbemi Matthias Busoye, Tolulope Matthew Busoye, Eghonghon-aye Eigbe
Activation memory, not compute, limits CNN inference on constrained hardware such as microcontrollers. Direct in-place convolution removes the dual-buffer cost, but the memory-opti…
A Tilted Bowl Is Not a Slippery Slope: Compressing Looped Models
Steven Kolawole, Pearse Jim, Opegbemi M. Busoye +2
Looped models reason by applying the same block of weights many times, so compressing that block saves memory traffic on every loop. Compressed looped models, however, often collap…
Deep Microcompression: Structured Pruning and Bit-packed Quantization for Microcontrollers
Opegbemi Matthias Busoye, Tolulope Matthew Busoye, Eghonghon-aye Eigbe
This paper introduces Deep Microcompression (DMC), a hardware-aware pipeline for deep learning inference on bare-metal microcontrollers. DMC integrates structured pruning, quantiza…
What Survives When You Compress a Recursive Reasoner for the Edge?
Pearse Jim, Steven Kolawole, Opegbemi Matthias Busoye +2
Recursive reasoning models solve hard structured tasks with a few million parameters by iterating a latent state, but deploying them on edge hardware means compressing them -- and…