6 citations · 6 across the 4 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.AR2026
ShatterQuant: Breaking Uniform Precision with Block-Wise Mixed-Precision on a Systolic Transformer Hardware Accelerator
Mikolaj Walczak, Edward Humes, Chao Fang +2
Due to limited support for intra-tensor heterogeneous precision in conventional accelerators, neural network quantization remains largely restricted to per-tensor precision assignm…
cs.CV2026
SatReg: Regression-based Neural Architecture Search for Lightweight Satellite Image Segmentation
Edward Humes, Tinoosh Mohsenin
As Earth-observation workloads move toward onboard and edge processing, remote-sensing segmentation models must operate under tight latency and energy constraints. We present SatRe…