Skip to content
conftrace_

bit-shift operation

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

model compression (3) additive operation (1) fine-grained pruning (1) power-of-two quantization (1) dynamic quantization (1) sparse convolutional neural network (1) integer arithmetic (1) mixed-precision quantization (1) weight pruning (1) efficient computing (1)

Papers

DQT: Dynamic Quantization Training via Dequantization-Free Nested Integer Arithmetic AAAI 2026 ShiftAddNet: A Hardware-Inspired Deep Network NeurIPS 2020 Focused Quantization for Sparse CNNs NeurIPS 2019