# CRIMP: Compact & Reliable DNN Inference on In-Memory Processing via Crossbar-Aligned Compression and Non-ideality Adaptation

arXiv: https://arxiv.org/abs/2607.08015 · HTML: https://mlsanity.com/paper/2607.08015/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 48 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Fast Certified Robust Training with Short Warmup](https://mlsanity.com/paper/2103.17268/) (2021)
- [Improving Noise Tolerance of Mixed-Signal Neural Networks](https://mlsanity.com/paper/1904.01705/) (2019)
- [CorrectNet: Robustness Enhancement of Analog In-Memory Computing for Neural Networks by Error Suppression and Compensation](https://mlsanity.com/paper/2211.14917/) (2022)
- [Crossbar-aware neural network pruning](https://mlsanity.com/paper/1807.10816/) (2018)
- [Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware](https://mlsanity.com/paper/2607.06915/) (2026)
- [Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization](https://mlsanity.com/paper/2607.06922/) (2026)

## Abstract (arXiv)

Crossbar-based In-Memory Processing (IMP) accelerators achieve high-speed, low-power computing for deep neural networks (DNNs), but face three obstacles. First, floating-point (FP) arithmetic is incompatible with crossbars, and existing quantization schemes still require FP processors for scaling factors, incurring hardware overhead. Second, redundant DNN parameters occupy too many crossbars, and current IMP-aware pruning methods require data aligning across crossbars, introducing significant memory and computing overhead. Third, non-ideal crossbar behaviors such as write variations degrade the accuracy of deployed models, and existing compensation methods add substantial overhead. In this paper, we address all three problems within a single training process. We reuse bit-shift units in crossbars to approximately multiply scaling factors, avoiding FP processors. We apply kernel-group pruning and crossbar pruning to remove the hardware units needed for data aligning. We adopt runtime-aware non-ideality adaptation to relieve the impact of device non-ideality from the training stage by exploiting crossbar features. Integrating these three optimizations into one comprehensive learning framework reduces training overhead and improves accuracy. Experiments show that our quantization incurs a negligible accuracy drop, and our pruning achieves higher sparsity and accuracy than state-of-the-art methods. Our framework produces integer-only, pruned, and reliable VGG-16 and ResNet-56 models for CIFAR-10 on IMP accelerators, with accuracy drops of only 2.19% and 1.26%, respectively, without hardware overhead.