mlsanityData to 14 Oct 2026

Sensitivity-Aware Mixed-Precision Quantization for ReRAM-based Computing-in-Memory

arXiv 2512.19445 ↗First posted 22 Dec 2025cs.AR cs.ETcited by 0

Not on the map. Why?

Abstract (arXiv)

Compute-In-Memory (CIM) systems, particularly those utilizing ReRAM and memristive technologies, offer a promising path toward energy-efficient neural network computation. However, conventional quantization and compression techniques often fail to fully optimize performance and efficiency in these architectures. In this work, we present a structured quantization method that combines sensitivity analysis with mixed-precision strategies to enhance weight storage and computational performance on ReRAM-based CIM systems. Our approach improves ReRAM Crossbar utilization, significantly reducing power consumption, latency, and computational load, while maintaining high accuracy. Experimental results show 86.33% accuracy at 70% compression, alongside a 40% reduction in power consumption, demonstrating the method's effectiveness for power-constrained applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 5 of its 32 references that are in the map. First posted on arXiv 22 Dec 2025.

Builds on

5 of 32 references.

References · 5

  1. 2017Visualizing the Loss Landscape of Neural Netscited by 1,130
  2. 2019HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networkscited by 261
  3. 2017Fisher-Rao Metric, Geometry, and Complexity of Neural Networkscited by 100
  4. 2018Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approachcited by 91
  5. 2021Hessian-Aware Pruning and Optimal Neural Implantcited by 45

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Block-Wise Mixed-Precision Quantization: Enabling High Efficiency for Practical ReRAM-based DNN Accelerators
  2. 2023ReDy: A Novel ReRAM-centric Dynamic Quantization Approach for Energy-efficient CNN Inference
  3. 2021PR-CIM: a Variation-Aware Binary-Neural-Network Framework for Process-Resilient Computation-in-memory
  4. 2026NANQ: Noise-Floor-Aware Mixed-Precision Non-Uniform Quantization for Analog Compute-in-Memory
  5. 2024Algorithm-hardware co-design for Energy-Efficient A/D conversion in ReRAM-based accelerators
  6. 2025A Hybrid-Domain Floating-Point Compute-in-Memory Architecture for Efficient Acceleration of High-Precision Deep Neural Networks ↗
  7. 2023On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks
  8. 2025QS4D: Quantization-aware training for efficient hardware deployment of structured state-space sequential models