MiCo: End-to-End Mixed Precision Neural Network Co-Exploration Framework for Edge AI
Not on the map. Why?
Abstract (arXiv)
Quantized Neural Networks (QNN) with extremely low-bitwidth data have proven promising in efficient storage and computation on edge devices. To further reduce the accuracy drop while increasing speedup, layer-wise mixed-precision quantization (MPQ) becomes a popular solution. However, existing algorithms for exploring MPQ schemes are limited in flexibility and efficiency. Comprehending the complex impacts of different MPQ schemes on post-training quantization and quantization-aware training results is a challenge for conventional methods. Furthermore, an end-to-end framework for the optimization and deployment of MPQ models is missing in existing work. In this paper, we propose the MiCo framework, a holistic MPQ exploration and deployment framework for edge AI applications. The framework adopts a novel optimization algorithm to search for optimal quantization schemes with the highest accuracies while meeting latency constraints. Hardware-aware latency models are built for different hardware targets to enable fast explorations. After the exploration, the framework enables direct deployment from PyTorch MPQ models to bare-metal C codes, leading to end-to-end speedup with minimal accuracy drops.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 17 of its 30 references that are in the map. First posted on arXiv 13 Aug 2025.
Builds on
17 of 30 references.
References · 17
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
- 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
- 2023TinyStories: How Small Can Language Models Be and Still Speak Coherent English?cited by 449
- 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 443
- 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 269
- 2018CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUscited by 121
- 2017Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networkscited by 109
- 2020Bayesian Bits: Unifying Quantization and Pruningcited by 94
- 2020DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUscited by 58
- 2021Stronger NAS with Weaker Predictorscited by 28
- 2022SDQ: Stochastic Differentiable Quantization with Mixed Precisioncited by 28
5 more
- 2020A Mixed-Precision RISC-V Processor for Extreme-Edge DNN Inferencecited by 13
- 2023GP-NAS-ensemble: a model for NAS Performance Predictioncited by 7
- 2024Mixed-precision Neural Networks on RISC-V Cores: ISA extensions for Multi-Pumped Soft SIMD Operationscited by 5
- 2023BOMP-NAS: Bayesian Optimization Mixed Precision NAScited by 4
- 2024A Scalable RISC-V Vector Processor Enabling Efficient Multi-Precision DNN Inferencecited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2023Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge
- 2025InfoQ: Mixed-Precision Quantization via Global Information Flow
- 2022AMED: Automatic Mixed-Precision Quantization for Edge Devices
- 2022Edge Inference with Fully Differentiable Quantized Mixed Precision Neural Networks
- 2025Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization
- 2023On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks
- 2024Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks
- 2023A Practical Mixed Precision Algorithm for Post-Training Quantization