# Can LLMs Revolutionize the Design of Explainable and Efficient TinyML Models?

arXiv: https://arxiv.org/abs/2504.09685 · HTML: https://mlsanity.com/paper/2504.09685/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 13 Apr 2025.

## Builds on (most cited first, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [The Falcon Series of Open Language Models](https://mlsanity.com/paper/2311.16867/) (2023)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [Large-Scale Evolution of Image Classifiers](https://mlsanity.com/paper/1703.01041/) (2017)
- [Visual Transformers: Token-based Image Representation and Processing for Computer Vision](https://mlsanity.com/paper/2006.03677/) (2020)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [Neural Architecture Search with Bayesian Optimisation and Optimal Transport](https://mlsanity.com/paper/1802.07191/) (2018)
- [The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4](https://mlsanity.com/paper/2311.07361/) (2023)
- [MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning](https://mlsanity.com/paper/2110.15352/) (2021)
- [LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization](https://mlsanity.com/paper/2306.01102/) (2023)
- [Can GPT-4 Perform Neural Architecture Search?](https://mlsanity.com/paper/2304.10970/) (2023)
- [Tiny Machine Learning: Progress and Futures](https://mlsanity.com/paper/2403.19076/) (2024)

## Built on by (most cited first, 5 of 5)

- [SEAL: Searching Expandable Architectures for Incremental Learning](https://mlsanity.com/paper/2505.10457/) (2025)
- [Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions](https://mlsanity.com/paper/2508.08352/) (2025)
- [HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Search](https://mlsanity.com/paper/2605.04103/) (2026)
- [FTerViT: Fully Ternary Vision Transformer](https://mlsanity.com/paper/2605.21171/) (2026)
- [Human-Centered Explainable AI for TinyML Edge Devices: A Pareto-Based Selection Framework with LLM-Guided Design](https://mlsanity.com/paper/2608.07091/) (2026)

## Abstract (arXiv)

This paper introduces a novel framework for designing efficient neural network architectures specifically tailored to tiny machine learning (TinyML) platforms. By leveraging large language models (LLMs) for neural architecture search (NAS), a vision transformer (ViT)-based knowledge distillation (KD) strategy, and an explainability module, the approach strikes an optimal balance between accuracy, computational efficiency, and memory usage. The LLM-guided search explores a hierarchical search space, refining candidate architectures through Pareto optimization based on accuracy, multiply-accumulate operations (MACs), and memory metrics. The best-performing architectures are further fine-tuned using logits-based KD with a pre-trained ViT-B/16 model, which enhances generalization without increasing model size. Evaluated on the CIFAR-100 dataset and deployed on an STM32H7 microcontroller (MCU), the three proposed models, LMaNet-Elite, LMaNet-Core, and QwNet-Core, achieve accuracy scores of 74.50%, 74.20% and 73.00%, respectively. All three models surpass current state-of-the-art (SOTA) models, such as MCUNet-in3/in4 (69.62% / 72.86%) and XiNet (72.27%), while maintaining a low computational cost of less than 100 million MACs and adhering to the stringent 320 KB static random-access memory (SRAM) constraint. These results demonstrate the efficiency and performance of the proposed framework for TinyML platforms, underscoring the potential of combining LLM-driven search, Pareto optimization, KD, and explainability to develop accurate, efficient, and interpretable models. This approach opens new possibilities in NAS, enabling the design of efficient architectures specifically suited for TinyML.