A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on TinyML — the intersection of machine learning and ultra-low-power embedded systems. This repository is crafted to serve as a comprehensive, well-organized knowledge base for researchers, engineers, and developers working on deploying intelligent models on edge devices with limited compute, memory, and power.
To keep pace with the fast-moving field, our repository is automatically updated with the latest TinyML-related research papers from arXiv. This ensures that users always have access to the most recent innovations, techniques, and breakthroughs in the TinyML ecosystem.
Note
📢 Announcement: Our paper from AIT Lab is now published on ACM Computing Surveys!
Title: From Tiny Machine Learning to Tiny Deep Learning: A Survey
If you find this paper interesting, please consider citing our work. Thank you for your support! Also, check out our paper story on AIT Lab Website.
@article{somvanshi2025tiny,
title={From tiny machine learning to tiny deep learning: A survey},
author={Somvanshi, Shriyank and Islam, Md Monzurul and Chhetri, Gaurab and Chakraborty, Rohit and Mimi, Mahmuda Sultana and Shuvo, Sawgat Ahmed and Islam, Kazi Sifatul and Javed, Syed and Rafat, Sharif Ahmed and Dutta, Anandi and others},
journal={ACM Computing Surveys},
publisher={ACM New York, NY}
}Whether you're designing deep learning models for microcontrollers, optimizing inference for edge hardware, or exploring real-world applications like wearables, smart sensors, or autonomous systems, this collection offers a centralized hub for everything TinyML — enriched by community contributions and peer-reviewed research that shape the future of efficient on-device intelligence.
- [October 21, 2025]: Our paper has been accepted at ACM Computing Surveys 🎉!
- [June 21, 2025]: Preprint is now available in arXiv.
July 21, 2026 at 02:09:48 AM UTC
- TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems He, Warden, et al., 2020 – arXiv:2010.08678 Presents the architecture and design of TensorFlow Lite Micro for microcontrollers and resource-constrained systems.
- Wake Vision: A Tailored Dataset and Benchmark Suite for TinyML Computer Vision Applications
- Integration of TinyML and LargeML: A Survey of 6G and Beyond
- msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyML
- TActiLE: Tiny Active LEarning for wearable devices
- TinyML NLP Scheme for Semantic Wireless Sentiment Classification with Privacy Preservation
- MultiCore+TPU Accelerated Multi-Modal TinyML for Livestock Behaviour Recognition
- Can LLMs Revolutionize the Design of Explainable and Efficient TinyML Models?
- TinyFormer: Efficient Transformer Design and Deployment on Tiny Devices
- Consolidating TinyML Lifecycle with Large Language Models: Reality, Illusion, or Opportunity?
- Edge Intelligence for Wildlife Conservation: Real-Time Hornbill Call Classification Using TinyML
- On-Sensor Convolutional Neural Networks with Early-Exits
- Dendron: Enhancing Human Activity Recognition with On-Device TinyML Learning
- Fast Data Aware Neural Architecture Search via Supernet Accelerated Evaluation
- ETHEREAL: Energy-efficient and High-throughput Inference using Compressed Tsetlin Machine
- EdgeMark: An Automation and Benchmarking System for Embedded Artificial Intelligence Tools
- Enhancing Field-Oriented Control of Electric Drives with Tiny Neural Network Optimized for Micro-controllers
- Toward Attention-based TinyML: A Heterogeneous Accelerated Architecture and Automated Deployment Flow
- DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators
- Enhancing Predictive Maintenance in Mining Mobile Machinery through a TinyML-enabled Hierarchical Inference Network
- Enhanced FIWARE-Based Architecture for Cyberphysical Systems With Tiny Machine Learning and Machine Learning Operations: A Case Study on Urban Mobility Systems
- QUTE: Quantifying Uncertainty in TinyML with Early-exit-assisted ensembles for model-monitoring
- TinyML Security: Exploring Vulnerabilities in Resource-Constrained Machine Learning Systems
- Energy-Aware FPGA Implementation of Spiking Neural Network with LIF Neurons
- P-YOLOv8: Efficient and Accurate Real-Time Detection of Distracted Driving
- A Tiny Supervised ODL Core with Auto Data Pruning for Human Activity Recognition
- Accelerating TinyML Inference on Microcontrollers through Approximate Kernels
- Optimizing TinyML: The Impact of Reduced Data Acquisition Rates for Time Series Classification on Microcontrollers
- A Continual and Incremental Learning Approach for TinyML On-device Training Using Dataset Distillation and Model Size Adaption
- Training on the Fly: On-device Self-supervised Learning aboard Nano-drones within 20 mW
- On TinyML and Cybersecurity: Electric Vehicle Charging Infrastructure Use Case
- StreamTinyNet: video streaming analysis with spatial-temporal TinyML
- Enhancing TinyML Security: Study of Adversarial Attack Transferability
- TinyAirNet: TinyML Model Transmission for Energy-efficient Image Retrieval from IoT Devices
- HTVM: Efficient Neural Network Deployment On Heterogeneous TinyML Platforms
- TinySV: Speaker Verification in TinyML with On-device Learning
- Towards Contactless Elevators with TinyML using CNN-based Person Detection and Keyword Spotting
- On-device Online Learning and Semantic Management of TinyML Systems
- FunnelNet: An End-to-End Deep Learning Framework to Monitor Digital Heart Murmur in Real-Time
- EcoPull: Sustainable IoT Image Retrieval Empowered by TinyML Models
- Simulating Battery-Powered TinyML Systems Optimised using Reinforcement Learning in Image-Based Anomaly Detection
- TinyVQA: Compact Multimodal Deep Neural Network for Visual Question Answering on Resource-Constrained Devices
- Tiny Machine Learning: Progress and Futures
- Tiny Graph Neural Networks for Radio Resource Management
- Scheduled Knowledge Acquisition on Lightweight Vector Symbolic Architectures for Brain-Computer Interfaces
- MosquIoT: A System Based on IoT and Machine Learning for the Monitoring of Aedes aegypti (Diptera: Culicidae)
- DTMM: Deploying TinyML Models on Extremely Weak IoT Devices with Pruning
- Is TinyML Sustainable? Assessing the Environmental Impacts of Machine Learning on Microcontrollers
- Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review
- Physics-Enhanced TinyML for Real-Time Detection of Ground Magnetic Anomalies
- Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices
- Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and Algorithms
- From Tiny Machine Learning to Tiny Deep Learning: A Survey
- Data Aware Differentiable Neural Architecture Search for Tiny Keyword Spotting Applications
- SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyML
- Quantized Neural Networks for Microcontrollers: A Comprehensive Review of Methods, Platforms, and Applications
- A Survey of TinyML Applications in Beekeeping for Hive Monitoring and Management
- A Multicore and Edge TPU-Accelerated Multimodal TinyML System for Livestock Behavior Recognition
- Tiny Machine Learning for Real-Time Aquaculture Monitoring: A Case Study in Morocco
- Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications
- NanoCockpit: Performance-optimized Application Framework for AI-based Autonomous Nanorobotics
- TinyML-Enabled IoT for Sustainable Precision Irrigation
- Rethinking Temporal Models for TinyML: LSTM versus 1D-CNN in Resource-Constrained Devices
- Scaling Laws in the Tiny Regime: How Small Models Change Their Mistakes
- Energy-Aware Multi-Exit TinyML for Smart Zero-Energy Devices
- Affordable Precision Agriculture: A Deployment-Oriented Review of Low-Cost, Low-Power Edge AI and TinyML for Resource-Constrained Farming Systems
- Once-for-All Channel Mixers (HYPERTINYPW): Generative Compression for TinyML
- TinyML for Acoustic Anomaly Detection in IoT Sensor Networks
- Fully Autonomous Z-Score-Based TinyML Anomaly Detection on Resource-Constrained MCUs Using Power Side-Channel Data
- Co-Design of CNN Accelerators for TinyML using Approximate Matrix Decomposition
- LiteAtt: A Peer-to-Peer Self-Attestation Framework and Handshake Protocol for Connected IoT Devices
- ArrythML: An Autoencoder-Based TinyML Approach for On-Device Arrhythmia Detection on Resource-Constrained Embedded Systems
- Running hardware-aware neural architecture search on embedded devices under 512MB of RAM
- TinyML for On-Device and Edge Analytics in Wireless Networks: A Survey of Deployments, Opportunities, and Concept-Drift Mitigation
- TensorFlow Lite for Microcontrollers — Google's official framework for TinyML deployment
- CMSIS-NN — ARM’s optimized neural network kernels for Cortex-M processors
- uTensor — Lightweight inference engine for ARM Cortex-M devices
- Edge Impulse — Full-stack TinyML platform with web IDE and device integration
- ONNX Runtime Mobile — Portable ONNX inference engine for mobile and embedded systems
- TensorFlow Lite Micro: Embedded ML on Microcontrollers — Covers architecture, design, and performance trade-offs
- On-Device Training Under 256 KB RAM — Demonstrates methods for training ML models within severe memory constraints
- Benchmarking TinyML Systems — Discusses performance evaluation and standardization needs in TinyML
- Legend of Elya — World's first LLM on Nintendo 64. 819K-parameter nano-GPT transformer running live inference on the MIPS R4300i CPU (93.75 MHz, 4 MB RAM) at 60 tok/s. The ultimate TinyML demo: a Zelda-style dungeon crawler with AI NPCs on 1996 console hardware. Uses RSP vector unit for matrix multiplication.
- TinyML Education Course (HarvardX) — Free edX course with Arduino-based labs
- Hackster.io Anomaly Detection Tutorial — Real-world predictive maintenance using Wio Terminal + Edge Impulse
- TensorFlow Lite Micro Examples — Official embedded examples using TFLM
- Getting Started with TinyML (Shawn Hymel) — Introductory talk with code walkthroughs
- Edge Impulse Anomaly Detection Workshop — Step-by-step demo for deploying on real hardware
- TinyML Summit Playlist (TinyML Foundation) — Talks from global researchers and engineers
We welcome contributions to this repository! If you have a resource that you believe should be included, please submit a pull request or open an issue. Contributions can include:
- New libraries or tools related to TinyML
- Tutorials or guides that help users understand and implement TinyML techniques
- Research papers that advance the field of TinyML
- Any other resources that you find valuable for the community
- Fork the repository.
- Create a new branch for your changes.
- Make your changes and commit them with a clear message.
- Push your changes to your forked repository.
- Submit a pull request to the main repository.
Before contributing, take a look at the existing resources to avoid duplicates.
This repository is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. You are free to share and adapt the material, provided you give appropriate credit, link to the license, and indicate if changes were made.