The paper discusses TinyML, which deploys machine learning on devices with limited memory and computing resources. It introduces a preliminary study using the tree depth prune instance hardness method to control thresholds in TinyML systems. The results suggest that adjusting these thresholds can reduce energy consumption while maintaining classification quality.
arXiv:2608.21646v1 Announce Type: cross Abstract: TinyML systems are enabling machine learning (ML) inference at the edge. However, there is little quantitative analysis of such systems. This paper p...
arXiv:2502. 16886v4 Announce Type: replace-cross Abstract: To reduce memory consumption during LLM inference, a handful of methods have been proposed for KV cache pruning.
arXiv:2606. 02256v1 Announce Type: new Abstract: Our work presents a method for ECG segmentation and arrhythmia detection using Tiny Machine Learning (TinyML) models for real-time, on-device inference on resource-constrained embedded systems.
arXiv:2606. 19712v1 Announce Type: new Abstract: While much effort has focused on developing and benchmarking high-performance neural networks, less attention has been given to how dataset properties, known to practitioners, can guide efficient model selection.
The paper explores how to combine Federated Learning with TinyML model compression techniques—such as knowledge distillation, structured pruning, and quantization—to create lightweight, privacy‑preserving intrusion detection systems for IoT devices. It evaluates these strategies within a federated training pipeline and finds that training stability is crucial; a server‑coordinated cosine learning‑rate schedule boosts Attack Recall from 46.7% to 93.85% while still allowing significant model compression and efficient edge deployment.
arXiv:2606. 19964v1 Announce Type: new Abstract: Tsetlin Machine (TM) is a logic-based machine learning approach that relies on simple bitwise operations and finite-state automata, which makes it attractive for edge AI deployments.
The paper investigates the environmental impact of running large language models (LLMs) on mobile devices. It evaluates 18 different LLM configurations on two smartphones and a server, measuring energy per token, latency, accuracy, and battery-cycle consumption. Findings reveal that on-device inference is about three times less energy‑efficient than batched server inference, that energy consumption varies non‑monotonically with quantization bit‑width, and that most models are not on the Pareto front of accuracy and energy efficiency. The study concludes that local AI is not inherently more sustainable than cloud inference, with the majority of environmental impact stemming from device embodied carbon.
arXiv:2607. 20003v1 Announce Type: cross Abstract: An increase in advanced Android malware requires the use of deep learning models, which can run on Android devices.
arXiv:2608.23101v1 Announce Type: cross Abstract: Recent progress in the field of TinyML has demonstrated that low-power hardware based on microcontrollers can achieve bird species monitoring in real...
arXiv:2606. 29518v1 Announce Type: cross Abstract: With the widespread adoption of AI in various IoT scenarios such as smart sensing and processing, AI chips have become a common component at the edge.
arXiv:2605. 18331v2 Announce Type: replace Abstract: Large Language Models (LLMs) have experienced significant growth and development in recent years.
arXiv:2607. 22583v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved widespread adoption because of their strong reasoning and query-response capabilities.