arXiv:2608. 13863v1 Announce Type: new Abstract: Deep neural network (DNN) inference on mobile devices often incurs high latency and energy consumption due to limited computing and memory resources.
arXiv:2608. 03589v1 Announce Type: new Abstract: We present a method for designing deep neural networks (DNNs) for intermittent, energy-autonomous, on-device learning on microcontroller units (MCUs).
arXiv:2609.09662v1 Announce Type: cross Abstract: Deploying Large Language Models (LLMs) directly on mobile platforms at the edge is gaining traction due to a myriad of benefits, such as increased pr...
The paper introduces GQ-FSL, a green quantized federated split learning framework designed for wireless edge networks. It uses stochastic quantization for both local training and wireless transmissions, allowing asymmetric precision between client and server submodels to balance device energy limits with global convergence. The authors develop energy models and a convergence bound for heterogeneous data, then formulate an optimization problem to set the DNN split point and precision levels, achieving lower energy consumption while meeting latency and accuracy targets.
arXiv:2607. 06922v1 Announce Type: new Abstract: Deep learning applications have been widely adopted on edge devices, to mitigate the privacy and latency issues of accessing cloud servers.
arXiv:2607. 29659v1 Announce Type: new Abstract: Deploying state-of-the-art deep neural networks (DNNs) at the wireless edge is severely bottlenecked by the strict energy and resource constraints of mobile devices.
arXiv:2606. 12742v1 Announce Type: new Abstract: Wearable healthcare devices are the fastest-growing Internet of Things (IoT) sector.
The paper presents a novel multi‑exit computational scheme for TinyML on an ultra‑low‑power GAP9 SoC, adding confidence‑based gating points to a MobileNetV2 CNN for ImageNet‑100. By allowing inference to stop early, the approach cuts average MAC operations by 41 % (from 313 MMAC to 185 MMAC), reduces inference time by 29 % (49 ms to 35 ms), and saves 24 % in energy (2.1 mJ to 1.6 mJ per frame) with only a ~1 % drop in accuracy. Compared to a state‑of‑the‑art adaptive CNN on the same hardware, the method more than doubles computational efficiency, raising MAC/cycle from 8.1 to 17.2.
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. 24256v1 Announce Type: cross Abstract: As communication networks adopt virtualized and disaggregated architectures, achieving energy efficiency has become increasingly important for both economic and environmental reasons.
arXiv:2608. 15502v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a promising foundation for Embodied AI, but their high inference cost poses significant challenges for deployment in robotic systems.
FeatureFormer is a neural performance predictor that adds explicit node-wise encodings of FLOPs, parameter counts, and memory proxies to a gated graph attention architecture. It is designed to improve latency and energy prediction for neural networks on edge devices, addressing the limitation of existing GNN and transformer predictors that largely ignore node-level computational cost. The authors also introduce NNEQ, a large-scale energy consumption dataset, and show through extensive experiments that FeatureFormer achieves state‑of‑the‑art performance across both metrics, including challenging out‑of‑domain settings, while the encoding can broadly enhance existing predictors with negligible overhead.
The paper introduces Radio‑Frequency Convolutional Neural Networks (RF‑CNNs), which repurpose the frequency mixer in wireless radios to perform convolutional neural network inference directly on edge devices. By mapping multi‑channel convolutions onto frequency tones, the passive mixer can execute the entire operation in a single pass, enabling deep CNNs with up to 26.4 million parameters and nine layers to run on smartphones, wearables, and drones. Experimental results show near full‑precision performance while reducing energy consumption to 0.72 fJ per multiply‑accumulate—two orders of magnitude lower than adding a digital processor. "whyItMatters":"The approach leverages existing radio hardware to deliver efficient, state‑of‑the‑art AI inference on billions of devices without increasing size, weight, power, or cost."