Overview

Edge inference studies how to run AI models close to where data is collected, often on devices with limited memory, power, and computing capacity. Common approaches include quantization, pruning and distillation, hardware-aware model and accelerator design, and adaptive methods such as early exits, model routing, and device-edge splitting. Work spans tasks from object detection and segmentation to language and multimodal models, with evaluation on benchmarks such as COCO and MVTec as well as phones, Raspberry Pi, Jetson, microcontrollers, and FPGAs. A central challenge is balancing accuracy, latency, energy, and robustness: proxy measures such as FLOPs may not predict real-device performance, which also varies with hardware, workload contention, and sustained operation.

Latest papers

248 papers26 papers in the last four weeks, up 13% on the four weeks before. 0.2% of all new papers.

Feb 22, 2026

Metasurfaces-Integrated Wireless Neural Networks for Lightweight Over-The-Air Edge Inference

The upcoming sixth Generation (6G) of wireless networks envisions ultra-low latency and energy efficient Edge Inference (EI) for diverse Internet of Things (IoT) applications. However, traditional digital hardware for machine learning is power intensive, motivating the need for alternative computation paradigms. Over-The-Air (OTA) computation is regarded as an emerging transformative approach assigning the wireless channel to actively perform computational tasks. This article introduces the concept of Metasurfaces-Integrated Neural Networks (MINNs), a physical-layer-enabled deep learning framework that leverages programmable multi-layer metasurface structures and Multiple-Input Multiple-Output (MIMO) channels to realize computational layers in the wave propagation domain. The MINN system is conceptualized as three modules: Encoder, Channel (uncontrollable propagation features and metasurfaces), and Decoder. The first and last modules, realized respectively at the multi-antenna transmitter and receiver, consist of conventional digital or purposely designed analog Deep Neural Network (DNN) layers, and the metasurfaces responses of the Channel module are optimized alongside all modules as trainable weights. This architecture enables computation offloading into the end-to-end physical layer, flexibly among its constituent modules, achieving performance comparable to fully digital DNNs while significantly reducing power consumption. The training of the MINN framework, two representative variations, and performance results for indicative applications are presented, highlighting the potential of MINNs as a lightweight and sustainable solution for future EI-enabled wireless systems. The article is concluded with a list of open challenges and promising research directions.
Feb 17, 2026

DART: Input-Difficulty-AwaRe Adaptive Threshold for Early-Exit DNNs

Early-exit deep neural networks enable adaptive inference by terminating computation when sufficient confidence is achieved, reducing cost for edge AI accelerators in resource-constrained settings. Existing methods, however, rely on suboptimal exit policies, ignore input difficulty, and optimize thresholds independently. This paper introduces DART (Input-Difficulty-Aware Adaptive Threshold), a framework that overcomes these limitations. DART introduces three key innovations: (1) a lightweight difficulty estimation module that quantifies input complexity with minimal computational overhead, (2) a joint exit policy optimization algorithm based on dynamic programming, and (3) an adaptive coefficient management system. Experiments on diverse DNN benchmarks (AlexNet, ResNet-18, VGG-16) demonstrate that DART achieves up to \textbf{3.3×\times} speedup, \textbf{5.1×\times} lower energy, and up to 42% lower average power compared to static networks, while preserving competitive accuracy. Extending DART to Vision Transformers (LeViT) yields power (5.0×\times) and execution-time (3.6×\times) gains but also accuracy loss (up to 17 percent), underscoring the need for transformer-specific early-exit mechanisms. We further introduce the Difficulty-Aware Efficiency Score (DAES), a novel multi-objective metric, under which DART achieves up to a 14.8 improvement over baselines, highlighting superior accuracy, efficiency, and robustness trade-offs.
Feb 12, 2026

MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios

Mixture-of-Experts (MoE) models enable scalable performance but face severe memory constraints on edge devices. Existing offloading strategies struggle with I/O bottlenecks due to the dynamic, low-information nature of autoregressive expert activation. In this paper, we propose to repurpose Speculative Decoding (SD) not merely as a compute accelerator, but as an informative lookahead sensor for memory management, supported by our theoretical and empirical analyses. Hence, we introduce MoE-SpAc, an MoE inference framework that integrates a Speculative Utility Estimator to track expert demand, a Heterogeneous Workload Balancer to dynamically partition computation via online integer optimization, and an Asynchronous Execution Engine to unify the prefetching and eviction in the same utility space. Extensive experiments on seven benchmarks demonstrate that MoE-SpAc achieves a 42% improvement in TPS over the SOTA SD-based baseline, and an average 4.04x speedup over all standard baselines. Code is available at https://github.com/lshAlgorithm/MoE-SpAc .
Jan 22, 2026

FlashMoE: Reducing SSD I/O Bottlenecks via ML-Based Cache Replacement for Mixture-of-Experts Inference on Edge Devices

Recently, Mixture-of-Experts (MoE) models have gained attention for efficiently scaling large language models. Although these models are extremely large, their sparse activation enables inference to be performed by accessing only a fraction of the model at a time. This property opens the possibility of on-device inference of MoE, which was previously considered infeasible for such large models. Consequently, various systems have been proposed to leverage this sparsity and enable efficient MoE inference for edge devices. However, previous MoE inference systems like Fiddler[8] or DAOP[13] rely on DRAM-based offloading and are not suitable for memory constrained on-device environments. As recent MoE models grow to hundreds of gigabytes, RAM-offloading solutions become impractical. To address this, we propose FlashMoE, a system that offloads inactive experts to SSD, enabling efficient MoE inference under limited RAM. FlashMoE incorporates a lightweight ML-based caching strategy that adaptively combines recency and frequency signals to maximize expert reuse, significantly reducing storage I/O. In addition, we built a user-grade desktop platform to demonstrate the practicality of FlashMoE. On this real hardware setup, FlashMoE improves cache hit rate by up to 51% over well-known offloading policies such as LRU and LFU, and achieves up to 2.6x speedup compared to existing MoE inference systems.
Dec 4, 2025

Hardware-Algorithm Co-Optimization of Early-Exit Neural Networks for Multi-Core Edge Accelerators

The deployment of Early-Exiting Neural Networks (EENNs) on edge accelerators requires optimizing not only the network architecture but also its hardware deployment. Exit configuration, quantization, and hardware workload mapping interact in non-trivial ways, influencing memory traffic, accelerator utilization, and ultimately the energy-latency trade-off. This work presents a hardware-aware co-design framework for EENNs that jointly optimizes exit configuration, quantization-aware training, and multi-core hardware mapping within a unified NAS process. Leveraging analytical design space exploration, the framework identifies efficient workload mappings for each candidate architecture while providing accurate latency and energy estimates during the search. We further formulate EENN deployment as a constrained multi-objective optimization problem balancing predictive accuracy, energy-latency product, exit overhead, and dynamic inference efficiency. Experimental results on CIFAR-10 demonstrate that the proposed framework achieves over a 50% reduction in energy-latency product compared with static baselines under 8-bit quantization. These results demonstrate that jointly optimizing architecture and deployment is essential for realizing the full efficiency potential of dynamic inference on heterogeneous edge accelerators.
Mar 20, 2025

LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices

While there are many advantages to deploying machine learning models on edge devices, the resource constraints of mobile platforms, the dynamic nature of the environment, and differences between the distribution of training versus in-the-wild data make such deployments challenging. Current test-time adaptation methods are often memory-intensive and not designed to be quantization-compatible or deployed on low-resource devices. To address these challenges, we present LeanTTA, a novel backpropagation-free and stateless framework for quantized test-time adaptation tailored to edge devices. Our approach minimizes computational costs by dynamically updating normalization statistics without backpropagation, which frees LeanTTA from the common pitfall of relying on large batches and historical data, making our method robust to realistic deployment scenarios. Our approach is the first to enable further computational gains by combining partial adaptation with quantized module fusion. We validate our framework across sensor modalities, demonstrating significant improvements over state-of-the-art TTA methods, including a 15.7% error reduction, peak memory usage of only 11.2MB for ResNet18, and fast adaptation within an order-of-magnitude of normal inference speeds on-device. LeanTTA provides a robust solution for achieving the right trade offs between accuracy and system efficiency in edge deployments, addressing the unique challenges posed by limited data and varied operational conditions.
Feb 26, 2025

Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies

In recent years, vision transformers (ViTs) have emerged as powerful and promising techniques for computer vision tasks such as image classification, object detection, and segmentation. Unlike convolutional neural networks (CNNs), which rely on hierarchical feature extraction, ViTs treat images as sequences of patches and leverage self-attention mechanisms. However, their high computational complexity and memory demands pose significant challenges for deployment on resource-constrained edge devices. To address these limitations, extensive research has focused on model compression techniques and hardware-aware acceleration strategies. Nonetheless, a comprehensive review that systematically categorizes these techniques and their trade-offs in accuracy, efficiency, and hardware adaptability for edge deployment remains lacking. This survey bridges this gap by providing a structured analysis of model compression techniques, software tools for inference on edge, and hardware acceleration strategies for ViTs. We discuss their impact on accuracy, efficiency, and hardware adaptability, highlighting key challenges and emerging research directions to advance ViT deployment on edge platforms, including graphics processing units (GPUs), application-specific integrated circuit (ASICs), and field-programmable gate arrays (FPGAs). The goal is to inspire further research with a contemporary guide on optimizing ViTs for efficient deployment on edge devices.
Sep 25, 2024

A Comprehensive Evaluation of Deep Learning Object Detection Models on Heterogeneous Edge Devices

Modern applications such as autonomous vehicles, intelligent surveillance, and smart city systems increasingly require object detection on resource-constrained edge devices. Yet, there is still limited understanding of how different object detection models behave across heterogeneous edge devices and under varying scene complexity. In this paper, we benchmark YOLOv8 (Nano, Small, Medium), EfficientDet Lite (Lite0, Lite1, Lite2), and SSD (SSD MobileNet V1, SSDLite MobileDet) on Raspberry Pi 3, 4, 5 with/without Coral TPU accelerators, Raspberry Pi 5 with AI HAT+, Jetson Nano, and Jetson Orin Nano. We evaluate energy consumption, inference time, and accuracy, and further examine how accuracy changes with the number of objects in the input image. The results reveal clear trade-offs among accuracy, latency, and energy efficiency across model-device combinations. SSD MobileNet V1 achieves the lowest latency and energy consumption but the lowest accuracy, whereas YOLOv8 Medium achieves the highest accuracy at higher computational cost. TPU-based Raspberry Pi devices improve the efficiency of SSD and EfficientDet Lite while reducing YOLOv8 accuracy. Orin Nano offers the most favorable overall balance across most model families. The object-count-based analysis further shows that models achieve more similar accuracy on simpler images, while the accuracy gap widens as scene complexity increases.