边缘智能 · 全部实体（第 5 / 96 页）

本页收录第 401–500 条，共 9595 条 · 返回 边缘智能 首页

• Energy-Efficient Hybrid Cache Memory Design for Edge-Based AI Inference Using SRAM and ReRAM
  Edge devices are becoming more burdened with the task of executing AI inference in real-time, although they have limited energy and efficient computing capabilities. The memory access and data movement is a very important part of the overall energy consumption…
  crossref Navaneeth Krishnan, Ram Krishna, Rajesh Kannan Megalingam 2026-05-12T19:46:43Z 置信度 0.82 energy storagecs.niinformation theorydistributed computingprocess engineering
• Accelerate Multi-view Inference with End-edge Collaborative Computing
  Multi-view inference can utilize visual information from several views like a human being and significantly improve accuracy in some scenes, but it inevitably incurs more computing overhead than traditional DNN inference. To meet the requirement of low latency…
  crossref Wangbing Cheng, MinFeng Zhang, Fang Dong, Shucun Fu 2023-06-23T23:57:23Z 置信度 0.79 computer and information sciencescs.lgcomputer sciencecs.aidistributed computing
• SAI: Latency-Aware Satellite Edge LAM Inference with Looped Transformer
  The rapid advancements in computing and communication capabilities of Low Earth Orbit (LEO) satellites have made it feasible to execute complex and collaborative inorbit computation missions. Transformer-based large AI models (LAMs), known for their exceptiona…
  crossref Honggang Yuan, Zixin Wang, Yuning Jiang, Xin Liu 等 2025-09-26T17:34:55Z 置信度 0.82 computer and information sciencescs.lgcs.aielectrical engineering, electronic engineering, information engineeringcomputer science
• Building Efficient Inference Systems for Resource-Constrained Edge AI Deployment
  crossref Xiangyu Li 2026-06-01T15:54:37Z 置信度 0.66
• Adaptive Inference Reinforcement Learning for Task Offloading in Vehicular Edge Computing Systems
  Vehicular edge computing (VEC) is expected as a promising technology to improve the quality of innovative applications in vehicular networks through computation offloading. However, in VEC system, the characteristics of distributed computing resources and high…
  crossref Dian Tang, Xuefei Zhang, Meng Li, Xiaofeng Tao 2020-07-21T21:24:43Z 置信度 0.79 computer and information scienceselectrical engineering, electronic engineering, information engineeringcomputer sciencenetworking and internet architecturecs.ni
• Inference of 3-D Shape with Edge from Image Brightness
  A traditional method to reconstruct a 3-D shape from shading is to structure an objective functional H(X), over surface normal distribution X, which is a weighted average of the regularization terms representing smoothness constraints and data term representin…
  crossref Wen Biao Jiang, Hai Yuan Wu, Tadayoshi Shioyama 2023-05-23T05:44:29Z 置信度 0.79 cs.lgstat.apcognitioncomputer and information sciencescontrol theory
• TensorRT Optimization of YOLOv9 for Real-time Edge Inference Under Multiple Power Modes
  Deploying machine learning models on edge computing platforms requires optimizing performance within limited computational resources, reducing latency, and enhancing inference speed. This study proposes a lightweight inference model architecture, utilizing the…
  crossref Jie-Hong Hou, Shih-Wen Chen 2025-10-27T17:53:54Z 置信度 0.82 computer and information sciencesedge computingcs.lgcs.dccryptography and security
• Tango: Low Latency Multi-DNN Inference on Heterogeneous Edge Platforms
  There is an increasing demand to run DNN applications on edge platforms for low-latency inference. Executing multi-DNN workloads with diverse compute and latency requirements on resource-constrained heterogeneous edge platforms poses a significant scheduling c…
  crossref Zain Taufique, Aman Vyas, Antonio Miele, Pasi Liljeberg 等 2025-01-02T19:17:19Z 置信度 0.82 computer and information sciencescs.dcedge computingcs.aicloud computing
• HALO: Semantic-Aware Distributed LLM Inference in Lossy Edge Network
  The deployment of large language models' (LLMs) inference at the edge can facilitate prompt service responsiveness while protecting user privacy. However, it is critically challenged by the resource constraints of a single edge node. Distributed inference has …
  crossref Peirong Zheng, Wenchao Xu, Haozhao Wang, Jinyu Chen 等 2026-06-29T19:38:15Z 置信度 0.82 computer and information sciencescs.aics.lgcs.cvcomputer science
• Enhancing Edge Performance: A Comparative Analysis of LSTM Inference Using Hardware Acceleration
  Field-Programmable Gate Arrays (FPGAs) provide compelling advantages for accelerating Long Short-Term Memory (LSTM) networks, particularly in edge computing applications where performance and power efficiency are critical. This study presents an optimized FPGA…
  crossref Sagar Mhatre, Vinitkumar Jayaprakash Dongre, Sudhakar Mande 2025-04-25T17:38:13Z 置信度 0.82 computer and information sciencescomputer scienceedge computingcs.dcelectrical engineering, electronic engineering, information engineering
• Online Resource Allocation for Edge Intelligence with Colocated Model Retraining and Inference
  With edge intelligence, AI models are increasingly push to the edge to serve ubiquitous users. However, due to the drift of model, data, and task, AI model deployed at the edge suffers from degraded accuracy in the inference serving phase. Model retraining han…
  crossref Huaiguang Cai, Zhi Zhou, Qianyi Huang 2024-08-12T17:25:41Z 置信度 0.82 computer and information sciencescs.lgcs.aielectrical engineering, electronic engineering, information engineeringdistributed computing
• Accelerating Native Inference Model Performance in Edge Devices using TensorRT
  In this era, deep learning is becoming increasingly popular for solving real-world problems. Due to the extremely high processing power required to execute the most complex deep learning models, Graphics Processing Units(GPUs) and Neural Processing Units(NPUs)…
  crossref Gopikrishna P B, Rubell Marion Lincy G, Abhishek Rishekeeshan, Deekshitha 2024-10-01T13:23:12Z 置信度 0.82 computer scienceartificial intelligencecs.lgcomputer and information sciencescloud computing
• Secure eFPGA-Enabled Edge LLM Inference: Architectural and Hardware Countermeasures
  crossref Voktho Das, M Zafir Sadik Khan, Jafar Vafaei, Kimia Azar 等 2026-06-18T20:06:49Z 置信度 0.66
• CarbonEdge: Carbon-Aware Deep Learning Inference Framework for Sustainable Edge Computing
  crossref Guilin Zhang, Wulan Guo, Ziqi Tan, Chuanyi Sun 等 2026-07-03T19:49:45Z 置信度 0.66
• eNODE: Energy-Efficient and Low-Latency Edge Inference and Training of Neural ODEs
  Neural ordinary differential equations (NODEs) provide better modeling performance with smaller amount of model parameters in many tasks by embedding neural networks (NNs) in ordinary differential equations (ODEs). They have been shown to outperform in represe…
  crossref Junkang Zhu, Yaoyu Tao, Zhengya Zhang 2023-03-24T17:42:55Z 置信度 0.79 computer and information scienceselectrical engineering, electronic engineering, information engineeringnetworking and internet architecturecs.lgcryptography and security
• Bayesian Analysis of Dynamic Network Regression with Joint Edge/Vertex Dynamics
  This chapter contains sections titled: Introduction Statistical Models for Social Network Data Dynamic Network Logistic Regression with Vertex Dynamics Empirical Examples and Simulation Analysis Discussion Conclusion
  crossref Zack W. Almquist, Carter T. Butts 2014-11-15T03:59:35Z 置信度 0.76 q-bio.mncs.cesoftwareq-bio.qmartificial neural network
• Efficient Dynamic Fixed-Point Quantization of CNN Inference Accelerators for Edge Devices
  This paper presents a dynamic fixed-point quantization flow. Different bit-width configurations of features, weights, and partial sums can be evaluated comprehensively over the state-of-the-art convolutional neural networks. The proposed quantization scheme si…
  crossref Yueh-Chi Wu, Chih- Tsun Huang 2019-06-21T02:19:04Z 置信度 0.79 cs.lgelectrical engineering, electronic engineering, information engineeringconvolutional neural networkcomputer and information scienceseess.iv
• Preva: Protecting Inference Privacy through Policy-based Video-frame Transformation
  Real-time edge-cloud video analytics systems have been widely used to support such applications as traffic counting, surveillance, autonomous driving, Metaverse, etc. In such a system, the edge and the cloud cooperatively conduct model inference of the video f…
  crossref Rui Lu, Siping Shi, Dan Wang, Chuang Hu 等 2023-01-02T19:16:06Z 置信度 0.79 computer and information sciencescloud computingedge computingcryptography and securitycs.cv
• Low-Latency Asynchronous Logic Design for Inference at the Edge
  Modern internet of things (IoT) devices leverage machine learning inference using sensed data on-device rather than offloading them to the cloud. Commonly known as inference at-the-edge, this gives many benefits to the users, including personalization and secu…
  crossref Adrian Wheeldon, Alex Yakovlev, Rishad Shafik, Jordan Morris 2021-08-24T22:11:46Z 置信度 0.79 computer sciencecomputer and information sciencescloud computingelectrical engineering, electronic engineering, information engineeringdistributed computing
• Adaptive partitioning of DNNs for resource-efficient inference on edge clusters
  crossref Azra Nazir, Faisal Rasheed Lone, Ashfaq Ahmad Najar 2025-09-03T14:17:10Z 置信度 0.66
• Modular Foundation Model Inference at the Edge: Network-Aware Microservice Optimization
  crossref Juan Zhu, Zixin Wang, Shenghui Song, Jun Zhang 等 2026-07-14T19:38:09Z 置信度 0.66
• Distributed Edge Intelligence for Efficient Artificial Intelligence Inference over Sixth-Generation Wireless Networks
  The recent proliferation of artificial intelligence (AI) applications in mission-critical and latency-sensitive domains, such as autonomous driving, remote healthcare services, smart manufacturing, and immersive extended reality, puts forward requirements on i…
  crossref B. T. Vijay, M. N. Varshini, R. Chaithra 2026-08-27T12:46:42Z 置信度 0.82 computer sciencecomputer and information scienceselectrical engineering, electronic engineering, information engineeringsignal processingnetworking and internet architecture
• Predicting Delay, Power, and Energy of Edge AI Inference with Ridge Regression
  As AI becomes central to consumer devices, edge inference must meet strict latency and energy constraints under limited compute and thermal budgets. We present a regression-based framework for predicting four inference metrics—Delay, Power, Energy, and Energy–…
  crossref Minkyu Park, Jaemin Jeong, Jiho Cho, Jeong-Gun Lee 2026-03-27T19:47:50Z 置信度 0.82 computer and information scienceselectrical engineering, electronic engineering, information engineeringrenewable energyenvironmental economicsscalability
• Semi-Supervised Approach For Inference Serving At The Edge
  crossref Saif Eddine Khelifa, Sihem Ouahouah, Miloud Bagaa, Messaoud Ahmed Ouameur 等 2026-07-03T19:49:45Z 置信度 0.66
• Content Popularity Estimation in Edge-Caching Networks from Bayesian Inference Perspective
  The efficiency of cache-placement algorithms in edge-caching networks depends on the accuracy of the content request’s statistical model and the estimation method based on the postulated model. This paper studies these two important issues. First, we introduce…
  crossref Sajad Mehrizi, Anestis Tsakmalis, Symeon Chatzinotas, Björn Ottersten 2019-02-28T18:40:01Z 置信度 0.79 cs.lgstat.mlstat.apcs.cvmath.oc
• RobustDiCE: Robust and Distributed CNN Inference at the Edge
  Prevalent large CNN models pose a significant challenge in terms of computing resources for resource-constrained devices at the Edge. Distributing the computations and coefficients over multiple edge devices collaboratively has been well studied but these work…
  crossref Xiaotian Guo, Quan Jiang, Andy D. Pimentel, Todor Stefanov 2024-03-25T19:06:53Z 置信度 0.82 computer and information sciencescomputer sciencecs.lgcs.aics.cv
• Ultra-Low-Latency Edge Inference for Distributed Sensing with Short Packets
  Artificial intelligence (AI) is expected to be a defining component in sixth-generation (6G) wireless networks. One specific use is AI-empowered sensing, where sensor data will be processed at the network edge, giving rise to integrated sensing and edge AI (IS…
  crossref Zhanwei Wang, Anders E. Kalør, You Zhou, Petar Popovski 等 2025-09-26T17:34:55Z 置信度 0.82 computer and information scienceselectrical engineering, electronic engineering, information engineeringsignal processingnetworking and internet architectureinformation theory
• Channel Capacity-Aware Distributed Encoding for Multi-View Sensing and Edge Inference
  Integrated sensing and communication (ISAC) unifies wireless communication and sensing by sharing spectrum and hardware, which often incurs trade-offs between two functions due to limited resources. However, this paper shifts focus to exploring the synergy bet…
  crossref Mingjie Yang, Guangming Liang, Dongzhu Liu, Lei Zhang 等 2025-09-26T17:34:55Z 置信度 0.82 computer and information scienceselectrical engineering, electronic engineering, information engineeringsignal processinginformation theorynetworking and internet architecture
• RAW 2024 Invited Talk-2: Digital In-Memory Computing to Accelerate Deep Learning Inference on the Edge
  Deploying Deep Learning (DL) models on edge devices presents several challenges due to the limited setof processing and memory resources, and the bandwidth constraints while ensuring performance and energyrequirements. In-memory computing (IMC) represents an e…
  crossref Stefania Perri 2024-07-26T17:22:29Z 置信度 0.82 computer scienceedge computingcloud computingcs.dctransformative learning
• Tiny Time-Series Transformers: Realtime Multi-Target Sensor Inference At The Edge
  Large-scale wireless sensor networks have become an invaluable tool for dense spatiotemporal modeling of urban air pollution. When coupled with complex nonlinear regression schemes, they become an unparalleled tool capable of dynamic, autonomous sensor calibra…
  crossref Tom Becnel, Kerry Kelly, Pierre-Emmanuel Gaillardon 2022-08-25T18:43:32Z 置信度 0.79 computer and information sciencescs.lgcs.aielectrical engineering, electronic engineering, information engineeringcs.cv
• DNN Partitioning for Inference Throughput Acceleration at the Edge
  Deep neural network (DNN) inference on streaming data requires computing resources to satisfy inference throughput requirements. However, latency and privacy sensitive deep learning applications cannot afford to offload computation to remote clouds because of …
  crossref Thomas Feltin, Léo Marchó, Juan-Antonio Cordero-Fuertes, Frank Brockners 等 2023-02-16T16:13:03Z 置信度 0.79 computer and information sciencescloud computingcomputer sciencecs.lgcryptography and security
• ELPG: End-to-End Latency Prediction for Deep-Learning Model Inference on Edge Devices
  The demand for running deep learning models on edge devices is increasing. In order to achieve lower latency and higher accuracy on edge devices, many studies have custom-designed deep learning models for edge devices, among which hardware-aware neural archite…
  crossref Wenhao Zhao, Lin Wang, Fei Duan 2025-04-03T00:01:20Z 置信度 0.82 cs.lgcomputer and information sciencesartificial neural networkartificial intelligenceedge computing
• Reinforcement Learning Based Collaborative Inference and Task Offloading Optimization for Cloud-Edge-End Systems
  Deep Neural Network (DNN) has been widely used in intelligence applications due to its excellent performance in executing inference tasks. Since DNN tasks require a large amount of computation and high-resolution raw input, collaborative inference is proposed …
  crossref Jiangyu Tian, Xin Li, Xiaolin Qin 2024-09-09T17:35:05Z 置信度 0.82 cs.lgcomputer and information sciencescomputer scienceelectrical engineering, electronic engineering, information engineeringcs.ai
• Research on Lightweight Model-Based Leather Defect Edge Inference Mechanism
  Real-time and accurate detection of production defects is one of the most critical aspects of the production process. This paper proposes a model lightweight-based edge inference mechanism for leather defect detection. By collecting thousands of samples of lea…
  crossref Wen Xiao, Meilin Wang, Jiaxian He, Zhipeng Feng 2023-09-19T17:39:58Z 置信度 0.79 convolutional neural networkstat.mlrobustnesscryptography and securityeess.sp
• LSTCB: Long-Short-Timescale Cooperative Batching for Energy-Efficient Edge Inference
  crossref Zichuan Zheng, Shan Zhang, Naixin Lu, Zhiyuan Wang 等 2026-06-29T19:38:15Z 置信度 0.66
• Efficient and Privacy-Preserving Large Language Model Inference at the Edge
  crossref Vilhelm Toivonen 2026-07-02T19:42:40Z 置信度 0.66
• Distributed Inference on Mobile Edge and Cloud: A Data-Cartography based Clustering Approach
  The large size of DNNs poses a significant challenge for deployment on devices with limited resources, such as mobile, edge, and IoT platforms. To address this issue, a distributed inference framework can be utilized. In this framework, a small-scale DNN (init…
  crossref Divya Jyoti Bajpai, Manjesh Kumar Hanawal 2026-03-10T19:50:41Z 置信度 0.82 computer and information sciencescomputer sciencesignal processingelectrical engineering, electronic engineering, information engineeringcs.ai
• Offloaded Execution of Deep Learning Inference at Edge: Challenges and Insights
  Efforts to leverage the benefits of Deep Learning(DL) models for performing inference in resource constrained embedded devices is very popular nowadays. Researchers worldwide are trying to come up with software and hardware accelerators that make pre-trained D…
  crossref Swarnava Dey, Jayeeta Mondal, Arijit Mukherjee 2019-06-06T23:24:53Z 置信度 0.79 computer and information sciencescomputer scienceedge computingcs.lgelectrical engineering, electronic engineering, information engineering
• Self-Organized Neural Network Inference in Dynamic Edge Networks
  Inference of large machine learning models can quickly exceed the capabilities of edge devices in terms of performance, memory or energy consumption. When offloading computations to a cloud server is not possible or feasible, for instance, due to data sovereig…
  crossref Manuel Schrauth, Moritz Thome, Torsten Ohlenforst, Felix Kreyß 2025-12-01T09:34:37Z 置信度 0.82 computer sciencecomputer and information sciencesedge computingartificial intelligencecloud computing
• Edge Devices Inference Performance Comparison
  In this study, we investigated the inference time of the MobileNet family, EfficientNet V1 and V2 family, VGG models, ResNet family, and InceptionV3 on four edge platforms: Specifically, NVIDIA Jetson Nano, Intel Neural Stick, Google Coral USB Dongle, and Goog…
  crossref Tobiasz Rafal, Wilczynski Grzegorz, Graszka Piotr, Czechowski Nikodem 等 2023-07-10T03:52:02Z 置信度 0.79 cs.lgcs.dccs.necomputer scienceconvolutional neural network
• Generative Inference of Large Language Models in Edge Computing: An Energy Efficient Approach
  Large Language Models (LLMs) have demonstrated remarkable proficiency in generating text and producing fluent, succinct, and precise linguistic expressions. Limited battery life and computing power make it challenging to process LLM inference tasks in mobile d…
  crossref Xingyu Yuan, He Li, Kaoru Ota, Mianxiong Dong 2024-07-17T17:18:34Z 置信度 0.82 computer sciencecomputer and information scienceselectrical engineering, electronic engineering, information engineeringsignal processingcs.ni
• ADDA: Adaptive Distributed DNN Inference Acceleration in Edge Computing Environment
  Implementing intelligent mobile applications on IoT devices with DNN technology has become an inevitable trend. Due to the limitations of the size of DNN model deployed onto end devices and the instability of wide-area network transmission, either End-only mod…
  crossref Huitian Wang, Guangxing Cai, Zhaowu Huang, Fang Dong 2020-01-31T01:32:10Z 置信度 0.79 computer and information sciencesedge computingcs.dccs.lgcloud computing
• VitaLLM: A Versatile and Tiny Accelerator for Mixed-Precision LLM Inference on Edge Devices
  crossref Zi-Wei Lin, Tian-Sheuan Chang 2026-06-18T20:06:41Z 置信度 0.66
• Efficient Pre-Deployment CNN Compression for Edge Inference
  crossref Ahmed S. Farghaly, Mohamed O. Elsedfy, Mohamed A. Elshafey 2026-07-02T19:42:12Z 置信度 0.66
• Performance Characterization of Distributed Inference on Heterogeneous Edge Device Clusters Compared with Single-Device Omnimodal Inference
  본 연구는 이기종 엣지 클러스터의 모달리티별 특화 모델 분산 배치를 단일 디바이스 옴니모달 배포와 동일 태스크에서 비교한다. AGX Orin, Raspberry Pi 5+Hailo-8, Orange Pi 5 Plus에서 MobileViT-S, Whisper-tiny, DistilBERT를 gRPC 분산 추론하고 LLaVA-1.5-7B FP16·INT4 및 Qwen2-VL-2B FP16과 비교한 결과, 분산 구성은 Vision 80~288배, Text 3.7~25…
  crossref Pil-Seong Jeong 2026-08-05T01:04:56Z 置信度 0.82 natural language processingmechanical engineeringcs.cewirelessregolith
• Seismic and well-log inference of gas-hydrate accumulations on Richards Island, Northwest Territories, Canada
  The Mackenzie Delta in Canada's Northwest Territories hosts many permafrost-related gas-hydrate accumulations that were indirectly discovered or inferred from conventional hydrocarbon exploration programs. In particular, gas-hydrate intervals characterized wit…
  crossref Gilles Bellefleur, Michael Riedel, Tom Brent 2013-04-29T18:48:30Z 置信度 0.74 geologymeteoritegeochemistrycs.lgplanet
• A Trusted Inference Mechanism for Edge Computing Based on Post-Quantum Encryption
  Edge computing is a computing framework that offers fewer computing resources compared to cloud computing but brings enterprise applications closer to data sources like Internet of Things (IoT) devices or local edge servers. This proximity to data sources brin…
  crossref Yukang Huang, Junyi Mai, Wanling Jiang, Enyi Yao 2024-07-02T17:22:52Z 置信度 0.82 computer sciencecloud computingedge computingcomputer and information sciencesdistributed computing
• Semantics-Driven Cloud-Edge Collaborative Inference A Case Study of License Plate Detection
  With the proliferation of video data in smart city applications like intelligent transportation, efficient video analytics has become crucial but also challenging. This paper proposes a semantics-driven cloud-edge collaborative approach for accelerating video …
  crossref Yuche Gao, Beibei Zhang 2024-02-13T18:34:14Z 置信度 0.82 computer sciencecomputer and information sciencescloud computingelectrical engineering, electronic engineering, information engineeringedge computing
• TurboInfer: Targeting Age of Model Inference Optimization for Joint Model Inference in Edge Cloud Systems
  crossref Chenxuan Hou, Chao Qiu, Tiantian Cao, Yunfeng Zhao 等 2026-08-04T19:15:34Z 置信度 0.66
• Getting the Best Out of Both Worlds: Algorithms for Hierarchical Inference at the Edge
  We consider a resource-constrained Edge Device (ED), such as an IoT sensor or a microcontroller unit, embedded with a small-size ML model (S-ML) for a generic classification application and an Edge Server (ES) that hosts a large-size ML model (L-ML). Since the…
  crossref Vishnu Narayanan Moothedath, Jaya Prakash Champati, James Gross 2024-02-14T18:49:19Z 置信度 0.82 cs.lgcs.nistat.mlcs.itedge computing
• From Atlas to Actuary: Immunai Expands Immune Mapping with $215M in Series B
  crossref Alex Philippidis 2022-02-14T15:34:46Z 置信度 0.57
• DipDCE: Offloading-Aware Vision Inference in Edge with Concurrent Executions
  Distributed computer vision deployment frameworks aim to reduce end-to-end latency and backbone traffic by distributing computation across edge and cloud tiers. In typical architectures, nodes can process a portion of incoming image streams locally or in an ed…
  crossref Abhinaba Chakraborty, Wouter Tavernier, Mario Pickavet, Didier Colle 2025-10-16T17:35:42Z 置信度 0.82 computer and information sciencescloud computingcomputer sciencecs.dcedge computing
• Cloud-Edge Joint Inference Algorithm for Target Recognition in Cloud-Edge Collaborative Intelligence
  Cloud-edge co-computing has been widely used for real-time processing of image detection scenarios in IoT.The functional limitations of edge devices and how to effectively determine whether an edge device initiates cloud mode is a new challenge.By proposing a …
  crossref Gongyi Xiao, Jing Chen, Wen Li, Hao Sun 等 2023-01-30T09:36:36Z 置信度 0.79 edge computingcloud computingdistributed computingcs.dccs.ni
• PIMPAL: Accelerating LLM Inference on Edge Devices via In-DRAM Arithmetic Lookup
  Deploying Large Language Models (LLMs) on edge devices poses significant challenges due to their high computational and memory demands. In particular, General MatrixVector Multiplication (GEMV), a key operation in LLM inference, is highly memory-intensive, mak…
  crossref Yoonho Jang, Hyeongjun Cho, Yesin Ryu, Jungrae Kim 等 2025-09-15T17:35:41Z 置信度 0.82 computer and information sciencescs.aielectrical engineering, electronic engineering, information engineeringcomputer sciencecryptography and security
• A Cloud-Edge Collaborative Inference System for Data-secure LLM Serving
  The surge in private deployment of large language models (LLMs) driven by open-source advancements has intensified challenges in computational scalability, infrastructure costs, and data privacy. While cloud-edge collaborative inference frameworks alleviate lo…
  crossref Wenjie Chu, Yunfeng Shao, Chunhui Du 2025-09-02T16:19:34Z 置信度 0.82 computer and information sciencesmachine learningcryptography and securitycs.aicomputer science
• Probabilistic edge inference of gene networks with markov random field-based bayesian learning
  Current algorithms for gene regulatory network construction based on Gaussian graphical models focuses on the deterministic decision of whether an edge exists. Both the probabilistic inference of edge existence and the relative strength of edges are often over…
  crossref Yu-Jyun Huang, Rajarshi Mukherjee, Chuhsing Kate Hsiao 2022-11-10T05:37:10Z 置信度 0.79 cs.lgstat.apeess.syartificial neural networksignal processing
• Cloudburst AI: Orchestrating SRE-Driven AI Inference Across Multi-Cloud and Edge Zones
  Artificial Intelligence (AI) workloads are increasingly deployed across heterogeneous infrastructures consisting of public clouds, private clouds, and edge computing environments. However, achieving reliable, cost-efficient, and scalable inference across these…
  crossref Rishiraj Kohli, Mourya Chigurupati, Sivarama Krishna Akhil Koduri, Nagarjuna Nellutla 2026-05-12T19:46:43Z 置信度 0.82 computer and information sciencescs.aicomputer sciencecloud computingscalability
• EdgeRL: Reinforcement Learning-driven Deep Learning Model Inference Optimization at Edge
  Balancing mutually diverging performance metrics, such as, processing latency, outcome accuracy, and end device energy consumption is a challenging undertaking for deep learning model inference in ad-hoc edge environments. In this paper, we propose EdgeRL fram…
  crossref Motahare Mounesan, Xiaojie Zhang, Saptarshi Debroy 2024-12-31T19:23:43Z 置信度 0.82 cs.lgcomputer and information sciencescs.aireinforcement learningcomputer science
• Distributed Mixture-of-Agents for Edge Inference with Large Language Models
  Mixture-of-Agents (MoA) has recently been proposed as a method to enhance performance of large language models (LLMs), enabling multiple individual LLMs to work together for collaborative inference. This collaborative approach results in improved responses to …
  crossref Purbesh Mitra, Priyanka Kaswan, Sennur Ulukus 2025-12-12T18:33:25Z 置信度 0.82 computer sciencecomputer and information sciencescs.aics.lgartificial intelligence
• Low-Latency Neural Inference on an Edge Device for Real-Time Handwriting Recognition from EEG Signals
  Abstract Brain–computer interfaces (BCIs) hold significant promise for restoring communication in individuals with severe motor or speech impairments. Imagined handwriting, as a form of motor imagery, offers an intuitive paradigm for character-level neural dec…
  crossref Ovishake Sen, Raghav Soni, Darpan Virmani, Akshar Parekh 等 2025-08-27T06:24:29Z 置信度 0.82 brain-computer interfacecomputer sciencecomputer and information sciencesartificial intelligenceelectroencephalography
• In-Network Split Inference with Named Data Networking under Lossy Edge Connectivity
  In-Network Computing (INC) is emerging as a key enabler of Sixth-Generation (6 G) systems, allowing programmable network nodes to provide not only connectivity, but also storage and processing across the cloud-to-edge continuum. Machine learning (ML) tasks, pa…
  crossref Marica Amadeo, Claudia Campolo, Antonella Molinaro, Giuseppe Ruggeri 2025-12-22T18:40:10Z 置信度 0.82 computer and information sciencescomputer sciencecs.aiartificial intelligencecs.lg
• AutoScale: Energy Efficiency Optimization for Stochastic Edge Inference Using Reinforcement Learning
  Deep learning inference is increasingly run at the edge. As the programming and system stack support becomes mature, it enables acceleration opportunities in a mobile system, where the system performance envelope is scaled up with a plethora of programmable co…
  crossref Young Geun Kim, Carole-Jean Wu 2020-11-11T16:55:22Z 置信度 0.79 computer and information sciencescomputer scienceelectrical engineering, electronic engineering, information engineeringsignal processingcloud computing
• Speeding up Machine Learning Inference on Edge Devices by Improving Memory Access Patterns using Coroutines
  We demonstrate a novel method of speeding up large iterative tasks such as machine learning inference. Our approach is to improve the memory access pattern, taking advantage of coroutines as a programming language feature to minimise the developer effort and r…
  crossref Bruce Belson, Bronson Philippa 2023-03-16T17:25:23Z 置信度 0.79 computer sciencecs.lgcs.cvcs.clcs.ai
• Neuromorphic Photonic Processors for Ultra-Low-Latency Edge Inference
  Neuromorphic photonic processors are promising direction with regard to realising ultra-low-latency inference at the edge, through the parallelism of neuromorphic architectures with the speed of photonic interconnects. A performance evaluation of these process…
  crossref Bhanu Prakash Reddy Rella, Natalya Yaronova, Sathish Krishna Anumula, Rajesh Gangavarapu 2026-02-16T21:03:12Z 置信度 0.82 neuromorphic engineeringphotonicsedge computingoptoelectronicsneuromorphic computing
• Energy-Efficient Cooperative Inference Via Adaptive Deep Neural Network Splitting at the Edge
  Learning and inference at the edge is all about distilling, exchanging, and processing data in a cooperative and distributed way, to achieve challenging trade-offs involving energy, delay, and accuracy. This calls for a joint orchestration of radio and computi…
  crossref Ibtissam Labriji, Mattia Merluzzi, Fatima Ezzahra Airod, Emilio Calvanese Strinati 2023-10-23T17:54:10Z 置信度 0.79 computer and information sciencescomputer scienceelectrical engineering, electronic engineering, information engineeringsignal processinginformation theory
• Work-in-Progress: Real-Time Deep Neural Inference on Resource-Constrained Edge Devices
  Deep neural networks (DNNs) are now central to perception and control in time-critical cyber-physical systems, yet many mid- and low-tier edge platforms (e.g., single-board computers without GPUs and most microcontrollers) cannot host full models or meet real-…
  crossref Md Tasnim Farhan Fatin, Monowar Hasan 2025-12-31T18:42:18Z 置信度 0.82 computer sciencecs.lgcs.aicomputer and information sciencesartificial neural network
• Edge Intelligence
  As the backbone technology of machine learning, deep neural networks (DNNs) have have quickly ascended to the spotlight. Running DNNs on resource-constrained mobile devices is, however, by no means trivial, since it incurs high performance and energy overhead.…
  crossref En Li, Zhi Zhou, Xu Chen 2018-08-01T15:07:07Z 置信度 0.78 computer and information sciencescomputer sciencecs.lgedge computingcloud computing
• Neuromorphic Wireless Device-Edge Co-Inference via the Directed Information Bottleneck
  An important use case of next-generation wireless systems is device-edge co-inference, where a semantic task is partitioned between a device and an edge server. The device carries out data collection and partial processing of the data, while the remote server …
  crossref Yuzhen Ke, Zoran Utkovski, Mehdi Heshmati, Osvaldo Simeone 等 2024-12-02T18:37:03Z 置信度 0.82 computer and information scienceselectrical engineering, electronic engineering, information engineeringsignal processinginformation theorycs.ni
• Distributing deep learning inference on edge devices
  Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs) are widely used in IoT related applications. However, inferencing pre-trained large DNNs and CNNs consumes a significant amount of time, memory and computational resources. This makes it infe…
  crossref Buddhi Gunarathne, Chiranthana Prabhath, Vinura Perera, Kutila Gunasekara 2020-11-24T22:53:05Z 置信度 0.79 cs.lgcomputer sciencecomputer and information sciencesedge computingartificial neural network
• Classification of Thyroid Carcinoma using Sobel Edge Detection and Adaptive Neuro Fuzzy Inference System Approach
  Bioinformatics applications in the medical world become human needs. Pathologists as analysts required computer-assisted to conduct a diagnosis. This research aims to create an application that could help pathologic to diagnose thyroid cancer. The diagnosis co…
  crossref I. Intan, Y.J.W Soetikno 2020-01-23T22:20:32Z 置信度 0.79 computer scienceeess.ivconvolutional neural networkcs.cvartificial intelligence
• Lightweight prediction based big/little design for efficient neural network inference
  The accuracy improvement of neural networks may be only a few percentage points while the computation effort explodes, as previous less computation-intensive designs can already produce correct results for a large portion of inputs. We employ a lightweight pre…
  crossref Ye Tian, Min Li, Qiang Xu 2019-11-04T14:11:35Z 置信度 0.77 cryptography and securitycs.lgartificial neural networkbenchmarkinterpretability
• Energy-Efficient AI Inference at the Edge: Optimizing Semiconductor Hardware for Small Language Models
  The rapid expansion of artificial intelligence applications across mobile devices, Internet of Things (IoT) platforms, and embedded systems has intensified the demand for efficient on-device inference. While large language models have demonstrated remarkable p…
  crossref Rohit Chandrakant Kulkarni 2026-03-19T07:55:51Z 置信度 0.82 computer sciencecomputer and information sciencesartificial intelligencecs.aics.lg
• Active Inference-Enhanced Reinforcement Learning for Adaptive Service Migration in Edge Computing-Enabled Networks
  With the widespread adoption of edge computing, service migration is critical for meeting real-time computing demands and ensuring service continuity. However, the dynamic and uncertain nature of edge computing-enabled networks, characterized by fluctuating to…
  crossref Yuxia Cheng, Chengchao Liang, Qianbin Chen, F. Richard Yu 2025-09-26T17:34:55Z 置信度 0.82 computer and information scienceselectrical engineering, electronic engineering, information engineeringcloud computingnetworking and internet architectureedge computing
• A Study on Edge Computing-Based Microservices Architecture Supporting IoT Device Management and Artificial Intelligence Inference
  Currently, cloud computing is commonly used for the purpose of transmitting and storing data collected from various IoT devices to the cloud through a network, and providing services that create new values through big data analysis. However, in recent years, t…
  crossref Tai-Gil Kwon, Kwanghyun Ro 2023-03-10T18:20:59Z 置信度 0.79 computer sciencecloud computingedge computingcs.dcdata science
• Joint DNN partitioning and Resource Allocation for Completion Rate Maximization of Delay-Aware DNN inference Tasks in Wireless Powered Mobile Edge Computing
  Abstract With the development of smart Internet of Things (IoT), it has seen a surge in wireless devices deploying Deep Neural Network (DNN) models for real-time computing tasks. However, the inherent resource and energy constraints of wireless devices make lo…
  crossref Xianzhong Tian, Pengcheng Xu, Yifan Shen, Yuheng Shao 2023-06-12T03:15:30Z 置信度 0.79 computer sciencecomputer and information scienceselectrical engineering, electronic engineering, information engineeringsignal processingnetworking and internet architecture
• Dynamic Fuzzy Inference System for Edge Detection of Stone Inscriptions
  The identification of stone inscriptions is of great significance to the study of Chinese characters and the exploration of ancient history. The identification and analysis of the stone inscriptions can determine the age when they belong, and can help to study…
  crossref Jie Song, Jie Wang, Shanshan Li 2019-05-13T12:17:59Z 置信度 0.79 mars exploration programnetworking and internet architecturecloud computingmartianreliability
• Enabling AI Quality Control via Feature Hierarchical Edge Inference
  With the rise of edge computing, various AI services are expected to be available at a mobile side through the inference based on deep neural network (DNN) operated at the network edge, called edge inference (EI). On the other hand, the resulting AI quality (e…
  crossref Jinhyuk Choi, Seong-Lyun Kim, Seung-Woo Ko 2023-10-23T17:54:10Z 置信度 0.79 computer sciencecomputer and information scienceselectrical engineering, electronic engineering, information engineeringsignal processingbrain-computer interface
• Energy-Aware Selective Inference Task Offloading for Real-Time Edge Computing Applications
  IoT has recently witnessed a boom in AI deployment at the edge as a result of the newly developed small size Machine Learning (ML) models and integrated hardware accelerators. Although it brings huge benefits such as privacy-preserving and low-latency applicat…
  crossref Abdelkarim Ben Sada, Amar Khelloufi, Abdenacer Naouri, Huansheng Ning 等 2024-05-22T13:42:36Z 置信度 0.82 computer and information sciencescs.lgcs.aicomputer sciencemachine learning
• Exploring Edge Inference Feasibility of Small Scale Deep Learning Models for Robotic Manipulation
  Large deep-learning models for general-purpose robotic applications rely on powerful cloud computation resulting in high inference latency, computational costs, and network traffic. Despite such requirements, these models exhibit strong anchoring bias to train…
  crossref Rishik R. Tiwari, Daniel T. H. Lai 2025-08-19T18:06:18Z 置信度 0.82 computer and information sciencesartificial intelligencecs.lgcs.aicomputer science
• Towards Safe Online Machine Learning Model Training and Inference on Edge Networks
  With the increasing demand for edge computing in cyber-physical system (CPS) applications, ensuring the safety and reliability of machine learning models running on edge devices during online model training and inference is essential. Although data and model p…
  crossref Md Al Maruf, Akramul Azim, Nitin Auluck, Mansi Sahi 2024-03-19T18:08:18Z 置信度 0.82 computer and information sciencescs.lgcomputer sciencemachine learningelectrical engineering, electronic engineering, information engineering
• Orpheus: A New Deep Learning Framework for Easy Deployment and Evaluation of Edge Inference
  Optimising deep learning inference across edge devices and optimisation targets such as inference time, memory footprint and power consumption is a key challenge due to the ubiquity of neural networks. Today, production deep learning frameworks provide useful …
  crossref Perry Gibson, Jose Cano 2020-10-26T21:19:13Z 置信度 0.79 computer sciencecs.lgcomputer and information sciencescs.aiartificial intelligence
• Agentic CDNs: A Multi-Agent Architecture for Edge-Native AI Inference and Control
  crossref Venkata Gopi Kolla, Chintan Tank, Luc Giavelli 2026-07-22T19:19:38Z 置信度 0.66
• Merging approach of pre-trained deep learning models for edge-cloud collaborative inference
  Artificial Intelligence (AI)-based Internet of Things (IoT) applications benefit greatly from advanced deep learning models. However, the increasing complexity and resource requirements of deep learning models pose challenges to computational efficiency and de…
  crossref Wansong Yan 2024-11-18T16:41:20Z 置信度 0.82 computer scienceartificial intelligencecomputer and information sciencescs.lgelectrical engineering, electronic engineering, information engineering
• Tracy–Widom distribution for the edge eigenvalues of elliptical model
  Abstract In this paper, we study the largest eigenvalues of sample covariance matrices with elliptically distributed data. We consider the sample covariance matrix $Q=YY^{*},$ where the data matrix $Y \in \mathbb{R}^{p \times n}$ contains i.i.d. $p$-dimensiona…
  crossref Xiucai Ding, Jiahui Xie 2025-04-18T09:11:37Z 置信度 0.78 geologyphysicsquant-phmeteoritecs.it
• Fused DSConv: Optimizing Sparse CNN Inference for Execution on Edge Devices
  Accelerating CNN on resource-constrained edge devices is becoming an increasingly important problem with the emergence of IoT and edge computing. This paper proposes an execution strategy and an implementation for efficient execution of CNNs. Our execution str…
  crossref Jia Guo, Radu Teodorescu, Gagan Agrawal 2021-08-02T21:11:07Z 置信度 0.79 computer and information sciencescs.aicomputer sciencedistributed computingcs.cv
• Power-Efficient and Reconfigurable Compute Unit for Multi-Precision AI Inference at the Edge
  crossref Muhammad Hamis Haider, Hao Zhang, Seokbum Ko 2026-06-18T20:06:41Z 置信度 0.66
• A Full System Co-Simulation Platform for Evaluating Edge Machine Learning Inference Using Compute-in-Memory
  crossref Belsen Lee, Tom Springer 2026-07-02T19:41:25Z 置信度 0.66
• GNN-SAMPLER: Accelerating Distributed GNN Inference Sampling at the Edge
  crossref Heng Mao, Yong Guo, Jiawei Liao, Yi Ren 2026-07-06T19:42:40Z 置信度 0.66
• Llm-Guided Training and Llm-Free Inference for Reliable Task Offloading in Edge Computing
  crossref Hao Guo, Kaixiang Xv, Lei Yang 2026-08-04T19:14:37Z 置信度 0.66
• MultiTASC: A Multi-Tenancy-Aware Scheduler for Cascaded DNN Inference at the Consumer Edge
  Cascade systems comprise a two-model sequence, a lightweight model processing all samples and a heavier model conditionally refining harder samples to improve accuracy. By placing the light model on the device side and the heavy model on a server, model cascad…
  crossref Sokratis Nikolaidis, Stylianos I. Venieris, Iakovos S. Venieris 2023-08-28T17:46:48Z 置信度 0.79 computer and information scienceselectrical engineering, electronic engineering, information engineeringcs.aics.lgrobotics
• Modifier guided resilient CNN inference enables fault-tolerant edge collaboration for IoT
  In resource-constrained Internet of Things (IoT) scenarios, implementing robust and accurate deep learning inference is problematic due to device failures, limited computing power, and privacy concerns. We present a resilient, completely edge-based distributed…
  crossref Omid Jamshidi, Mahdi Abbasi, Abbas Ramazani, Atefeh Salimi Shahraki 等 2025-11-27T10:20:56Z 置信度 0.82 computer sciencecomputer and information sciencesartificial intelligencecs.aicloud computing
• FlexEdge: A Hardware-Software Co-Design for Flexible Edge Transformer Inference
  crossref Jiewen Zheng, Zifeng Zhao, Qi Wu, Gengsheng Chen 等 2026-06-18T20:06:41Z 置信度 0.66
• Model-Distributed Inference in Multi-Source Edge Networks
  Distributed inference techniques can be broadly classified into data-distributed and model-distributed schemes. In data-distributed inference (DDI), each worker carries the entire deep neural network (DNN) model, but processes only a subset of the data. Howeve…
  crossref Pengzhen Li, Hulya Seferoglu, Erdem Koyuncu 2023-08-02T17:30:54Z 置信度 0.79 computer and information sciencescs.lgcomputer scienceartificial intelligencecs.ai
• Digital In-Memory Computing to Accelerate Deep Learning Inference on the Edge
  Deploying Deep Learning (DL) models on edge devices presents several challenges due to the limited set of processing and memory resources, and the bandwidth constraints while ensuring performance and energy requirements. In-memory computing (IMC) represents an…
  crossref Stefania Perri, Cristian Zambelli, Daniele Ielmini, Cristina Silvano 2024-07-26T17:22:29Z 置信度 0.82 computer scienceedge computingcomputer and information sciencescloud computingtransformative learning
• Learning Training Samples for Occlusion Edge Detection and Its Application in Depth Ordering Inference
  This paper studies the problem of occlusion edge detection, which is applied to infer the depth order of objects in a monocular image. The key observation is that, given the fixed regression objective, the accuracy of occlusion edge detection is effectively bo…
  crossref Yu Zhou, Jianxiang Ma, Anlong Ming, Xiang Bai 2018-11-30T00:17:38Z 置信度 0.78 computer and information sciencescs.cvcs.lgconvolutional neural networkstat.ml
• Inference Routing Over Multi-Hop Edge Networks
  The emergence of artificial intelligence (AI) has paved the way for ubiquitous intelligent application on edge devices. However, the deep neural networks (DNN) based AI technology suffers from heavy computing burden, which is prohibitive for edge devices as th…
  crossref Ce Xu, Yuan Liu, Jiarong Yang 2025-09-23T17:26:10Z 置信度 0.82 computer and information sciencescomputer sciencecs.lgelectrical engineering, electronic engineering, information engineeringcs.ai
• Fast and Accurate Streaming CNN Inference via Communication Compression on the Edge
  Recently, compact CNN models have been developed to enable computer vision on the edge. While the small model size reduces the storage overhead and the light-weight layer operations alleviate the burden of the edge processors, it is still challenging to sustai…
  crossref Diyi Hu, Bhaskar Krishnamachari 2020-05-21T22:37:09Z 置信度 0.79 computer and information scienceselectrical engineering, electronic engineering, information engineeringsignal processinginformation theorycs.lg
• QoE Inference and Improvement Without End-Host Control
  Network quality-of-service (QoS) does not always translate to user quality-of-experience (QoE). Consequently, knowledge of user QoE is desirable in several scenarios that have traditionally operated on QoS information. Examples include traffic management by IS…
  crossref Ashkan Nikravesh, Qi Alfred Chen, Scott Haseley, Xiao Zhu 等 2018-12-11T01:06:28Z 置信度 0.78 computer and information sciencescomputer sciencecs.aics.lgelectrical engineering, electronic engineering, information engineering
• Optimization of Deep Learning Inference on Edge Devices
  Concerning Artificial Intelligence (AI)-based applications, it is necessary to reduce latency in real-time inference. This paper implements and compares two separate models, Inception V3 and Mobilenet, using Intel Neural Compute Stick (NCS) 2 and Raspberry Pi …
  crossref Endah Kristiani, Chao-Tung Yang, Kieu Lan Phuong Nguyen 2021-04-16T16:50:08Z 置信度 0.79 edge computingartificial neural networkcomputer sciencecs.nics.cv
• HiDP:Hierarchical DNN Partitioning for Distributed Inference on Heterogeneous Edge Platforms
  Edge inference techniques partition and distribute Deep Neural Network (DNN) inference tasks among multiple edge nodes for low latency inference, without considering the core-level heterogeneity of edge nodes. Further, default DNN inference frameworks also do …
  crossref Zain Taufique, Aman Vyas, Antonio Miele, Pasi Liljeberg 等 2025-05-21T17:36:35Z 置信度 0.82 edge computingcomputer and information sciencescs.dcdistributed computingcryptography and security