Edge AI

Follow this topic Ask about this topic

Edge AI studies how to run and learn with AI close to where data is produced, from microcontrollers and wearables to robots, industrial systems, and nearby edge servers. Common approaches include quantization, pruning, and distillation; hardware-aware runtimes for CPUs, GPUs, and NPUs; and split inference or federated learning across devices and cloud services. Evaluation must balance task quality with latency, energy use, memory, and reliability on real hardware, often using vision, speech, sensor, and language tasks. A central challenge is making systems adapt to changing workloads and conditions while remaining safe and dependable across heterogeneous devices, without assuming that compression or simulated performance will translate to field results.

Latest papers

35 papers3 papers in the last four weeks, down 57% on the four weeks before. 0.0% of all new papers.

From Acoustic Sensing to Physical Actions: A Comprehensive Survey of Security Risks in Edge-Deployed Audio LLM-Based Agents
Oct 11, 2026Binhong Wang, Haidong Kang, Yanfeng Zhang +3LLM Agent Security Edge AI
Northeastern University, China · Department of Computer Science, Hong Kong Baptist University, Hong Kong · Institute of Intelligent Manufacturing, Nanjing Tech University, Nanjing, China +1
DCM-SAM: Defect-Conditioned Mixture of LoRA Experts for NPU-Deployed AM Defect Segmentation
Sep 30, 2026Md Mushfiqur Rahaman, Md Mahedi Hasan, Imtiaz Ahmed +1Low-Rank Adaptation Mixture of Experts
Department of Industrial and Management Systems Engineering West Virginia University, Morgantown, WV · School of Mathematical and Data Sciences West Virginia University, Morgantown, WV · Lane Department of Computer Science & Electrical Engineering West Virginia University, Morgantown, WV
EdgeVLN: Runtime-Aware Deployment Ready Quantized Vision Language Navigation Model
Sep 28, 2026Rithvik Jonna, Man Namgung, Aakash Gurram +1Visual Navigation VLM Quantization
Department of Electrical and Computer Engineering Johns Hopkins University · Laboratory for Computational Sensing and Robotics Johns Hopkins University
TerMeZO: Ternary Sparse Zeroth-Order Optimization for Fine-tuning BitNet Models at the Edge
Sep 27, 2026Houssem Sifaou, Prabodh Katti, Bipin Rajendran +1Memory-Efficient Fine-Tuning Zeroth-Order Optimization
Institute for Intelligent Networked Systems, Northeastern University London, UK
NAVIR: Neuromorphic Audio-Visual Speech Recognition for Robust Human-Robot Interaction on Edge Hardware
Sep 21, 2026Leonidas Delimpasis, Panagiota Moraiti, Antonis Porichis +2Visual Speaker Recognition Automatic Speech Recognition
Plaixus Ltd., Spyrou Patsi 62, 11855, Athens, Greece · Tech Hive Labs, 280 Kifisias Ave., 152 32 Halandri, Greece · AI Innovation Centre, University of Essex, Little Abington, CB21 6GP Cambridge, U.K.
PAANI : On Device Visual Evidence Fusion and Explainable Guidance for River Robot Simulation
Sep 17, 2026Savio Cardoz, Santhiya RajanRobotics Robotic Perception
ACL Digital, Pune · Multiverse Computing, Spain · Ph.D. (Part-time) Research Scholar, PSG College of Technology, Coimbatore, India
SH-WRNN: Implicit Spherical Harmonics Weight Field Routing Neural Networks for Asymmetric Edge Intelligence
Sep 13, 2026Zhibin Jiao, Xiangjing AnEfficient Neural Network Inference Dynamic Neural Networks
Independent Researcher Team
An Affordable AI-Integrated Smart Cane for Multimodal Mobility Assistance of Visually Impaired Users
Sep 12, 2026Ali Akarma, Adeel Ahmad, Toqeer Ali SyedVisually Impaired Navigation Assistance Assistive Robotics
AI Center, Faculty of Computer and Information Systems, Islamic University of Madinah, Madinah 42351, Saudi Arabia · AI V&V Lab, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi Arabia
Distilling Vision-Language Models for On-Device Fire Understanding
Sep 5, 2026Mohammad Kazzazi, Zixuan Liu, Siavash KhajaviVLM Distillation Efficient VLM Inference
EPFL, Lausanne, Switzerland · Detectium, Espoo, Finland
GaLe: memory-efficient Global Approximate and Local Exact features
Sep 2, 2026Alberto Ancilotto, Elisabetta FarellaMemory-Efficient Inference Edge AI
Fondazione Bruno Kessler (FBK), Trento, Italy
A-MADiff: Attention-Guided Multi-Agent DRL with Diffusion Policies for Memory-Aware Task Orchestration in Mobile AIGC Networks
Aug 29, 2026Chongzhi Wu, Zhengtao Li, Jiawen Kang +4Multi-Agent Orchestration Edge AI
School of Automation, Guangdong University of Technology, Guangzhou 510006, China · Department of Computer Science, City University of Hong Kong, Hong Kong · School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China +3
DART-FL: Burst-Aware Multitask Federated Learning under Dynamic Inference Demand at the Edge
Aug 27, 2026Yiming Xie, Pinrui Yu, Geng Yuan +2Federated Learning Edge AI
Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA · School of Computing, University of Georgia, Athens, GA, USA
Cognitively-Grounded On-Device Runtime Learning for Ground Robots in Unknown Physical Environments
Aug 25, 2026Yihao Cai, Yanbing Mao, Christian LebiereRobot Learning Continual Robot Learning
Department of Electrical and Computer Engineering, Wayne State University, Detroit, MI, USA · Engineering Technology Division, Wayne State University, Detroit, MI, USA · Department of Psychology, Carnegie Mellon University, Pittsburgh, PA, USA
A Generalized Optimization Engine (GOE) for Edge AI Inference Acceleration
Aug 19, 2026Venkat R. Dasari, Jakob A. Adams, Vinod K. Mishra +1Efficient Neural Network Inference Edge AI
DEVCOM Army Research Laboratory Aberdeen Proving Ground, MD, USA · University of West Florida Pensacola, FL, USA
Large Models for Small Devices: Recent Advances and Empirical Analysis of Edge AI Deployment
Aug 16, 2026Subhransu Das, Jiaming Cheng, Arnav Kumar +6Edge AI Model Compression
The Ohio State University, Department of Computer Science and Engineering, Columbus, OH, USA
TS-MAMP: A Remanufactured Agricultural Robot with Second-Life EV Components and NMS-Free On-Device Weed Detection
Aug 3, 2026Weijie Shi, Zicheng Xu, Zhenbang Cheng +3Weed Detection Object Detection
School of Mechanical and Automotive Engineering, West Anhui University, Lu'an, 237000, China · School of Automation, Nanjing University of Information Science and Technology, Nanjing, 210000, China · School of Engineering, Westlake University, Hangzhou, 310030, China
Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligence
Jul 23, 2026Jay Gor, Karm Dave, Akshita Abrol +3Efficient Multimodal Inference VLM Quantization
Nirma University · Singapore Institute of Technology, Singapore · Department of CE-AI and Big Data, Marwadi University
Clustered Edge Intelligence: Beyond Just Convergence of Edge Computing and AI
Jul 23, 2026Chinmaya Kumar Dehury, Boris Sedlak, Alaa Saleh +4Edge-Cloud Computing Edge AI
Department of PComputer Science, IISER Berhampur, Odisha, India · Distributed Systems Group, TU Wien, 1040 Vienna, Austria. · Department of Computer Science, University of Helsinki, 00100 Helsinki, Finland +4
Edge Intelligence in Civil Aviation: Paradigms, Techniques, and Applications
Jul 22, 2026Wenbin Li, Zhongtian Liao, Bolin Liu +4Edge Inference Edge Computing
China Southern Digital Intelligence Technology (Guangdong) Co., Ltd. China Southern Airlines Co., Ltd. Guangzhou, China
NEUROSYMLAND: Neuro-Symbolic Landing-Site Assessment for Robust and Edge-Deployable UAV Autonomy
Jul 2, 2026Weixian Qian, Tianyi Yang, Sebastian Schroder +5Aerial Robotics Neuro-Symbolic Reasoning
School of Computing, Macquarie University, Sydney, NSW, Australia. · Department of Computer Science, University of California, Santa Barbara, CA, USA. · Anitron
From Prompt to Service: An SLM-Based Agent Orchestration Gateway for AI-Driven Virtual Worlds
Jun 2, 2026Louis Nisiotis, Aimilios HadjiliasiLLM Agent Orchestration Small Language Models
Department of Computing, Engineering and Mathematics UCLan Cyprus
The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution
May 26, 2026Deepak Panigrahy, Aakash TyagiEdge AI
Independent Researcher Bentonville, USA · Texas A&M University Dept. of Computer Science and Engineering College Station, Texas, USA
PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligence
May 18, 2026Zile Wang, Qianli Liu, Kaibin Guo +4Multi-Agent Collaboration LLM Agents
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong · School of Software Engineering, Sun Yat-Sen University, China
Agentic Performance at the Edge: Insights from Benchmarking
May 11, 2026Shiqiang Wang, Herbert WoisetschlägerLLM Agent Evaluation AI Agent Evaluation
University of Exeter · Exeter, United Kingdom · Technical University of Munich +1
ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device
May 5, 2026Mergen Nachin, Digant Desai, Sicheng Stephen Jia +36Heterogeneous Computing Edge ML
Meta · Work done while at Meta.
Hierarchical Federated Learning for Networked AI: From Communication Saving to Architecture-Aware Design
May 1, 2026Seyed Mohammad Azimi-Abarghouyi, Mehdi Bennis, Leandros TassiulasHierarchical Federated Learning Communication-Efficient Distributed Training
Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden · Centre for Wireless Communications, University of Oulu, Oulu, Finland · Department of Electrical Engineering, Yale University, New Haven, USA
Edge AI Deployment Beyond Models: A BSP-Aware Systems Framework for Industrial Embedded Platforms
Apr 20, 2026Pitchai Muthu MEdge Inference Edge AI
Embedded & IoT Software Team Lead Advantech Industrial Computing India Pvt. Ltd., India
Multi-Agent Object Detection Framework Based on Raspberry Pi YOLO Detector and Slack-Ollama Natural Language Interface
Apr 14, 2026Vladimir Kalušev, Branko Brkljač, Milan BrkljačMulti-Agent Orchestration LLM Agent Orchestration
The Institute for Artificial Intelligence Research and Development of Serbia Fruškogorska 1, 21000 Novi Sad, Republic of Serbia · Department of Power, Electronic and Telecommunication Engineering Faculty of Technical Sciences, University of Novi Sad Trg Dositeja Obradovića 6, 21000 Novi Sad, Republic of Serbia · Faculty of Finance, Banking and Auditing, Alfa BK University Bulevar maršala Tolbuhina 8, 11070 Belgrade, Republic of Serbia
Towards Edge Intelligence via Autonomous Navigation: A Robot-Assisted Data Collection Approach
Apr 4, 2026Tingting Huang, Yingyang Chen, Sixian Qin +3Robotic Data Collection Robot Navigation
College of Information Science and Technology, Jinan University, Guangzhou 510632, China · College of Physics and Information Engineering, Fuzhou University, Fuzhou 350108, China · School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, China +1
Position Paper: From Edge AI to Adaptive Edge AI
Mar 31, 2026Fabrizio Pittorino, Manuel RoveriEdge AI Adaptive Inference
Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, Italy

Oct 11, 2026J/K move · Enter open · S save

From Acoustic Sensing to Physical Actions: A Comprehensive Survey of Security Risks in Edge-Deployed Audio LLM-Based Agents

Binhong Wang, Haidong Kang, Yanfeng Zhang, Hong-Ning Dai+2

Northeastern University, China · Department of Computer Science, Hong Kong Baptist University, Hong Kong · Institute of Intelligent Manufacturing, Nanjing Tech University, Nanjing, China+1

LLM Agent Security Edge AI Adversarial Attacks

Open paper AskPDF arXiv

Audio Large Language Models (Audio LLMs) are embedded in agents for smart homes, vehicles, wearables, and embodied systems, where acoustic inputs can propagate from perception into persistent state and consequential execution. This setting extends security analysis beyond model behavior to the system conditions that determine how acoustic inputs can influence agent behavior and external actions. Existing surveys examine acoustic security, LLM-based agents, and edge deployment in isolation, leaving their security interactions in deployed Audio LLM-based agents insufficiently characterized. This survey introduces an Acoustic Sensing-to-Action (S2A) system model that traces these security implications along the path from acoustic sensing to external execution, while accounting for edge-cloud runtime and lifecycle transformation. We use the model to synthesize attacks, defenses, and evaluation methods across the acoustic, agent, and edge-system literature. The synthesis shows that security gaps can emerge within components and at the transitions between stages, where protections developed for one stage do not necessarily provide end-to-end assurance in the deployed system. These findings motivate security evaluation that follows acoustic influence from sensing to action across persistent state, system boundaries, and changing deployment conditions in real-world agents.