Edgefm: Leveraging foundation model for open-set learning on the edge
Deep Learning (DL) models have been widely deployed on IoT devices with the help of
advancements in DL algorithms and chips. However, the limited resources of edge devices …
advancements in DL algorithms and chips. However, the limited resources of edge devices …
What do Blind and Low-Vision People Really Want from Assistive Smart Devices? Comparison of the Literature with a Focus Study
Over the last decade there has been considerable research into how artificial intelligence
(AI), specifically computer vision, can assist people who are blind or have low-vision (BLV) …
(AI), specifically computer vision, can assist people who are blind or have low-vision (BLV) …
Cross-Modality Graph-Based Language and Sensor Data Co-Learning of Human-Mobility Interaction
Learning the human--mobility interaction (HMI) on interactive scenes (eg, how a vehicle
turns at an intersection in response to traffic lights and other oncoming vehicles) can …
turns at an intersection in response to traffic lights and other oncoming vehicles) can …
A Review on Edge Large Language Models: Design, Execution, and Applications
Large language models (LLMs) have revolutionized natural language processing with their
exceptional capabilities. However, deploying LLMs on resource-constrained edge devices …
exceptional capabilities. However, deploying LLMs on resource-constrained edge devices …
Resource Optimization for Semantic-Aware Networks with Task Offloading
The limited capabilities of user equipment restrict the local implementation of computation-
intensive applications. Edge computing, especially the edge intelligence system, enables …
intensive applications. Edge computing, especially the edge intelligence system, enables …
VELO: A Vector Database-Assisted Cloud-Edge Collaborative LLM QoS Optimization Framework
The Large Language Model (LLM) has gained significant popularity and is extensively
utilized across various domains. Most LLM deployments occur within cloud data centers …
utilized across various domains. Most LLM deployments occur within cloud data centers …
TinyVQA: Compact Multimodal Deep Neural Network for Visual Question Answering on Resource-Constrained Devices
Traditional machine learning models often require powerful hardware, making them
unsuitable for deployment on resource-limited devices. Tiny Machine Learning (tinyML) has …
unsuitable for deployment on resource-limited devices. Tiny Machine Learning (tinyML) has …
AI-Enabled Smart Glasses for People with Severe Vision Impairments
B Gamage - ACM SIGACCESS Accessibility and Computing, 2024 - dl.acm.org
Over the last decade, there has been significant research on how smart assistive devices
with artificial intelligence (AI) built into them can assist people with severe vision …
with artificial intelligence (AI) built into them can assist people with severe vision …
Efficient Visual Question Answering on Embedded Devices: Cross-Modality Attention With Evolutionary Quantization
A Mishra, A Agarwala, U Tiwari… - … on Image Processing …, 2024 - ieeexplore.ieee.org
Visual Question Answering (VQA) lies at the intersection of vision and language domains
necessitating learning representations from multiple modalities. While the model …
necessitating learning representations from multiple modalities. While the model …
BlabberSeg: Real-Time Embedded Open-Vocabulary Aerial Segmentation
Real-time aerial image segmentation plays an important role in the environmental
perception of Uncrewed Aerial Vehicles (UAVs). We introduce BlabberSeg, an optimized …
perception of Uncrewed Aerial Vehicles (UAVs). We introduce BlabberSeg, an optimized …