The emergent large language/multimodal models facilitate the evolution of mobile agents, especially in mobile UI task automation. However, existing evaluation approaches, which rely on human validation or established datasets to compare agent-predicted ...

Web applications have increasingly adopted Deep Learning (DL) through in-browser inference, wherein DL inference performs directly within Web browsers. The actual performance of in-browser inference and its impacts on the quality of experience (QoE) ...

The increasing demand for artificial intelligence and cloud computing has led to skyrocketing energy consumption of data centers (DCs). This paper focuses on tackling this energy challenge through cooling control system optimization, which aims to ...

This paper introduces ChainStream, an LLM-based framework for building and serving context-aware AI agents. Driven by the goal to enable context awareness of LLM agents and flexible information sharing between them, we adopt a stream-based design, in ...

Privacy leakage from user queries is a widely-concerned issue in search engines and chatbot services. Existing solutions based on privacy information removal, obfuscation, and encryption may inevitably hurt service quality or require full trust of the ...

Web is increasingly becoming the primary platform to deliver AI services onto edge devices, making in-browser deep learning (DL) inference more prominent. Nevertheless, the heterogeneity of edge devices, combined with the underdeveloped state of Web ...

In this poster, we introduce a novel dynamic user interface (UI) specifically designed for mobile devices powered by large language models (LLMs) agents. The advent of LLMs has led to a surge in deploying LLM-based agents on personal and Internet of ...

In this paper, a novel health indicator-based decentralized event-triggered optimal fault-tolerant control method is proposed for modular robot manipulators (MRMs). First, the subsystem dynamic model is established by utilizing the joint torque ...

• The motor energy efficiency estimation-based health monitor is designed.
• The value function with health indicator (HI) is proposed to optimize actuator.
• The HI-based switching threshold event-triggering condition is firstly ...

Due to the popularity of deep neural networks (DNNs) and considerations over network overhead, data privacy, and inference latency, there is a growing interest in deploying DNNs to edge devices in recent years. However, the limited memory becomes a major ...

Mobile task automation is an attractive technique that aims to enable voice-based hands-free user interaction with smartphones. However, existing approaches suffer from poor scalability due to the limited language understanding ability and the non-...

AI is making the Web an even cooler place, but also introduces serious privacy risks due to the extensive user data collection. Federated learning (FL), as a privacy-preserving machine learning paradigm, enables mobile devices to collaboratively learn a ...

Seamless cross-edge migration for real-time rendering applications is challenging. The strong interactive nature of real-time rendering applications demands a downtime lower than <inline-formula><tex-math notation="LaTeX">$\text{15}\;\text{ms}$</tex-math><...

Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which aims to trigger misbehavior of neural network models under attacker-controlled conditions. However, most backdoor attacks have to modify the neural network ...

This article proposes a model free position-force control method for uncertain environmental constrained reconfigurable manipulators based on adaptive dynamic programming algorithm. Through the analysis of kinematic uncertainties, an adaptive ...

Deep learning models are increasingly deployed to edge devices for real-time applications. To ensure stable service quality across diverse edge environments, it is highly desirable to generate tailored model architectures for different conditions. ...

In the past few years, Transformer has been widely adopted in many domains and applications because of its impressive performance. Vision Transformer (ViT), a successful and well-known variant, attracts considerable attention from both industry and ...

High-resolution depth estimation, with a minimum resolution of <inline-formula><tex-math notation="LaTeX">$1280\times 960$</tex-math><alternatives><mml:math><mml:mrow><mml:mn>1280</mml:mn><mml:mo>&#x00D7;</mml:mo><mml:mn>960</mml:mn></mml:mrow></mml:math><...

Many activation values of Convolutional Neural Networks (CNNs) are zeros due to ReLU (Rectified Linear Unit), one of the most common activation functions used in modern neural networks. Since ReLU outputs are zero for all negative inputs, existing CNN ...

Crowdsourcing Federated learning (CFL) is a new crowdsourcing development paradigm for the Deep Neural Network (DNN) models, also called "software 2.0". In practice, the privacy of CFL can be compromised by many attacks, such as free-rider attacks, ...

In this paper, an event-triggered-based decentralized tracking control method is proposed for modular robot manipulators (MRMs) using a recurrent neural network (RNN) and neuro-dynamic programming (NDP). The joint torque feedback (JTF) technique ...