About
Research & Development
Building Trust in Decentralized AI Systems: A New Defense Against Malicious Actors
TLDR: This research introduces an online decentralized federated multi-task learning algorithm designed to provide personalized AI models and resilience against Byzantine attacks in cyber-physical...
Research & Development
Unveiling Hidden Scenes: One-Shot Occlusion Removal from Glass
TLDR: A new deep learning model called "Seeing through Unclear Glass" introduces an all-in-one framework for removing various types of contaminants (dirt, raindrops, muddy...
Research & Development
How AI-Driven Network Adaptation Fosters Cooperation in Complex Systems
TLDR: A new study introduces a Q-learning-based adaptive rewiring mechanism for multi-agent systems, allowing agents to optimize both strategies and social connections. This approach,...
Research & Development
The Economic Landscape Reshaped by AI Agents
TLDR: The research paper "An Economy of AI Agents" explores the profound economic implications of autonomous AI agents, which are expected to be widely...
Research & Development
Goal-Oriented Semantic Communication: A New Framework for Efficient Image Transmission
TLDR: SC-GIR is a novel framework for goal-oriented semantic communication that uses self-supervised learning and invariant representation to efficiently transmit only task-essential information for...
Research & Development
Advancing Respiratory Sound Event Detection with Graph Neural Networks and Anchor Intervals
TLDR: EZhouNet is a new deep learning framework that uses Graph Neural Networks (GNNs) and anchor intervals to detect abnormal respiratory sound events. It...