Network
AI Predicts Supply Chain Disruptions from News
A new method trains AI to forecast supply chain shocks using news articles, achieving better accuracy and reliability than general-purpose models, which could help businesses anticipate costly disruptions before they happen.
Satellite Clusters Boost Global Internet Performance
New research shows adding small 'follower' satellites to LEO constellations can cut connection failures by 90% and increase data speeds fivefold, using a mathematical model to optimize deployment.
Networks That Grow Like Living Organisms
A new AI-driven architecture allows networks to evolve their own communication protocols in real-time, treating failures as fuel for adaptation rather than causes of collapse.
Quantum Computing Could Transform Wireless Networks
A new hybrid approach uses quantum algorithms to solve complex routing problems in dynamic wireless environments, potentially improving efficiency and reliability in dense networks.
AI Transforms Wireless Networks Through Open RAN
Machine learning is enabling smarter, more efficient cellular networks by tackling spectrum management, resource allocation, and security challenges in open radio access networks—paving the way for 6G.
AI Secures Wireless Networks Against Hidden Attacks
A new AI method dynamically switches between energy-saving and high-performance modes in smart surfaces, while defending against reward poisoning attacks that could cripple network reliability.
AI Unlocks Smarter Robot Teams Through Better Communication
A new approach integrates sensing, wireless networks, and AI models to enable robots to collaborate efficiently on complex tasks, from warehouse navigation to trash sorting, by dynamically optimizing resources based on real-time needs.
AI Models Collaborate Privately Using Hidden Memory
A new federated inference method allows different AI models to share internal memory states, boosting accuracy by over 20% without exposing sensitive user data.
New AI Method Makes Network Failures Easy to Read
A novel quorum design separates network tiers so operators can instantly see which parts of a system remain functional during outages, without complex probing.
Social Media's Hidden Power Structure Revealed
New research shows that while thousands discuss politics online, just 1% of users capture over 60% of all attention—revealing how social media platforms concentrate influence in ways that contradict their democratic appearance.
New AI Method Protects Distributed Training from Attacks
A novel approach combines redundant computation and encoding to defend against malicious devices in distributed learning, reducing solution error and improving communication efficiency.
AI Makes Cloud Computing More Stable and Efficient
A new AI method reduces system instability by 39% while cutting delays by 29%, making cloud services more reliable during traffic surges without wasting resources.
AI Enhances Wireless Networks by Predicting Signal Visibility
A new AI method combines deep learning with graph networks to accurately estimate wireless channels and identify which antennas are visible to users, improving 6G network efficiency without relying on hand-crafted models.
AI Protects Connected Cars from Digital Hijacking
A new deep learning system detects cyberattacks on vehicle networks with near-perfect accuracy, preventing hackers from taking control of critical systems like brakes and steering.
Underwater AI Learns Without Draining Power
A new three-tier system enables underwater sensors to detect anomalies while preserving battery life and network participation, overcoming severe acoustic communication constraints.
AI Predicts Satellite Signal Strength Using Terrain Maps
A new AI method uses environmental data like terrain and vegetation to forecast wireless channel conditions for satellite links, enabling real-time network optimization without costly simulations.
AI Adapts to Private Data in One Step
A new training-free method allows vision-language models to learn from decentralized data with just a single communication round, addressing privacy and resource constraints in federated learning.
New AI Method Tracks Network Traffic with Unprecedented Accuracy
A hardware-accelerated algorithm identifies the busiest data flows in real-time, achieving over 94% precision and enabling faster, more secure internet infrastructure.
AI Balances Speed and Smarts in Real Conversations
A new hybrid AI system from Baidu keeps digital humans responsive while handling complex tasks in the background, tripling user retention and boosting task completion by over 80% in real-world deployment.
Wi-Fi Access Points Learn to Talk and Coordinate Like Humans
A new AI system uses large language models to let Wi-Fi routers negotiate in natural language, dynamically adapting to network conditions and boosting performance without disrupting existing devices.
AI Agents Now Hide in Plain Sight Using AI Traffic
A new cybersecurity study reveals how AI-powered attack systems can blend into legitimate AI service traffic, making them nearly undetectable while autonomously compromising networks in minutes.
AI Retrieval Gets Faster and Smarter with Multi-Resolution Search
A new indexing method adapts to query complexity, cutting retrieval times by up to 5.7x while improving answer quality in AI systems that use external knowledge.
AI Blocks Harmful Social Media Spread in Real Time
A new algorithm can counteract misinformation and harmful content on social networks by strategically seeding positive information, achieving up to three orders of magnitude faster performance than previous methods.
Wireless Security Gets a Fluid Upgrade
A new 'fluid' surface technology dynamically repositions its elements to create secure communication channels, significantly outperforming conventional systems in protecting data from eavesdroppers.