Data
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.
AI Overlooks a Key Way People Show Emotion Online
Researchers find that repeated letters and punctuation in social media posts are crucial for sentiment analysis, but many AI models miss their meaning, leading to a new method to improve understanding.
AI Models Learn to Focus on What Matters
A new training-free method helps AI systems identify and prioritize relevant visual and textual evidence, improving accuracy in complex question-answering tasks without any model modifications.
AI Solves Hard Programming Problems by Thinking in Parallel
A new method combines reinforcement learning with multi-threaded reasoning to outperform top AI systems on competitive coding challenges, using millions of tokens per problem without breaking computational limits.
AI Predicts Uncertainty in Sparse Sensor Data
A new method adds noise to sensor inputs, enabling AI to generate reliable confidence intervals for reconstructing complex systems like climate and brain activity—without extra computational cost.
AI Makes Self-Driving Cars See Better in Bad Weather
A new hybrid AI method generates realistic sensor data for rain and snow, helping autonomous vehicles navigate safely without costly real-world testing.
New AI Benchmark Tests Self-Driving Cars in Real-Time Scenarios
A new framework evaluates vision-language models in dynamic driving environments, revealing gaps in current AI's ability to handle unexpected situations and recover from errors.
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.
AI Learns to Focus on What Matters in Time Series Data
A new method helps AI models predict future trends by intelligently compressing historical data, reducing noise and computational costs while improving accuracy.
AI Learns to Balance Speech Sounds and Emotion for Natural Voices
A new training method helps AI generate more natural-sounding speech by teaching it to distinguish between different sounds while capturing emotional nuances, outperforming existing approaches in clarity and speaker similarity.
AI Transforms Library Search from Keywords to Knowledge
A new AI-powered system uses knowledge graphs to help researchers find relevant papers faster and reduce information overload by up to 90%, modernizing digital libraries for the age of big data.
AI Solves Physics Equations Without Retraining
A new method uses diffusion models to solve complex partial differential equations by incorporating physical laws during inference, achieving high accuracy and generalization across unseen parameters in seconds.
AI Routing Success Depends on Hidden System Choices
A new study reveals that how AI systems package their decisions matters more than which model you choose—and getting it wrong can break critical workflows.
AI Models How Cooperation Persists Without Contracts
A new computational framework reveals how reciprocity sustains cooperation in platform ecosystems and multi-agent systems—explaining everything from App Store dynamics to AI coordination.
AI Learns to See Images Like Humans Do
A new method fine-tunes image similarity metrics with human feedback, making AI tools more reliable for creative and practical tasks where personal judgment matters.
AI Spots Hidden IT Problems in Company Documents
A new AI method can detect early warning signs of architectural debt in unstructured business documents, helping organizations avoid costly inefficiencies before they escalate.
Robots Learn Faster with AI-Generated Rewards
A new method uses language and vision models to create automatic feedback, boosting robot success rates by up to 56% without manual tuning—paving the way for more adaptable household assistants.
A New Language Makes AI Reasoning More Accessible
DriftScript simplifies programming for adaptive AI agents, replacing dense symbolic notation with readable code that connects to real-world systems through C, Python, and HTTP interfaces.
AI Memory Retains Past 30 Days with Just 10 Slots
A new AI method compresses daily experiences into a smooth 'movie' of the past, allowing resource-limited devices to recall old information without catastrophic forgetting—and it works with images too.
AI's Hidden Environmental Cost in Materials Science
A new perspective reveals how machine learning in chemistry and materials research is driving up energy consumption—and proposes strategies to make AI-driven discovery more sustainable without sacrificing accuracy.
AI Generates TV-Quality Soccer Commentary
A new AI system can produce live soccer commentary that accurately names players and adds statistical insights, mimicking professional broadcasters for a more engaging viewing experience.
AI Models Learn Tasks, Not Users, for Better Privacy
A new federated learning method trains specialized AI models for specific tasks across distributed data, improving performance by up to 136% when handling multiple or unseen tasks without compromising privacy.
AI's Hidden Climate Cost Revealed in New Study
Climate-focused AI chatbots can consume significantly more energy than generic models, with some designs using over 10 times the power without clear quality gains, challenging their sustainability claims.
AI Still Fails at Women's Health Advice
A new benchmark reveals that even the best AI models struggle with women's health questions, often providing unsafe or incomplete guidance, with equity gaps as a universal blind spot.