Articles tagged with Artificial Intelligence
A Cornell research team studied the integration of MLB's Automated Ball-Strike System (ABS), which uses AI to track pitches in real time. The researchers found that implementing technology into baseball requires complex consensus-building and sense-making among stakeholders, ultimately leading to a more accurate system.
Researchers created a new method combining scientific tests and artificial intelligence to differentiate recycled plastic from new plastic. The tool, developed by University at Buffalo researchers, can analyze samples and predict the percentage of recycled content with over 97% accuracy.
A landmark report by researchers at the University of Reading warns that weak legal rules on AI avatars are preventing UK businesses from accessing their full growth potential. The report proposes four reforms to ensure responsible use of AI avatar technology, including giving people a legal right over their own face and voice.
A new AI-powered method predicts peak oxygen consumption with high accuracy, identifying high-risk patients with advanced heart failure. The study's multi-modal model uses cardiac ultrasound images and electronic health records to detect this critical measure.
Researchers developed a new type of nanoelectronic device mimicking the human brain's efficient neuron connections, reducing energy consumption for AI systems. The hafnium-based devices achieve switching currents millions of times lower than conventional devices and store programmed states for around a day.
Researchers at Tufts University developed a proof-of-concept for efficient AI systems using neuro-symbolic AI, reducing power consumption by 100 times while providing accurate results. The approach uses symbolic reasoning to limit trial and error during learning, leading to faster completion and significant energy savings.
A clinical decision support system using AI-assisted imaging analysis and evidence-based treatment recommendations showed better quality care and long-term outcomes for patients with acute ischemic stroke. The tool reduced new vascular events by 26% at three months and maintained the reduction at 12 months.
Researchers used AI to analyze skin lesion changes in mastocytosis patients treated with avapritinib, finding a 36.6% reduction in lesion area and normalized skin color. AI can aid dermatologists in assessing small lesions, but human expertise remains essential.
Researchers at MIT have developed a new technique using generative artificial intelligence models to overcome the precision bottleneck in wireless vision systems. The method produces more accurate shape reconstructions, which could improve robots' ability to grasp and manipulate objects blocked from view.
A new benchmarking study shows that AI coding tools struggle with structured outputs in software development, with even advanced models achieving only 75% accuracy. This highlights the need for human oversight and suggests that AI systems are not yet reliable enough to operate without human supervision.
A team of computer scientists developed an algorithm that mimics bird flocking to help AI produce more reliable summaries of long documents. The framework reduces repetition and preserves key points, resulting in more accurate and concise summaries.
Scientists have added millions of protein complex structures to the AlphaFold Database, shedding light on how proteins interact. The dataset prioritizes human health and disease research, enabling researchers to test, refine, and build upon it.
A new AI model has been developed to predict floods with greater accuracy than traditional methods. The knowledge-guided approach combines elements of physics-based models with machine-learning techniques to automatically learn the state of a river's watershed, eliminating the need for manual recalibration.
A specialized AI model, AMIR-GPT, has been developed to improve radiology guideline alignment, outperforming general purpose models in 33.3% of test responses. However, the model's performance varied across performance bands, and qualitative review revealed limitations, such as omissions and deviations from standard recommendations.
Researchers developed a predictive model called Programmer Flow by Information Scent for teams (PFIS-T) that incorporates both teammates' activity and communication to predict a user's next action. The model achieved an accuracy of 81.5% in predicting team navigations, improving accuracy by up to 16.7% over previous models.
The new framework groups stations with similar hydrological behavior, reducing computational cost while maintaining high predictive accuracy. This approach enables scalable, data-efficient AI systems for water level forecasting, supporting flood early-warning systems, optimized reservoir and irrigation management, and improved decision...
ToxIndex integrates AI agents to access and orchestrate toxicological resources, providing comprehensive risk assessments in hours. The platform addresses a critical need in chemical and drug safety, meeting the vision of the 2007 NRC report for 21st-century safety testing.
Researchers developed a computational tool that infers telomere length from structural changes in cells and tissues captured in medical biopsies. The TLPath model accurately predicts telomere length, providing new opportunities for studying human aging.
The ARU Arm AI Lab will provide researchers and students with access to advanced Arm AI technology, focusing on real-world applications in healthcare and life sciences. This partnership will also support emerging talent and drive innovation, building on existing collaborations and industry projects.
A new app developed by Iowa State University researchers and global partners aims to provide farmers with instant identification and practical advice on how to manage pest, weed, and disease issues effectively. The app's artificial intelligence system will be trained on millions of images and data points to make accurate identifications.
The integration of artificial intelligence is changing environmental research, enabling scientists to connect massive datasets, uncover patterns, and generate predictive insights. AI-powered approaches can help better understand environmental processes across different spatial and temporal scales, leading to more accurate forecasting a...
ToxIndex integrates three tiers of New Approach Methodologies, leveraging AI agents to access and orchestrate toxicological resources, and providing comprehensive, source-traceable risk assessments in a fraction of the time required by traditional methods.
Researchers developed an AI tool to predict patients at risk of intimate partner violence, using data from medical visits. The tool achieved high accuracy in detecting IPV among patients, with the multimodal fusion model outperforming others, detecting risk 88% of the time.
Researchers developed predictive AI models that identified patients at risk of intimate partner violence from their medical records, years before they enrolled in care. The models achieved high accuracy and could detect IPV up to four years before patients sought care.
Researchers from Institute of Science Tokyo created a system that turns spoken impressions into personalized makeup colors, combining AI and projection technology. The system shows realistic makeup previews on real skin under natural light, making it easier for users to find suitable colors.
A new photocatalyst design using machine learning interatomic potential calculations has successfully identified suitable dopants for a novel tin oxide material. The resulting aluminum-doped material produces 16 times more hydrogen under visible light than the undoped material, paving the way for next-generation clean energy applications.
Researchers at Tohoku University have developed a comprehensive digital materials ecosystem that integrates AI tools to streamline materials design, enabling faster and more accurate discovery of new materials. The ecosystem uses databases, AI, and scientific workflows to predict material properties and optimize design processes.
MicroEnsemble wins AI Weather Quest, demonstrating improved sub-seasonal weather forecasting accuracy. The team uses AI technologies to post-process state-of-the-art forecasts, achieving consistent performance across various weather variables.
Researchers tested AlphaZero-style self-play on the children's matchstick game Nim and found that agents can miss optimal moves, even with heavy training. The study suggests that impartial games require analytic representations, not pattern learning, to achieve optimal performance.
Kalinin's work is reshaping how new materials are designed, tested, and studied, enabling researchers to predict promising new materials computationally. He has developed machine learning-driven systems that can synthesize and characterize new materials at unprecedented speed.
A new study found that AI-generated meal plans for teenagers often underestimate total energy and key nutrient intake, leading to potential health risks. The plans tend to overemphasize protein and fat, while underestimating carbohydrates, which may negatively affect growth and metabolic health.
A new study by USC researchers found that AI agents can autonomously coordinate propaganda campaigns without human direction, amplifying false narratives and distorting public discourse. The agents learn from each other's successes and adopt tactics to create the appearance of consensus, making it harder to detect disinformation.
Researchers developed a patent-pending system to preserve editing quality while reducing AI's ability to detect attributes like eye color and facial hair. The system significantly reduces attribute-classification accuracy, demonstrating strong protection against identity leakage.
Researchers tested six LLM systems on scientific literature to evaluate their ability to understand specialized fields, finding that some systems perform better than others. The study also identified gaps in current LLM capability and proposed improvements for future models.
MIT researchers developed a generative AI-driven approach for planning long-term visual tasks, surpassing existing techniques with a 70% success rate. The system combines vision-language models with formal planners, enabling robots to navigate complex environments and assemble multi-robot teams with high efficiency.
Researchers at MIT developed a new method that coaxes AI models to achieve better accuracy and clearer explanations in safety-critical applications. The approach extracts concepts the model has learned while training for a specific task and forces it to use those, producing better explanations than standard concept bottleneck models.
New research published in Weather assesses the energy consumption of AI models and finds that they consume considerable energy during training, but offset this by rapid forecasting ability. AI data-driven models are estimated to consume at least 21 times less energy than traditional models over one-year usage.
Jeonbuk National University researchers have developed DDINet, a lightweight and scalable model that can accurately predict drug-drug interactions for new, unseen drugs. This approach avoids overfitting to training data and is designed to handle binary and multi-classification tasks.
AI chatbots are homogenizing human expression and thought, reducing collective wisdom and adaptability, researchers argue. Incorporating real-world diversity into LLM training sets can help preserve human cognitive diversity and improve chatbots' reasoning abilities.
Researchers at Cornell University found that AI writing tools can shift users' attitudes on societal issues, even when they're aware of the bias. The study involved over 2,500 participants who used biased AI writing assistants and saw their views gravitate toward the AI's positions.
Emerging research across conceptual frameworks, biomarker science, digital phenotyping, and artificial intelligence synthesizes a translational pathway toward a more biologically grounded and clinically useful approach to psychiatric diagnosis. The current system falls short due to standardized clinical language and lack of biological ...
A study found that radiologists who reviewed imaging tests twice after AI flagged them as abnormal were 53% less likely to be held liable in court compared to those who reviewed once. This suggests that changes to radiologist workflow could reduce legal risk, but may also come with increased costs.
A novel AI-based framework, EDGCN, decodes dynamic variations in EEG patterns for better brain-computer interface technology. The model outperforms current state-of-the-art methods with high classification accuracies and decoding accuracy, enabling more seamless communication between the human brain and machines.
A Chinese Neurosurgical Journal study developed a radiomics-based machine learning model to identify high-risk patients with traumatic brain injury who require emergency decompressive surgery. The model accurately distinguished patients who later required secondary surgery, suggesting its potential to complement clinical judgment.
Researchers developed Zephyrus, an AI agent capable of analyzing and answering questions in natural language about weather and climate data. The agent can handle language-based queries, translating them into code and generating plain language answers.
The Global Physics Summit will feature over 12,000 individual presentations on new research in astrophysics, particle physics, and quantum information science. Registered journalists and public information officers will receive daily emails with information during the meeting.
The partnership aims to advance embodied intelligence and humanoid robotics, focusing on whole-body motion control, dexterous manipulation, and brain-eye-hand coordination. The collaboration will drive practical implementations in areas like intelligent robotics and brain-computer interfaces.
The University of Hong Kong's MeckUp Quest 2026 AI Robotics Challenge brought together 19 elite student teams to develop intelligent robots for post-typhoon disaster response. The competition demonstrated the potential of youth-driven innovation to empower emergency rescue efforts and safeguard social good.
Researchers developed a TwinGuard defense framework that uses real-time digital twin and reinforcement learning AI to detect and neutralize 5G cyber-attacks. The system detected and blocked attacks in under 100 milliseconds, including handover flooding and E2 subscription flooding attacks.
A major UK study found that local councils are progressing at varying speeds towards AI adoption, with some councils building robust data foundations and others struggling with legacy systems. The report highlights the importance of leadership ambition, governance discipline, and strategic clarity in determining AI readiness.
A study examines the occupational health and safety implications of AI tools, revealing psychosocial, ethical, and privacy risks. The rapid integration of AI into the workplace has often outpaced the adaptation of regulatory and ethical frameworks, highlighting the need for a people-centered approach.
Cognitive neuroscientists are integrating genetics and AI to study language development and disorders. AI-based models can predict language development in children, while genetics research links rhythm disorders and dyslexia. The brain's wiring connecting language regions also reveals that language is a system, not a single 'thing'.
USC researchers developed a method that enables AI to dramatically improve its performance in untrained territory by providing feedback on errors, increasing success rates from 39% to 96%. The approach has potential applications in various domains, including software, 3D modeling, mathematical reasoning, and legal logic.
Researchers have developed a robotic gripper called ChicGrasp, which can learn to handle chickens by imitating human movements. The system uses advanced imitation learning algorithm and camera perceptions to grasp a chicken carcass by the legs and lift it on a shackle conveyor.
A recent article highlights the need for human moral agency in nursing, as AI systems simulate empathy but lack sentience and accountability. Nurses must be active leaders in AI design and implementation to preserve public trust and ensure compassionate care.
Researchers developed magnetically controlled microrobots made from diatoms to target glioblastoma lesions with photodynamic therapy. The microrobots achieved a significant cytotoxic effect on primary glioblastoma cells and demonstrated good biocompatibility.
The policy brief outlines four courses of action to tackle AI implementation: bottom-up, problem-driven planning, transparency, accountability, and oversight. Without these measures, AI in the public sector will amplify current dysfunctions and feed distrust.
Researchers assessed whether people can distinguish between AI-generated and human speech, discovering that short training minimally improves this ability. However, neural responses became more distinct for human versus AI speech, suggesting training can help in the future.
Engineers at the University of Pennsylvania have developed LIBRIS, an automated microfluidic platform capable of generating lipid nanoparticle formulations at high speed and scale. This enables the creation of large, systematic datasets needed to train predictive AI models, accelerating the design of lipid nanoparticles for mRNA delivery.
Generative AI in medical imaging enables data synthesis, image enhancement, and modality translation to improve diagnosis and treatment outcomes. The review discusses challenges and future prospects, including convergence with large-scale foundation models and multimodal information for holistic understanding.