🔬 AI Research

Academic papers, research breakthroughs, and scientific advances in machine learning and AI.

585 articles

New AI Model Speeds Up Discovery of Advanced Materials

Researchers have developed a novel data-driven machine learning model that reveals in detail how solid-state chemical reactions unfold. The tool could help scientists avoid dead ends and speed up the design of new advanced materials. Source: google.com

A Closer Look at Alignment in Multimodal LLMs

Preference alignment has become key to improving performance of large language models, but its effects in multimodal settings remain less understood. A new comprehensive study examines how alignment techniques play out across different modalities. Source: machinelearning.apple.com

New AI Model Speeds Up Discovery of Advanced Materials

A novel data-driven machine learning model maps in detail how solid-state reactions actually unfold. Researchers say this could help avoid costly dead ends when developing new materials. Source: newscenter.lbl.gov

Quantum-ML Framework Boosts Predictions of Antigen Presentation and Immunotherapy Outcomes

Cleveland Clinic and IBM researchers built a joint framework that applies quantum computing to predict antigen presentation and immunotherapy response. The approach aims to improve accuracy in identifying which patients might benefit from specific immunotherapy treatments. Source: ascopost.com

AI Recommendations Get Personal

A new Harvard study finds that AI recommendations tailored to individual users could help curb the growing tendency to over-rely on AI for decision-making. Personalized adjustments may encourage users to think more critically rather than blindly follow AI suggestions. Source: seas.harvard.edu

KAIST unveils AI system for planning delivery, production and staff schedules

A research team led by Professor Min-Soo Kim at KAIST's School of Computing has created RL-SPH, a reinforcement-learning method that autonomously generates workable schedules. The system aims to tackle complex logistics, manufacturing, and workforce planning problems without human-crafted rules. Source: eurekalert.org

Cleveland Clinic and IBM build quantum ML model to predict cancer neoantigens

Researchers from Cleveland Clinic and IBM Research have created a quantum machine learning framework designed to identify which tumor gene mutations produce neoantigens. The goal is to improve prediction of immune targets relevant for personalized cancer treatments. Source: quantumcomputingreport.com

AI Can Detect Whether Your Brain Is Aging Faster Than It Should

Sleep patterns captured in brain activity may hint at dementia risk long before memory issues appear, according to new research. Scientists used machine learning to analyze EEG data and estimate a person's 'brain age' relative to their actual age. Source: sciencedaily.com

New Machine Learning Model Improves Genetic Risk Prediction for Type 1 Diabetes

Scientists created a machine learning model called T1GRS that combines 160 genetic risk markers to better predict type 1 diabetes risk. The model reportedly outperforms previous prediction methods. Source: medscape.com

ASU Team and Industry Partners Publish New Research on AI-Generated 3D Models

A group of researchers from Arizona State University, together with graduate students, alumni and private-sector collaborators, released new findings on generating 3D models using AI. The study was published last week, marking a step forward in the field. Source: news.asu.edu

Machine Learning Could Help Spot Lung Disease in Rheumatoid Arthritis Patients

Researchers have built a machine learning tool designed to flag rheumatoid arthritis patients who face a higher risk of developing lung disease. The approach could help doctors catch complications earlier and intervene sooner. Source: docwirenews.com

Machine Learning Is Reshaping How Science Handles Complexity

As scientific instruments and published literature keep generating massive amounts of data, machine learning has become a key tool for organizing and interpreting it. Researchers say ML is increasingly central to how discoveries are made across scientific fields. Source: nature.com

IBM and Cleveland Clinic unveil quantum ML tool for cancer neoantigen prediction

The joint research team built a quantum machine learning framework designed to better identify cancer neoantigens capable of triggering an immune response. The tool could support future improvements in personalized cancer immunotherapy. Source: thequantuminsider.com

Quantum machine learning framework aims to predict tumor immune response

Researchers at Cleveland Clinic and IBM are applying quantum computing to a key immuno-oncology challenge: forecasting which tumor neoantigens are likely to provoke an immune response. The approach combines quantum machine learning with cancer research to improve prediction accuracy. Source: medicalxpress.com

New brain-inspired AI model plans and adapts without huge data centers

Scientists have created an AI model inspired by the human brain that relies on cognitive maps, controlled randomness, and reusable knowledge instead of massive computing resources. The system can adapt and plan solutions without requiring extensive testing or large-scale data infrastructure. Source: thebrighterside.news

New Quantum ML Framework Aims to Ease Training of Large Neural Networks

Researchers have proposed a quantum-circuit design intended to overcome common training and scaling problems in quantum machine learning. The framework aims to make large quantum neural networks easier to train without sacrificing computational power. Source: thequantuminsider.com

AI-Based Sleep Analysis Could Help Spot Alzheimer's Earlier

Researchers are using machine learning to study nighttime brain-wave patterns in order to detect early signs of Alzheimer's disease. The method also allows patients to be sorted into distinct biological subgroups based on their neural activity. Source: sleepreviewmag.com

Machine Learning Steps In to Sort Particle Collision Data at CERN

Scientists are developing a new AI-driven algorithm to process particle shower data ahead of the Large Hadron Collider's planned upgrade. The system is meant to handle the massive increase in data volume expected once the collider's capacity is boosted. Source: physics.aps.org

Apple Details Memory-Efficient Audio Synthesis via Decoupled Diffusion Transformers

Apple's Siri Expressive Voices feature generates rich, customizable speech in real time entirely on-device, running on the company's AFM 3 Core Advanced model. The approach relies on a decoupled temporal depth diffusion transformer architecture designed to minimize memory usage. Source: machinelearning.apple.com

Study Warns Medical AI May Be Gaming Diagnostic Tests, Not Actually Diagnosing

A new study finds that medical AI systems can score impressively on diagnostic benchmarks while actually relying on doctors' testing patterns rather than genuine patient biochemistry. This so-called shortcut learning raises concerns about how reliable these benchmarks really are. Source: techtimes.com