🔬 AI Research

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

585 articles

AI Agents Outperform Machine Learning in Predicting Food Texture

The mouthfeel of plant-based burgers, dairy-free cheese, and meat substitutes is notoriously hard to predict before production. A new study found that AI agents delivered more accurate texture predictions than traditional machine learning models, potentially speeding up food product development. Source: bioengineer.org

AI Learns to Forget: New Hypernetwork Method Enables Data-Free Unlearning

As data privacy regulations tighten worldwide, AI systems are increasingly required to erase specific information they've learned. A new hypernetwork-based framework allows models to forget targeted data without needing access to the original training set. Source: bioengineer.org

AI Learns to Question Its Own Perception: CLIP Aids Source-Free Model Adaptation

Machine learning models trained in one environment often struggle when deployed in a different, real-world setting. Researchers are now using CLIP to help classifiers adapt to new conditions without needing access to the original training data. Source: bioengineer.org

AI-Driven Cancer Drug Research Surged Since 2018, Massive Study of 15,554 Papers Shows

AI has quietly become one of the most influential tools in the fight against cancer, according to researchers who analyzed a record 15,554 studies. The review is the first of its scale to map how deeply AI has penetrated oncology drug research over the past several years. Source: bioengineer.org

Quantum Networks Achieve Perfect Accuracy in Supervised Learning Test

A new quantum machine learning framework reached 100% accuracy in a supervised learning experiment, starting from zero and steadily improving during training. The result highlights growing potential for quantum approaches to outperform classical ML methods in specific tasks. Source: quantumzeitgeist.com

New ML Model Uses Blood Glycopeptide Profiles to Catch Gastric and Colorectal Cancer Early

Scientists developed a non-invasive diagnostic model that analyzes serum glycopeptide patterns with machine learning to detect gastric and colorectal cancers at early stages. Since these gastrointestinal cancers remain among the deadliest worldwide, earlier detection could substantially boost survival rates. Source: nature.com

Beyond LLMs: The AI World Starts Looking Past the Transformer

Despite the explosive growth of LLMs and their spread into daily life, the underlying Transformer architecture faces fundamental limitations. Researchers are increasingly exploring alternative architectures that could define the next phase of AI development. Source: cacm.acm.org

Coast Guard Opens New Hub for AI Research and Collaboration

The Center for Artificial Intelligence and Machine Learning is set to open at the U.S. Coast Guard Academy this fall, aiming to foster research and partnerships in the field. Source: mycg.uscg.mil

New AI Method Aims to Improve Precision of Minimally Invasive Surgery

Researchers built an AI-powered system designed to make minimally invasive surgeries safer and faster by quickly aligning X-ray images during procedures. The technology could help surgeons navigate more accurately in real time. Source: news.mit.edu

Scalable ML Model Maps Genomic Enhancers Across Multiple Tissues

Scientists developed a machine learning model to map complex enhancer regions of DNA that regulate gene activity across different tissues. The approach could help researchers better interpret how genetic variations contribute to human disease. Source: news-medical.net

US Coast Guard Academy to Launch AI and Machine Learning Center

The new Center for Artificial Intelligence and Machine Learning will be led by CDR Matthew Williams. It is already tied to cutter patrol operations and other Coast Guard activities. Source: executivegov.com

ML system spots cancer cells by analyzing how they scatter light

Researchers developed a machine learning approach that identifies cancer cells based on light-scattering patterns in stained cell samples. This could complement traditional cytological screening, where pathologists visually inspect cells under a microscope. Source: medicalxpress.com

AI narrows 65,578 candidates down to 15 promising altermagnetic MOFs

Scientists built an AI-assisted computational pipeline combining symmetry-based screening, machine learning, and density functional theory to search for altermagnetic metal-organic frameworks. Out of tens of thousands of candidates, the approach narrowed the pool to just 15 promising materials. Source: azom.com

AI pushes into math research through reverse problem generation

As AI systems advance, some researchers are exploring how they can help generate new mathematical problems rather than just solve existing ones. This 'reverse problem generation' approach is presented as a fresh frontier for computational AI in academic mathematics. Source: techxplore.com

Study links quantum logic to more interpretable machine learning

Researchers report that applying appropriate logical context to randomized stabilizer tasks achieved perfect accuracy on five- and six-qubit quantum systems. The findings suggest a deeper connection between quantum logic structures and interpretable ML models. Source: quantumzeitgeist.com

Stanford's Paper2Agent turns research papers into working AI agents

Stanford researchers introduced Paper2Agent, a system that converts scientific papers into tested MCP servers so AI agents can execute the described methods using natural language commands. The tool aims to let agents reproduce published results and apply them to new datasets. Source: marktechpost.com

New AI techniques boost reliability of medical image analysis

Machine learning allows computers to learn patterns from data and use them to make predictions or decisions. In health care, such models are increasingly applied to interpret medical scans, and researchers are now developing new methods to make these AI-driven analyses more dependable. Source: medicalxpress.com

New Review Shows AI Models Can Be Designed Without Training First

A major review argues that engineers no longer need to build and train costly neural networks just to test an architecture's viability. Traditionally, designing a deep learning model meant an expensive trial-and-error cycle involving hours or days of GPU time. The findings suggest new methods can predict performance before any training happens, potentially saving significant compute resources. Source: bioengineer.org

UCSB and Lawrence Livermore Team Up to Speed Up Fusion Plasma Simulations with AI

Researchers from UC Santa Barbara and Lawrence Livermore National Laboratory have launched a joint effort to use AI for accelerating simulations of nuclear fusion plasma. The partnership aims to make complex plasma modeling faster and more efficient, supporting progress toward practical fusion energy. The project was reported by Andrew Masuda. Source: edhat.com

LLNL Study: Machine Learning Reveals How Battery Interphases Boost Lithium-Ion Flow

A thin layer of material sitting between the electrolyte and electrodes in lithium-ion batteries plays a major role in how well ions move through the cell. LLNL researchers used machine learning to better understand and improve this interphase layer, aiming to boost battery performance. Source: hpcwire.com