Academic papers, research breakthroughs, and scientific advances in machine learning and AI.
319 articles
A systematic review of 237 studies from 2014 to 2024 shows how explainable AI methods such as SHAP and LIME are making machine learning models for crash severity prediction more transparent and interpretable. Source: bioengineer.org
Cantina Security released apex-flash-1, an MIT-licensed 321B-parameter model built for security research. It reaches 66.7% pass@1 on held-out bug tasks while costing 31 times less than Opus. Source: marktechpost.com
Researchers trained six machine learning models on 2,048 laboratory records to forecast the compressive strength of cement-free concrete. Gradient boosting came out as the best predictor, offering a data-driven route to designing greener construction materials. Source: bioengineer.org
Researchers paired blockchain-based customer authentication with an ensemble of three machine learning classifiers to spot money laundering. The combined system reaches roughly 96% detection accuracy. Source: bioengineer.org
Google Research moved federated learning into trusted execution environments (TEEs). Gboard now trains with externally verifiable central differential privacy, and server-side training runs faster. Source: marktechpost.com
Researchers announced a Federated Learning system that provides externally verifiable privacy guarantees. It achieves this while shifting more of the computation to the server to improve efficiency. Source: research.google
Using dual-unitary circuits in a brickwork architecture offers a new platform for quantum reservoir computing, a machine learning technique. Researchers report that this setup improves the approach's performance. Source: quantumzeitgeist.com
Multilingual self-supervised speech models can gain from sharing information across languages, but the benefit is harder to realize when the total amount of pretraining data is held constant. The work looks at how explicitly discriminating between languages can improve what these models learn about linguistic structure. Source: machinelearning.apple.com
New research examines how a quantum kernel affects active learning when paired with Gaussian Process Regression (GPR). The framework's performance depends strongly on how the kernel is tuned. Source: quantumzeitgeist.com
The standard approach in reinforcement learning with verifiable rewards (RLVR) lets agents make several attempts at a task and then optimizes based on the outcomes. This work explores self-improvement by internalizing feedback that the agent generates for itself. Source: machinelearning.apple.com
Research from Quandela examines how photonic quantum computing can use quantum fingerprints to boost the data efficiency of machine learning. The approach is especially relevant when labeled data is scarce. Source: quantumzeitgeist.com
IoT systems produce a constant flood of sensor data, but converting that raw stream into truly good decisions is still a major challenge. A new closed-loop decision engine combines machine learning with operations research to bridge that gap. Source: bioengineer.org
Southwest Research Institute (SwRI) is applying a generative AI tool to pharmaceutical development. The machine learning toolkit aims to improve the chances that drug candidates succeed. Source: medicalxpress.com
Researchers examine what happens when language models, during chain-of-thought reasoning or when passing free-text intermediates, convert structured information into natural language. Their round-trip study of tree-structured expressions tests how much of that structure survives serialization, exposing a communication bottleneck. Source: machinelearning.apple.com
In complex physical systems, so-called nuisance data from large-scale simulations can serve as training material for machine learning algorithms. The models can then use it to identify underlying laws and interactions. Source: lanl.gov
Researchers combined machine learning with physical modeling to improve calibration and validation of wearable electrochemical sensors that track metabolites in sweat. The approach aims to make continuous, non-invasive health monitoring devices more accurate and reliable for real-world physiological use. Source: nature.com
Researchers combined machine learning with molecular scaffold techniques to improve production of liquiritigenin, a flavonoid found in licorice root known for potential heart-protective and antidiabetic properties. The approach could make this hard-to-produce compound more accessible for drug development. Source: bioengineer.org
Scientists used AI to identify markers of aging in the nuclei of hematopoietic stem cells, the cells responsible for blood production. Aging gradually weakens this system, and the new imaging-based approach could help track and better understand that decline. Source: medicalxpress.com
High accuracy scores and impressive backtests can be deceptive when evaluating financial machine learning systems. Real validation requires reproducibility, safeguards against data leakage, and evidence that models actually deliver economic value. Source: hackernoon.com
Researchers at Skylark Labs have developed a continual learning AI architecture that allows robots to adapt based on new experiences even after they've been deployed in the field. The system is designed to help robots improve performance over time without needing to be retrained from scratch. Source: roboticsandautomationnews.com