Science – Page 12

Listening to the Depths: AI Learns to Identify Underwater Sounds

16.12.2025 by qfx

The study visualizes connections within a Mel-spectrogram using graph representations, demonstrating how the integration of a UATR-GTransformer - composed of successive GTransformer blocks - builds upon a foundational Graph Neural Network to model spectral relationships.

A new approach combining graph and transformer neural networks enhances the accuracy of identifying objects based on their acoustic signatures in challenging underwater environments.

Unveiling Hidden Worlds: Microlensing with AI

16.12.2025 by qfx

$A simulation pipeline generates synthetic light curves, deliberately introducing observational imperfections-data gaps, dropouts, and noise-before feeding the resulting data into a Transformer encoder; the encoder’s output then conditions a normalizing flow designed to approximate the posterior distribution $p(\theta|x)$, effectively modeling the uncertainty inherent in inferring parameters $\theta$ from incomplete observations $x$.$

A new approach leverages the power of Transformer networks to rapidly analyze gravitational microlensing data and detect faint signals of free-floating planets.

Decoding the Cosmos: AI Spots Celestial Patterns

16.12.2025 by qfx

$The theoretical light curves demonstrate how even the most meticulously constructed models, described by equations like $L(t) = A \sin(\omega t + \phi)$, are ultimately transient phenomena susceptible to vanishing beyond the reach of observation, much like illusions of control before an inescapable truth.$

Machine learning is proving to be a powerful tool for astronomers, enabling the automated classification of high-energy sources in the universe.

Learning by Doing: How Agents Can Reason Through Action

15.12.2025 by qfx

The training process exhibits reward curves indicative of successful learning, demonstrating the algorithm's convergence towards an optimal policy.

A new training pipeline leverages reinforcement learning to enable conversational agents to improve their reasoning abilities by actively interacting with their environment.

The Creativity Paradox of AI Truthfulness

15.12.2025 by qfx

The study evaluates large language model creative performance on the NeoCoder and CS4 benchmarks, systematically comparing results with and without the application of three hallucination-reduction techniques-CoVe, DoLa, and RAG-to assess their effectiveness.

New research reveals that making large language models more factually accurate doesn’t automatically make them more creative, and can even stifle their ability to generate novel ideas.

Predicting Power Grid Stability with AI and Fluid Dynamics

15.12.2025 by qfx

A new approach combines machine learning with principles of fluid dynamics to forecast power flow and ensure grid reliability.

Uncovering the Past: How AI is Rewriting History from Old Newspapers

15.12.2025 by qfx

The distribution of documents across time reveals how the volume of available content ebbs and flows, fundamentally shaping the observed evolution of topics within the analysis-a pattern indicative of how data density itself becomes a critical, often overlooked, factor in understanding temporal trends.

Researchers are leveraging advanced artificial intelligence to analyze vast archives of historical newspapers, revealing hidden patterns and offering fresh perspectives on past events.

Seeing What the Data Says: A New Dataset Bridges Time Series and Language

15.12.2025 by qfx

Statistical tools facilitate the creation of trend datasets, enabling systematic observation and analysis of evolving patterns.

Researchers have created a large-scale dataset that links time series data with natural language descriptions, unlocking new possibilities for automated analysis and interpretation.

AI Harvests Knowledge for Greener Farming

15.12.2025 by qfx

New research shows artificial intelligence can synthesize complex information about ecological pest control, offering a powerful tool for sustainable agriculture.

Forecasting with Resilience: Learning to Spot What Matters in Time Series

15.12.2025 by qfx

Time-series forecasting must differentiate between input anomalies that are transient and inconsequential to predictions, and those that fundamentally alter the forecasted output, demanding robust anomaly detection capable of discerning their lasting impact.

A new framework enhances time-series forecasting by focusing on aligning learned representations with the deviations most relevant to accurate predictions.