Mapping the Cosmos: Machine Learning Predicts How Galaxies Cluster
A new machine learning framework accurately forecasts galaxy bias by analyzing the interplay between dark matter halos and cosmic environments.
Science
Unlocking Neural Network Secrets with Statistical Physics
Researchers are applying concepts from the Renormalisation Group to build more reliable and interpretable deep learning models.
The Deepfake Pipeline: Tracking the Technology Behind Non-Consensual Intimate Images
A new review maps the complex web of technologies enabling the creation and dissemination of AI-generated sexual abuse material, revealing how efforts to combat it often feel like a futile game of whack-a-mole.
Beyond Sequences: How Graph Networks and AI Language Models Are Unlocking Time Series Insights
A new framework combines the power of graph-based reasoning with large language models to dramatically improve the analysis and understanding of complex time series data.
Learning to Feel: AI Inspired by Biological Senses
A new approach to artificial intelligence mimics the way animals learn to avoid harm, creating more robust and adaptable systems.
When Reasoning Goes Wrong: Spotting Instability in AI’s Thought Process
![In large language models, dynamic instability during inference-manifested as abrupt shifts in next-token probability distributions and increased uncertainty-can be quantified via a diagnostic signal [latex]I\_t = D\_t + \lambda H\_t[/latex], where [latex]D\_t[/latex] measures distributional shift and [latex]H\_t[/latex] represents uncertainty, with the overall instability strength [latex]S = \max\_t I\_t[/latex] correlating with increased failure risk and the timing of instability episodes offering insights into potential recoverability.](https://arxiv.org/html/2602.02863v1/figures/Fig1.png)
New research reveals a way to detect when large language models begin to falter during reasoning, offering insights into why they sometimes fail.
Decoding the Spread: Who Fuels Conspiracy Theories Online?
New research reveals how data analysis can pinpoint the key individuals and automated accounts driving the proliferation of misinformation on X.
Weathering the Storm: Smarter Load Forecasting for a Changing Climate
A new probabilistic forecasting framework improves power grid resilience by accurately predicting extreme energy demand, even with limited data.
Scaling Up Graph Intelligence
New research details a framework for building and pre-training graph foundation models at an unprecedented scale, unlocking advanced capabilities for heterogeneous graph data.
Smarter Supply Chains: Forecasting Demand Without Sharing Data
A new approach combining federated learning and blockchain technology offers a path to more accurate retail demand forecasting and reduced food waste.