Hunting Fraud Across the Blockchain

A new framework leverages the power of artificial intelligence to identify malicious cryptocurrency accounts, even as they move between different blockchain networks.

A new framework leverages the power of artificial intelligence to identify malicious cryptocurrency accounts, even as they move between different blockchain networks.
A new study benchmarks the surprising ability of artificial intelligence to detect anomalies in system logs and predict potential failures.
![The distribution of 32,319 Lyman-alpha emitter (LAE) candidates within the HETDEX COSMOS catalog-subdivided into likely and unlikely real candidates based on signal-to-noise ratio, luminosity, and line width-demonstrates a sensitivity limit of [latex] 1.1 \times 10^{-{16}}~\mathrm{erg~s^{-1}~cm^{-2}} [/latex] at a redshift of approximately 2.7, corresponding to 50% completeness at a luminosity of [latex] 1.0 \times 10^{42.8}~\mathrm{erg~s^{-1}} [/latex], thereby defining the boundaries of detectable emission within this survey.](https://arxiv.org/html/2604.12414v1/x4.png)
A new deep learning approach dramatically improves the identification of distant, faint Lyα galaxies in the HETDEX survey, unlocking a larger sample for cosmological studies.

A new system dramatically speeds up the detection of illicit financial patterns by combining adaptable pattern definitions with specialized hardware acceleration.

New research demonstrates how intelligent agents powered by large language models can dramatically improve the analysis of value stream mapping simulations, leading to more effective process optimization.

New research tackles the pervasive biases in current AI-generated image detection systems, paving the way for more reliable and generalizable tools.

As AI-generated text floods the internet, distinguishing between machine-authored and human-written misinformation is becoming increasingly critical.
New research introduces a method for detecting instances where companies exaggerate or misrepresent their use of artificial intelligence.

Researchers have developed a new AI system capable of anticipating the core insights of future studies based on existing scientific literature.

A new approach uses the rigor of financial markets to evaluate and align multi-agent systems, sidestepping the pitfalls of subjective feedback and simulated environments.