Mapping the Mayhem: Smarter Traffic Forecasts with Incident Awareness
A new framework explicitly models how disruptions like accidents impact traffic flow, leading to significantly improved predictions.
Science
Mapping Global Risk: How Network Topology Reveals Imbalance Vulnerabilities
A new framework analyzes international financial risk not through traditional deficit metrics, but by mapping the network of balance of payments and assessing its inherent stability.
Can AI Predict the Next Big Thing?
New research shows artificial intelligence is surprisingly adept at forecasting the success of startup ventures, challenging traditional methods of strategic foresight.
Adapting Graphs for Smarter Stock Predictions
A new approach aligns graph neural networks with financial tasks, boosting performance in dynamic stock market forecasting.
Beyond FLOPs: Governing the Next Wave of AI
As artificial intelligence moves beyond conventional deep learning, current regulatory frameworks struggle to address the unique challenges posed by brain-inspired computing architectures.
Decoding Deep Networks: A Spectral Lens on Stability and Trust
A new framework reveals how the spectral properties of key network operators govern both the robustness and interpretability of deep learning models.
From Disaster to Data: Automating Damage Assessment with a Portable Analysis Pipeline
![The pipeline rigorously analyzes post-event data, establishing a framework for quantifying performance metrics and iteratively refining the underlying algorithms to ensure mathematical correctness and provable outcomes [latex] \forall \epsilon > 0 [/latex].](https://arxiv.org/html/2602.01798v1/pipeline.png)
This research details a new science gateway that streamlines post-disaster analysis by combining photogrammetry and machine learning techniques.
Harmonizing Data Streams: A New Approach to Time Series Forecasting
![The SpecTF framework encodes both time series data and textual information into the frequency domain, then integrates them via a Frequency Cross-Modality Fusion-employing attention mechanisms and complex multiplication [latex] \odot [/latex]-to map historical frequency representations into predictive ones, ultimately projecting these back into the temporal domain for forecasting.](https://arxiv.org/html/2602.01588v1/x1.png)
Researchers have developed a novel method for integrating textual information with time series data to improve the accuracy of future predictions.
Beyond Universal Forecasters: Why Time Series Prediction Needs Specialization
A new perspective argues that the pursuit of a single, all-powerful time series forecasting model is fundamentally limited, necessitating a move towards adaptable and domain-specific approaches.
Building Trustworthy AI: A New Framework for Agent Security
![The study draws a parallel between the complexities of human societal structures and the emerging dynamics of agentic AI systems, proposing a four-component ([latex]4C[/latex]) mapping to understand how these artificial societies might evolve and interact.](https://arxiv.org/html/2602.01942v1/x3.png)
As artificial intelligence becomes more autonomous, securing these systems requires moving beyond traditional defenses and focusing on the behavior and governance of AI agents within complex social environments.