Taming Chaos: Machine Learning’s New Frontier
Recent advances in machine learning are offering unprecedented tools for predicting and understanding the complex behavior of chaotic systems.
Science
From Text to Trends: Bridging Language Models and Financial Graphs
A new approach directly translates the relational knowledge embedded in language models into graph structures, enhancing predictions of financial market behavior.
Predicting Buybacks: How Deep Learning Uncovers Stock Repurchase Patterns
A new deep learning approach leverages temporal data and attention mechanisms to forecast corporate stock repurchases with improved accuracy.
Simulating Trust: How Knowledge Graphs Can Unlock Auditable AI
A new approach leverages event-driven simulation and ontological governance to build enterprise AI systems where decisions are traceable and explainable.
The Shifting Roots of Speech AI Errors
New research reveals how the causes of speech recognition ‘hallucinations’ fundamentally change as model size increases.
When Agents Fail: Uncovering the Roots of Error in AI Systems
A new empirical study dives deep into the common failure modes of modern agentic frameworks, pinpointing the architectural weaknesses and bug patterns that lead to unpredictable behavior.
Banking on Context: A New Foundation Model for Financial Understanding
![A user’s record is represented as an ordered event history and profile state, where each field is decomposed into a semantic type, associated values, and a temporal coordinate; keys and values are embedded from a shared lookup table, and value tokens receive positional embeddings within each field, allowing a Profile State Encoder to map the profile state-with time since life-long events encoded via RoPE-into a [USR] embedding, while an Event Encoder independently maps event tokens into a [EVT] embedding augmented with calendar features, and a History Encoder contextualizes the resulting sequence with time to the last event-also encoded via RoPE-to produce a comprehensive representation of the user record.](https://arxiv.org/html/2604.08649v1/x4.png)
Revolut’s PRAGMA model introduces a novel approach to understanding user financial histories by leveraging masked modeling and heterogeneous data sources.
From Digital Waste to Planetary Insight
A new approach, dubbed ‘Scrapyard AI’, repurposes discarded artificial intelligence models to monitor the environmental consequences of resource extraction.
Powering the AI Boom: Smart Grids for Data Center Demand
As artificial intelligence infrastructure expands, ensuring reliable and efficient transmission network capacity is crucial for avoiding outages and escalating costs.
Sequences and Connections: Rethinking Event Modeling
New research demonstrates that incorporating relationships between users and events significantly boosts the performance of sequence prediction models.