Archives AI News

A Graph-Based Approach to Alert Contextualisation in Security Operations Centres

arXiv:2509.12923v1 Announce Type: cross Abstract: Interpreting the massive volume of security alerts is a significant challenge in Security Operations Centres (SOCs). Effective contextualisation is important, enabling quick distinction between genuine threats and benign activity to prioritise what needs further analysis.This…

Enhancing Physical Consistency in Lightweight World Models

arXiv:2509.12437v1 Announce Type: new Abstract: A major challenge in deploying world models is the trade-off between size and performance. Large world models can capture rich physical dynamics but require massive computing resources, making them impractical for edge devices. Small world…

Implicit Neural Representations of Intramyocardial Motion and Strain

arXiv:2509.09004v3 Announce Type: replace-cross Abstract: Automatic quantification of intramyocardial motion and strain from tagging MRI remains an important but challenging task. We propose a method using implicit neural representations (INRs), conditioned on learned latent codes, to predict continuous left ventricular…

LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences

arXiv:2509.12273v1 Announce Type: new Abstract: The rise of large language models (LLMs) has made natural language-driven route planning an emerging research area that encompasses rich user objectives. Current research exhibits two distinct approaches: direct route planning using LLM-as-Agent and graph-based…

Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition

arXiv:2509.12423v1 Announce Type: new Abstract: Understanding user intents from UI interaction trajectories remains a challenging, yet crucial, frontier in intelligent agent development. While massive, datacenter-based, multi-modal large language models (MLLMs) possess greater capacity to handle the complexities of such sequences,…

Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization

arXiv:2509.12434v1 Announce Type: new Abstract: Software engineering presents complex, multi-step challenges for Large Language Models (LLMs), requiring reasoning over large codebases and coordinated tool use. The difficulty of these tasks is exemplified by benchmarks like SWE-bench, where current LLMs still…