InfoQ

MIT's Recursive Language Models Improve Performance on Long-Context Tasks

Researchers at MIT's CSAIL published a design for Recursive Language Models (RLM), a technique for improving LLM performance ...

New model maps social polarization as overlapping group opinions, not fixed sides

Researchers at TU Wien are developing a model that interprets opinions not as diametrically opposed poles, but as overlapping ...
IEEE

GAIN: GATv2-based Adaptive Framework for Innovative Topic Mining in Patent Knowledge Graphs

Abstract: With the exponential growth of scientific and technological patents, efficiently identifying key “technical topic” nodes in large-scale patent knowledge graphs is crucial for enhancing ...
IEEE

A Multi-Dimensional Telecom Fraud Detection Model Based on Graph Attention Networks

Abstract: With the rapid development of 5G mobile networks, telecom fraud methods are continuously evolving, and the number of fraudsters and victims is increasing. Traditional telecom fraud detection ...