TopoPlanner introduces a topology‑aware framework that lets large language models […]
Category: Research
Safe-Role Fine-Tuning Boosts LLM Safety
Safe-Role Fine-Tuning (SSRFT) redefines LLM safety by teaching models a […]
AegisFlow: AI Self‑Healing Data Pipelines
AegisFlow is a new agentic AI framework that turns data […]
EPOCH: Evidence‑Governed AI Discovery
EPOCH, a new evidence‑governed AI architecture, redefines how research agents […]
AI Risk Observatory: Annual Report Insights
Researchers at the AI Risk Observatory have mapped how UK […]
System-1 Decision Models: Evaluation & Audit
Researchers released a comprehensive paired evaluation of two System‑1 decision […]