About
Research & Development
Enhancing LLM Reliability: A New Approach to Multi-Model Uncertainty
TLDR: A new method called MUSE (Multi-LLM Uncertainty via Subset Ensembles) improves the reliability and accuracy of large language models by intelligently combining predictions...
Research & Development
Enhancing AI for Accurate Chemical Design and Synthesis
TLDR: This paper introduces a method to improve Large Language Models (LLMs) for chemistry by fine-tuning a reasoning-enhanced model called Magistral Small. By using...
News & Current Events
BRICS+ Nations Forge Unified Stance on Inclusive AI Governance, Challenging Western Frameworks
TLDR: At their 17th summit in Rio de Janeiro, BRICS+ leaders released a landmark statement on global AI governance, advocating for a multilateral, UN-centric...
Research & Development
Optimizing Experiments for Specific Causal Questions with GO-CBED
TLDR: GO-CBED is a new framework for designing experiments in causal learning. Unlike traditional methods that aim to uncover entire causal models, GO-CBED focuses...
Research & Development
ATHENA: A Hierarchical AI Framework for Advanced Atherosclerosis Classification and Patient Subtyping
TLDR: ATHENA is a novel hierarchical graph neural network framework that integrates patient clinical features with molecular interaction data to improve the classification of...
Research & Development
Piloc: A New Approach for Multi-Agent Search and Rescue in Dynamic Environments
TLDR: Piloc is a novel framework for multi-agent search and rescue (MASAR) in unknown, dynamic environments. It introduces a 'pheromone inverse guidance mechanism' to...