About
Research & Development
Roster of Experts: Enhancing LLM Predictions Through Internal Diversification
TLDR: The research introduces 'hyper-parallel scaling,' a new method to improve large language model (LLM) prediction quality at the token level. Implemented as 'Roster...
Research & Development
AI Co-Pilot Achieves 84% Agreement with Human Experts in Evaluating Systematic Reviews
TLDR: A new research paper introduces an LLM-based Multi-Agent System (MAS) designed to evaluate Systematic Literature Reviews (SLRs) by automating protocol validation, methodological assessment,...
Research & Development
Enhancing Highway Safety: A Physics-Informed AI for Predicting Lane Changes
TLDR: This research proposes a physics-informed AI framework for predicting highway lane changes, classifying them as left, right, or no change. It integrates vehicle...
Research & Development
Enhancing Program Generation with Test-Time Input Guidance
TLDR: A new method called SYNTRA improves program synthesis by actively using test inputs during the generation process. It leverages large language models to...
Research & Development
SPICED: A Brain-Inspired AI Framework for Continuous EEG Decoding
TLDR: SPICED is a new AI framework inspired by the brain's synaptic homeostasis, a mechanism that balances learning new information with retaining old memories....
Research & Development
Unifying AI’s Fragmented Landscape: Introducing Pangaea, the AI Supercontinent
TLDR: Pangaea is a new AI model that unifies different types of AI (called "Intelligence Islands") by converting all data into a universal "triplet...