About
Research & Development
LLM Agents Uncover Human-Like Social Dynamics in a Classic Economic Dilemma
TLDR: This research investigates the emergent social dynamics of Large Language Model (LLM) agents in a spatially extended El Farol Bar problem. The study...
Research & Development
VCMamba: A New Hybrid Model for Advanced Visual AI
TLDR: VCMamba is a novel vision architecture that combines the strengths of Convolutional Neural Networks (CNNs) for robust local feature extraction with Multi-Directional Mamba...
Research & Development
ODKE+: Enhancing Knowledge Graphs with LLM-Powered Fact Extraction
TLDR: ODKE+ is a production-grade system developed by Apple Inc. that uses large language models (LLMs) and ontology-guided prompting to automatically extract and ingest...
Research & Development
Unlocking Advanced Question Answering with KERAG’s Knowledge Graph Approach
TLDR: KERAG is a novel Knowledge Graph-based Retrieval-Augmented Generation (RAG) pipeline that significantly improves question answering. It addresses the limitations of traditional methods by...
Research & Development
Rethinking Distance Measures in Representation Learning
TLDR: The Beyond I-Con framework introduces a new approach to representation learning by systematically exploring alternative statistical divergences (like Total Variation, Jensen-Shannon, Hellinger) and...
Research & Development
Optimizing Large Language Models for Clinical Data Extraction
TLDR: This study explores how Large Language Models (LLMs) can best extract patient information from clinical notes. It compares encoder-only and decoder-only LLMs, different...