About
Research & Development
Navigating Dynamic Fairness in AI: A Graph-Based Learning Approach
TLDR: This research paper introduces a framework for learning and adapting to multiple, potentially conflicting, and time-varying fairness measures in AI systems. It models...
Research & Development
Enhancing Small Object Detection Through Inter-Class Spatial Relationships
TLDR: A new loss function, Inter-Class Relational (ICR) loss, improves the detection of small objects like license plates by leveraging their spatial relationship with...
Research & Development
AI Agents Unravel Human Physiology: A New Era for Clinical Simulation
TLDR: Organ-Agents is a novel multi-agent AI framework that simulates human physiology using LLM-driven agents for specific organ systems. It demonstrates high accuracy in...
Research & Development
Calibrating Large Language Models with a Structured Play Framework
TLDR: Researchers propose a novel prompt-based framework, inspired by the Credence Calibration Game, to improve Large Language Model (LLM) confidence calibration. The method involves...
Research & Development
DEPTH: A New AI Framework for Accurate Relation Extraction and Halucination Reduction
TLDR: DEPTH is a novel AI framework designed to improve relation extraction by Large Language Models (LLMs) and significantly reduce 'hallucinations' (incorrect relation predictions)....
Research & Development
Unlocking Spike-Driven Learning: How Synaptic Bundles and Motor Neuron Counts Impact AI Systems
TLDR: A new study reveals critical limits for successful spike-based learning in artificial sensor-motor systems. Researchers found that learning collapses if the number of...