About
Research & Development
Mapping Research Fields with AI: The Sci-OG Methodology
TLDR: Sci-OG is a novel semi-automated AI methodology designed to generate structured maps (ontologies) of research topics from large scientific paper corpora. It employs...
Research & Development
Improving Time Series Predictions with AI-Powered Data Refinement
TLDR: DCATS is a novel framework that utilizes LLM-powered agents to enhance time series forecasting by intelligently refining training data, rather than solely optimizing...
Research & Development
TalkDep: Creating Realistic AI Patients for Depression Screening Training
TLDR: TalkDep is a novel system that uses advanced large language models (LLMs) to create clinically validated, realistic virtual patients for training and evaluating...
Research & Development
VL-DAC: Training Vision-Language Models for Real-World Action Through Synthetic Environments
TLDR: A new reinforcement learning algorithm, Vision-Language Decoupled Actor-Critic (VL-DAC), enables Vision-Language Models (VLMs) to learn complex interactive behaviors in inexpensive synthetic environments. By...
Research & Development
Unveiling NIRMAL: A New Optimizer Inspired by Chess Moves for Deep Learning
TLDR: A new optimization algorithm called NIRMAL (Novel Integrated Robust Multi-Adaptation Learning) has been introduced, drawing inspiration from the strategic movements of chess pieces....
Research & Development
A New Framework for Trustworthy Medical AI Evaluation
TLDR: A new framework called MedCheck is introduced to address the unreliability of current medical Large Language Model (LLM) benchmarks. MedCheck evaluates benchmarks across...