About
Research & Development
CelloAI: A Local LLM Assistant for High Energy Physics Software Development
TLDR: CelloAI is a locally hosted AI coding assistant for High Energy Physics (HEP) that uses Large Language Models (LLMs) with retrieval-augmented generation (RAG)...
Research & Development
Unlocking LLM Potential: A New Approach to Prompt Engineering with Smaller Models
TLDR: The Weak-to-Strong Transfer (WST) framework introduces an automatic prompt engineering method where a small 'Teacher' model generates instructions to enhance the performance of...
Research & Development
FAIRWELL: Enhancing Fairness in Multimodal AI for Healthcare Wellbeing Prediction
TLDR: The research paper "FAIR WELL : Fair Multimodal Self-Supervised Learning for Wellbeing Prediction" introduces FAIRWELL, a novel self-supervised learning method designed to mitigate...
Research & Development
Boosting Graph Neural Network Performance by Preserving Node Attributes
TLDR: Graph Neural Networks (GNNs), particularly Message Passing Neural Networks (MPNNs), face a new challenge called "over-dilution," where crucial attribute-level information within nodes gets...
Research & Development
Smart Welding: AI Learns to Adapt and Predict Quality in Dynamic Factories
TLDR: A new AI framework uses autoregressive loss from a VQ-VAE Transformer to detect unexpected changes in welding processes, triggering model updates only when...
Research & Development
Unlocking Industrial Resilience: A Physics-Inspired AI Approach to Predicting Supply Chain Dynamics
TLDR: This research introduces NSL-Net, a novel physics-informed neural-symbolic learning method for predicting industrial chain resilience. It integrates non-linear ordinary differential equations describing physical...