About
Research & Development
Latent Knowledge Scalpel: A New Approach for Precise and Scalable LLM Knowledge Editing
TLDR: Latent Knowledge Scalpel (LKS) is a novel LLM editing method that precisely updates factual information by manipulating entity-specific internal representations using a lightweight...
Research & Development
Advancing Medical Image Diagnosis Through Vision-Language Pre-training
TLDR: ViSD-Boost is a new medical vision-language pre-training method that tackles the 'semantic density gap' between low-signal medical images and high-signal diagnostic reports. It...
Research & Development
Deep Learning Model Uses Geographic Law for Smarter Feature Detection
TLDR: A new GeoAI deep learning model uses Tobler's First Law of Geography to detect terrain features with only weak supervision (object counts, not...
Research & Development
Unlocking Urban Rhythms: How Data Reveals the Predictable Pulse of City Movement
TLDR: This research introduces a new machine learning method to identify and quantify recurring patterns, like weekly cycles, in urban human mobility data. Applied...
Research & Development
Refine-IQA: A Multi-Stage Approach to Enhancing Image Quality Assessment in AI Models
TLDR: Refine-IQA is a new multi-stage reinforcement fine-tuning (RFT) framework for Image Quality Assessment (IQA) in large multi-modal models (LMMs). It addresses limitations of...
Research & Development
CoughViT: Advancing AI Diagnosis of Respiratory Conditions Through Self-Supervised Learning
TLDR: CoughViT is a new AI framework that uses self-supervised learning and a Vision Transformer to analyze cough sounds. It learns general cough representations...