About
Research & Development
Pancreatic Cyst Analysis Enhanced by Fine-Tuned AI Models
TLDR: Researchers developed and fine-tuned open-source large language models (LLMs) to automatically extract features and categorize the risk of pancreatic cystic lesions (PCLs) from...
Research & Development
Advancing 6G Resource Management with Digital Twin Channel Technology
TLDR: This research introduces a Digital Twin Channel (DTC)-enabled framework for online resource allocation in 6G networks, particularly for demanding applications like the Industrial...
Research & Development
PITA: A Direct Path to Aligning Language Models with User Preferences
TLDR: PITA (Preference-Guided Inference-Time Alignment) is a novel framework that aligns large language models (LLMs) with user preferences directly during inference, eliminating the need...
Research & Development
HFrame: A Hybrid Approach to Efficient and Accurate Subgraph Homomorphism
TLDR: HFrame is a novel framework that combines algorithmic filtering (DualSim) with a specialized Graph Neural Network (HGIN) to solve the subgraph homomorphism problem....
Research & Development
SciToolAgent: An AI System for Automating Complex Scientific Workflows
TLDR: SciToolAgent is an AI agent that uses a knowledge graph (SciToolKG) to integrate and automate hundreds of scientific tools across biology, chemistry, and...
Research & Development
Navigating the Double-Edged Sword of LLM Dimensionality for Enhanced Safety
TLDR: This research paper investigates how increasing hidden dimensions in Large Language Models (LLMs) can both enhance capabilities and create vulnerabilities to 'jailbreaking' attacks...