About
Research & Development
Streamlining Software Debugging with AI: A New Approach Using Large Language Models
TLDR: A new approach uses generative AI and a system's process data (inputs, outputs, documentation) to create natural-language explanations for debugging distributed software systems....
Research & Development
ELATE: Automating Feature Creation for Better Time-Series Predictions
TLDR: ELATE is a novel framework that uses large language models (LLMs) within an evolutionary optimization process to automate feature engineering for time-series data....
Research & Development
ShizhenGPT: Advancing TCM Diagnostics with Multimodal AI
TLDR: ShizhenGPT is the first multimodal large language model (LLM) specifically designed for Traditional Chinese Medicine (TCM). It addresses the challenges of limited TCM...
Research & Development
Advancing Reactive Synthesis with New Game-Based Solvers for LTLf+ and PPLTL+
TLDR: This research introduces the first practical solvers for reactive synthesis in LTLf+ and PPLTL+, new temporal logics that combine the efficiency of finite-trace...
Research & Development
PepThink-R1: A New AI Approach for Designing Better Therapeutic Peptides
TLDR: PepThink-R1 is a new AI framework that uses large language models, Chain-of-Thought reasoning, and reinforcement learning to design cyclic peptides with improved drug-like...
Research & Development
New Framework Enhances Blurry License Plate Recognition from Dash Cams
TLDR: MF-LPR² is a novel multi-frame framework designed to restore and recognize low-quality license plate images from dash cams. It addresses issues like low...