About
Research & Development
Daily Greenery Exposure Linked to Significant Health Benefits in Urban Areas
TLDR: A new study reveals that 'on-road greenery' – the vegetation people see daily on streets – is more strongly linked to better health...
Research & Development
AI Models Enhance Cyberattack Consequence Prediction
TLDR: A study by Bipin Chhetri and Akbar Siami Namin explores using Transformer-based models (BERT and HAN) to predict cyberattack consequences from textual descriptions...
Research & Development
EvoCut: Accelerating Integer Program Solvers with AI-Driven Cut Generation
TLDR: EvoCut is a novel framework that automates the creation of acceleration cuts for integer programming problems, traditionally a manual and expert-intensive task. By...
Research & Development
Optimizing Data Mixtures for Fine-Tuning Large Language Models
TLDR: This paper introduces Data Mixing Optimization, a novel method for supervised fine-tuning (SFT) of Large Language Models (LLMs). It frames data mixing as...
Research & Development
UniCast: Enhancing Time Series Forecasting with Visual and Textual Context
TLDR: UniCast is a new framework that significantly improves time series forecasting by integrating visual and textual data with traditional time series models. It...
Research & Development
AgentCDM: A New Approach to Smarter Team Decisions in AI Systems
TLDR: AgentCDM is a novel framework that improves how multiple AI agents make collaborative decisions. Inspired by the Analysis of Competing Hypotheses (ACH) from...