About
Research & Development
Pinpointing Earth Changes: A Network That Connects ‘When’ to ‘Where’
TLDR: CAIM-Net is a new deep learning model for time series remote sensing image change detection. It addresses the challenges of unclear change boundaries...
Research & Development
GV ote: Smarter KV-Cache Compression for Efficient LLM Inference
TLDR: GV ote is a new adaptive KV-cache compression method for large language models (LLMs) that automatically determines the optimal memory budget for each...
Research & Development
Boosting Predictive Process Monitoring with Domain-Adapted LLMs
TLDR: This research explores directly adapting Large Language Models (LLMs) to process data for Predictive Process Monitoring (PPM) tasks like next activity and remaining...
Research & Development
Navigating the ‘Rashomon Effect’: Why AI Explanations in Self-Driving Cars Can Differ
TLDR: A new research paper quantifies the 'Rashomon effect' in autonomous driving, showing that equally accurate AI models can provide significantly different explanations for...
Research & Development
Navigating the Data Frontier: Differential Privacy from Principles to Practical Applications
TLDR: This research paper provides a comprehensive overview of Differential Privacy (DP), a mathematical framework for protecting individual privacy in data analysis and machine...
Research & Development
Unlocking Agent-Based Models: How Automatic Differentiation Enhances Simulation and Calibration
TLDR: A new research paper demonstrates how Automatic Differentiation (AD) can overcome the computational challenges of Agent-Based Models (ABMs). By applying AD, the researchers...