Conformal prediction is a powerful tool for uncertainty quantification, but its application to
time-series data is constrained by the violation of the exchangeability assumption. Current …

Quantifying uncertainty in multivariate regression is essential in many real-world
applications, yet existing methods for constructing prediction regions often face limitations …

Conformal Prediction provides statistical coverage guarantees for uncertainty quantification
but fails to account for spatially varying importance of predictive uncertainty in medical …

Ensuring fairness and accountability in Large Language Models (LLMs) remains a critical
challenge in AI ethics. Biases in training data, model architecture, and decision-making …

Abstract The integration of Artificial Intelligence (AI) in software development has
transformed traditional workflows, enhancing productivity and automating complex tasks. AI …

Ensuring fairness, robustness, and reliability in Artificial Intelligence (AI) systems remains a
significant challenge. Traditional evaluation metrics often fail to capture biases and edge …

The integration of multi-agent AI systems into software engineering is transforming
traditional development workflows. Large Language Models (LLMs), when used …

Abstract The integration of Multi-Agent Large Language Models (LLMs) in software
engineering is transforming Agile workflows by automating key development processes …

Explainability in AI remains a significant challenge, particularly in multi-agent systems where
decision-making processes involve complex interactions between multiple intelligent …

AI-driven Agile development is transforming engineering workflows by integrating multi-
agent Large Language Models (LLMs) to enhance collaboration, automation, and decision …