CognitiveLens is a Streamlit-powered analytics tool for exploring alignment between human and AI decisions. It visualizes fairness, calibration, and interpretability through metrics like Cohen’s κ, AUC, and Brier score. Designed for ethical AI, bias auditing, and decision transparency in machine learning systems.

An early-warning system that models disasters as instability transitions rather than isolated events. It combines force-based instability modeling with an interpretable ML escalation-risk layer to detect when hazards become disasters due to exposure growth, response delays, and buffer collapse.

An explanation-first HR analytics system that reconstructs why employee exit becomes rational. Instead of predicting attrition, it generates human-readable exit narratives by decomposing pressure and retention forces, adding peer context and counterfactual interventions to reveal how stability erodes over time.

What's In My Human Feedback? Explaining preferences in human feedback using interpretability + LLMs. https://arxiv.org/abs/2510.26202

Repository of the paper "Toward a Responsible Fairness Analysis: From Binary to Multiclass and Multigroup Assessment in Graph Neural Network-Based User Modeling Tasks"

Seed Lab is a research workspace exploring language model behavior, symbolic reasoning, and emergent communication patterns through structured personas, simulated interactions, and interpretability-focused experiments.

The Conscience Layer Prototype, created by Aleksandar Rodić in 2025, establishes a research foundation for ethical artificial intelligence. It brings moral awareness into computation through principles of truth, human autonomy, and societal responsibility, defining a transparent and accountable form of intelligence.

Counterfactual explanations for continuous reinforcement learning with simulation in T1D and Gym environments.

Human-Centered AI: explainability + active learning

open core assets

[AAAI 2026] Learning from Human Gaze: Human-like Robot Social Navigation in Dense Crowds

🌍 Monitor disaster instability and provide early warnings using advanced analytics and machine learning techniques to enhance preparedness and response.

🤖 Analyze and compare human and AI decision-making to enhance trust, fairness, and alignment in machine learning systems with CognitiveLens.

Human-centered AI interview prototype that generates follow-up questions and lets participants rate fairness, relevance, comfort, and trust.

Ethical AI governance framework for multi-model alignment, integrity, and enterprise oversight.

📊 Generate insightful exit narratives to analyze employee attrition and improve retention strategies using data-driven decision-making techniques.