Displaying 1 of 1 results explainable AI clear search
Tabish Ahmad is an AI and Machine Learning researcher whose work spans agent-based modeling, multi-agent systems, and trustworthy, calibrated AI. In computational social science, he studies how shared language and dialects emerge in networked populations through a naming-game model with communication noise and evolving strategies (under review at JASSS). His wider research develops reliable AI using conformal prediction, distribution-free risk control, and calibration, applied to multi-agent LLM systems, medical imaging, and industrial inspection. He has five papers under review, serves as a peer reviewer for Expert Systems with Applications (Elsevier), and builds open, reproducible models and benchmarks.
Agent-based modeling and multi-agent systems; the emergence of language, norms, and consensus in networked populations; trustworthy and calibrated AI (conformal prediction, distribution-free risk control, model calibration, and uncertainty quantification); multi-agent large language model (LLM) systems; explainable AI; and reproducible computational modeling applied to social simulation, medical imaging, and industrial systems.