Publications.

Papers, preprints, datasets, and software across machine learning, materials science, and physics.

42 works

2026

Physical survival and provenance limits on watermarking AI-generated crystals

Can Polat , Mustafa Kurban , Erchin Serpedin , Hasan Kurban Preprint

Generated crystals undergo relaxation and standardization before researchers use them. Those steps can erase the structural signatures intended to identify their origin. This makes provenance a practical question for anyone building or reusing datasets of AI-generated materials: what evidence survives the actual scientific workflow?

2025

xChemAgents: Agentic AI for Explainable Quantum Chemistry

Can Polat , Mehmet Tunçel , Mustafa Kurban , Erchin Serpedin , Hasan Kurban · ICML 2025 — MAS: Multi-Agent Systems in the Era of Foundation Models workshop Conference / workshop

Use cooperating agents to choose descriptors and check physical consistency in quantum-property prediction.