Rui (Ray) Ding

Schmidt AI in Science Fellow

University of Chicago & Argonne National Laboratory

• ruiding@uchicago.edu · rding@anl.gov

I build AI co-scientist systems for complex materials and device discovery in the no-database regime. In practice: software that mines the literature, builds device digital twins, and proposes candidates we then check in simulation and in the lab.

Trained as a materials scientist and electrochemist, I became interested in AI after seeing how much of materials discovery still depends on costly trial-and-error experiments.

Research Focus

The AI Co-Scientist Stack

Mapping the hard region · click to sample

data-rich · benchmarked active discovery no database yet · my focus

benchmark-rich problems materials discovery the hard region Where trial-and-error gets too expensive. system complexity → data cost →

Agentic Hypothesis Generation

DToR: a tree-structured deep-research agent that runs entirely on local hardware and wins ~79% of head-to-head comparisons with commercial deep-research systems across 27 nanomaterials/device topics.

Device Digital Twins

T³ translates literature into topology-aware device digital twins. 92.3% sensitivity prediction accuracy; 123 million PubChem candidates screened.

Rapid Physical Validation

RAPIDS benchmarks MLIPs against DFT across 5,567 probe–target dimers. Packaged as a validation tool that autonomous LLM agents can call.

Text

AI reads the literature and extracts structured device knowledge.

Twin

The full device context becomes a topology-aware graph.

Translation

The twin ranks new candidate materials and molecules.

cost

accuracy

throughput

n = 40

Not every candidate deserves full-cost validation. Drag the fidelity up and watch the field thin out.

Click any stage.

These pieces are being wired together under BRAINIAC into one autonomous discovery loop. DToR generates research hypotheses (arXiv). T³ turns literature into device digital twins for candidate screening; accepted at SIGKDD 2026 AI4Science, with a Spotlight Oral at ICLR 2026 AI4Mat (OpenReview, code). RAPIDS validates candidates at the atomistic level (ICML 2026 AI4Physics: OpenReview).

Advised by Prof. Junhong Chen (PME/Argonne) and Prof. Yuxin Chen (CS).