We are a multidisciplinary research team integrating AI with synthetic chemistry to accelerate materials discovery. By employing organic, inorganic, and solid-state synthesis strategies, we create novel, programmable crystalline structures with targeted properties, aiming to lead a future where human–AI collaborative workflows are routinely accessible to all laboratories. Our research focuses on several main directions:
 

Digital Reticular Chemistry

We are exploring the integration of large language models (LLMs) and autonomous AI agents to transform chemical research. Chemistry itself is a language, and our AI agents communicate directly with chemists using natural language through low-code/no-code interfaces, enabling automated literature data mining and robotic experimentation and making workflows user-friendly for synthetic chemists.
 

Preditive Synthesis of Framework Materials
 

Traditional synthesis of crystalline materials relies on trial-and-error across multidimensional parameters (e.g., temperature, concentration, ratios, etc.). Our lab integrates chemical knowledge with machine learning to answer the long standing “crystallization challnges” in reticular chemistry: can we predict under which conditions metals and organic linkers crystallize into desired frameworks?

Rational Design of Novel Nano-MOFs

The modularity of reticular chemistry—connecting molecular building blocks into frameworks with predetermined structures and functionalities—offers vast opportunities. We are particularly excited about advancing new design principles and more accessible synthetic methodologies for the (i) high-entropy MOFs and (ii) biocompatible MOFs that can be prepared at the nanoscale and applied in energy, environmental, and therapeutic applications.