- Generative models (guided diffusion models) for materials synthesis planning using molecular and crystalline materials datasets (NeurIPS AI for Materials (Oral Spotlight) paper, 2024 | Code in progress)
- Precursor recommendation for inorganic materials (Paper | Code in progress)
- Synthesis condition prediction for inorganic materials (Chemistry of Materials paper, 2023 | Code)
- Model explainability/interpretability (Aggregated SHAP) for materials synthesis (ACS Central Science paper, 2024 | Code)
- Reinforcement learning (deep Q-learning, policy gradient) for inverse design of inorganic materials (NeurIPS AI for Materials paper, 2022 | npj Computational Materials paper, 2024 | Code)
- Reaction Graph Networks for modeling precursor-target interactions to predict materials synthesis routes (NeurIPS AI for Materials paper, 2024 | Code in progress)
- Materials representation learning (multi-task transformer pretraining) for inorganic materials property/synthesis prediction (NeurIPS AI for Materials paper, 2023 | Code in progress)
-
Natural language processing (automated few-shot learning) for scientific data extraction (Work in progress)
-
Constrained RL for process optimization (Computers & Chemical Engineering paper, 2021 | Code)
- Bayesian optimization for chemistry/materials (Code for AC BO Hackathon)
Google scholar: Google scholar
Email: eltonpan@mit.edu
Linkedin: Linkedin