Elton Pan

Elton Pan, Christopher Karpovich, Elsa Olivetti

A major obstacle to the realization of novel inorganic materials with desirable properties is the inability to perform efficient optimization across both materials properties and synthesis of those materials. In this work, we propose a reinforcement learning (RL) approach to inverse inorganic materials design, which can identify promising compounds with specified properties and synthesizability constraints. Our model learns chemical guidelines such as charge and electronegativity neutrality while maintaining chemical diversity and uniqueness. We demonstrate a multi-objective RL approach, which can generate novel compounds with targeted materials properties including formation energy and bulk/shear modulus alongside a lower sintering temperature synthesis objectives. Using this approach, the model can predict promising compounds of interest, while suggesting an optimized chemical design space for inorganic materials discovery.

Xiaochen Du, Juno Nam, Jaemoo Choi et al.

Sampling from discrete distributions with multiple modes and energy barriers is fundamental to machine learning and computational physics. Recent discrete neural samplers like MDNS suffer from mode collapse and fail to sample high-energy barrier regions between modes, which is critical for free energy estimation and understanding phase transitions. We propose Metadynamics Discrete Neural Sampler (MetaDNS), a general framework integrating well-tempered metadynamics into discrete diffusion or autoregressive samplers. By maintaining an adaptive, history-dependent bias potential along selected low-dimensional coordinates, MetaDNS forces exploration of previously inaccessible regions, enabling free energy reconstruction infeasible with standard neural samplers due to a lack of high-energy samples. On challenging low-temperature benchmarks including Ising, Potts, and the copper-gold binary alloy, MetaDNS reproduces the thermodynamic distribution. Compared to MCMC-based metadynamics, MetaDNS also achieves comparable exploration requiring fewer bias deposition steps.

Magdalena Lederbauer, Siddharth Betala, Xiyao Li et al.

The development of synthesis procedures remains a fundamental challenge in materials discovery, with procedural knowledge scattered across decades of scientific literature in unstructured formats that are challenging for systematic analysis. In this paper, we propose a multi-modal toolbox that employs large language models (LLMs) and vision language models (VLMs) to automatically extract and organize synthesis procedures and performance data from materials science publications, covering text and figures. We curated 81k open-access papers, yielding LeMat-Synth (v 1.0): a dataset containing synthesis procedures spanning 35 synthesis methods and 16 material classes, structured according to an ontology specific to materials science. The extraction quality is rigorously evaluated on a subset of 2.5k synthesis procedures through a combination of expert annotations and a scalable LLM-as-a-judge framework. Beyond the dataset, we release a modular, open-source software library designed to support community-driven extension to new corpora and synthesis domains. Altogether, this work provides an extensible infrastructure to transform unstructured literature into machine-readable information. This lays the groundwork for predictive modeling of synthesis procedures as well as modeling synthesis--structure--property relationships.

Thorben Prein, Elton Pan, Janik Jehkul et al.

Inorganic synthesis planning currently relies primarily on heuristic approaches or machine-learning models trained on limited datasets, which constrains its generality. We demonstrate that language models, without task-specific fine-tuning, can recall synthesis conditions. Off-the-shelf models, such as GPT-4.1, Gemini 2.0 Flash and Llama 4 Maverick, achieve a Top-1 precursor-prediction accuracy of up to 53.8 % and a Top-5 performance of 66.1 % on a held-out set of 1,000 reactions. They also predict calcination and sintering temperatures with mean absolute errors below 126 °C, matching specialized regression methods. Ensembling these language models further enhances predictive accuracy and reduces inference cost per prediction by up to 70 %. We subsequently employ language models to generate 28,548 synthetic reaction recipes, which we combine with literature-mined examples to pretrain a transformer-based model, SyntMTE. After fine-tuning on the combined dataset, SyntMTE reduces mean-absolute error in sintering temperature prediction to 73 °C and in calcination temperature to 98 °C. This strategy improves models by up to 8.7 % compared with baselines trained exclusively on experimental data. Finally, in a case study on Li7La3Zr2O12 solid-state electrolytes, we demonstrate that SyntMTE reproduces the experimentally observed dopant-dependent sintering trends. Our hybrid workflow enables scalable, data-efficient inorganic synthesis planning.

Thorben Prein, Elton Pan, Sami Haddouti et al.

Retrosynthesis strategically plans the synthesis of a chemical target compound from simpler, readily available precursor compounds. This process is critical for synthesizing novel inorganic materials, yet traditional methods in inorganic chemistry continue to rely on trial-and-error experimentation. Emerging machine-learning approaches struggle to generalize to entirely new reactions due to their reliance on known precursors, as they frame retrosynthesis as a multi-label classification task. To address these limitations, we propose Retro-Rank-In, a novel framework that reformulates the retrosynthesis problem by embedding target and precursor materials into a shared latent space and learning a pairwise ranker on a bipartite graph of inorganic compounds. We evaluate Retro-Rank-In's generalizability on challenging retrosynthesis dataset splits designed to mitigate data duplicates and overlaps. For instance, for Cr2AlB2, it correctly predicts the verified precursor pair CrB + Al despite never seeing them in training, a capability absent in prior work. Extensive experiments show that Retro-Rank-In sets a new state-of-the-art, particularly in out-of-distribution generalization and candidate set ranking, offering a powerful tool for accelerating inorganic material synthesis.

Elton Pan, Soonhyoung Kwon, Sulin Liu et al.

The synthesis of crystalline materials, such as zeolites, remains a significant challenge due to a high-dimensional synthesis space, intricate structure-synthesis relationships and time-consuming experiments. Considering the one-to-many relationship between structure and synthesis, we propose DiffSyn, a generative diffusion model trained on over 23,000 synthesis recipes spanning 50 years of literature. DiffSyn generates probable synthesis routes conditioned on a desired zeolite structure and an organic template. DiffSyn achieves state-of-the-art performance by capturing the multi-modal nature of structure-synthesis relationships. We apply DiffSyn to differentiate among competing phases and generate optimal synthesis routes. As a proof of concept, we synthesize a UFI material using DiffSyn-generated synthesis routes. These routes, rationalized by density functional theory binding energies, resulted in the successful synthesis of a UFI material with a high Si/Al$_{\text{ICP}}$ of 19.0, which is expected to improve thermal stability and is higher than that of any previously recorded.

Elton Pan, Panagiotis Petsagkourakis, Max Mowbray et al.

Reinforcement learning (RL) is a control approach that can handle nonlinear stochastic optimal control problems. However, despite the promise exhibited, RL has yet to see marked translation to industrial practice primarily due to its inability to satisfy state constraints. In this work we aim to address this challenge. We propose an 'oracle'-assisted constrained Q-learning algorithm that guarantees the satisfaction of joint chance constraints with a high probability, which is crucial for safety critical tasks. To achieve this, constraint tightening (backoffs) are introduced and adjusted using Broyden's method, hence making them self-tuned. This results in a general methodology that can be imbued into approximate dynamic programming-based algorithms to ensure constraint satisfaction with high probability. Finally, we present case studies that analyze the performance of the proposed approach and compare this algorithm with model predictive control (MPC). The favorable performance of this algorithm signifies a step toward the incorporation of RL into real world optimization and control of engineering systems, where constraints are essential in ensuring safety.