Large language models (LLMs) are reshaping many aspects of materials science and chemistry research, enabling advances in molecular property prediction, materials design, scientific automation, knowledge extraction, and more. Recent developments demonstrate that the latest class of models are able to integrate structured and unstructured data, assist in hypothesis generation, and streamline research workflows. To explore the frontier of LLM capabilities across the research lifecycle, we review applications of LLMs through 32 total projects developed during the second annual LLM hackathon for applications in materials science and chemistry, a global hybrid event. These projects spanned seven key research areas: (1) molecular and material property prediction, (2) molecular and material design, (3) automation and novel interfaces, (4) scientific communication and education, (5) research data management and automation, (6) hypothesis generation and evaluation, and (7) knowledge extraction and reasoning from the scientific literature. Collectively, these applications illustrate how LLMs serve as versatile predictive models, platforms for rapid prototyping of domain-specific tools, and much more. In particular, improvements in both open source and proprietary LLM performance through the addition of reasoning, additional training data, and new techniques have expanded effectiveness, particularly in low-data environments and interdisciplinary research. As LLMs continue to improve, their integration into scientific workflows presents both new opportunities and new challenges, requiring ongoing exploration, continued refinement, and further research to address reliability, interpretability, and reproducibility.

Determining molecular taste remains a significant challenge in food science. Here, we present FART (Flavor Analysis and Recognition Transformer), a chemical language model capable of predicting molecular taste from chemical structure. Trained on the largest public dataset (15,025 compounds) of molecular tastants to date, FART is the first model capable of parallel predictions across four taste categories: sweet, bitter, sour, and umami. FART achieves an accuracy above 91% for parallel taste prediction and outperforms previous state-of-the-art binary classifier models that specialize on predicting one taste class. Its transformer architecture allows for interpretability through gradient-based visualization of molecular features. The model identifies key structural elements driving taste properties and demonstrates utility in analyzing known tastants as well as novel compounds. By releasing both the model and dataset, we equip the food science community with tools for rapid taste prediction, accelerating flavor compound development and enabling systematic exploration of taste chemistry.

The intricate relationship between electrons and the crystal lattice is a linchpin in condensed matter, traditionally described by the Fröhlich model encompassing the lowest-order lattice-electron coupling. Recently developed quantum acoustics, emphasizing the wave nature of lattice vibrations, has enabled the exploration of previously uncharted territories of electron–lattice interaction not accessible with conventional tools such as perturbation theory. In this context, our agenda here is two-fold. First, we showcase the application of machine learning methods to categorize various interaction regimes within the subtle interplay of electrons and the dynamical lattice landscape. Second, we shed light on a nebulous region of electron dynamics identified by the machine learning approach and then attribute it to transient localization, where strong lattice vibrations result in a momentary Anderson prison for electronic wavepackets, which are later released by the evolution of the lattice. Overall, our research illuminates the spectrum of dynamics within the Fröhlich model, such as transient localization, which has been suggested as a pivotal factor contributing to the mysteries surrounding strange metals. Furthermore, this paves the way for utilizing time-dependent perspectives in machine learning techniques for designing materials with tailored electron–lattice properties.

Determining molecular taste remains a significant challenge in food science. Here, we present FART (Flavor Analysis and Recognition Transformer), a chemical language model capable of predicting molecular taste from chemical structure. Trained on the largest public dataset (15,025 compounds) of molecular tastants to date, FART is the first model capable of parallel predictions across four fundamental taste categories: sweet, bitter, sour, and umami. FART achieves an accuracy above 91% for parallel taste prediction and outperforms previous state-of-the-art binary classifier models that specialize on predicting one taste class. Its transformer architecture allows for interpretability through gradient-based visualization of molecular features. The model identifies key structural elements driving taste properties and demonstrates utility in analyzing known tastants as well as novel compounds. By making both the model and the dataset publicly available, we provide the food science community with tools for rapid taste prediction, potentially accelerating the development of new flavor compounds and enabling systematic exploration of taste chemistry.