The field of materials science is moving towards the development of more efficient and systematic methods for discovering and synthesizing new materials. This is being driven by advances in machine learning and data management, which are enabling researchers to extract and organize large amounts of data from scientific literature and experimental results. One key area of focus is the development of predictive models that can guide the synthesis of new materials, taking into account factors such as synthesizability and defect phase diagrams. Another area of research is the creation of large-scale datasets and tools for extracting structured information from chemical literature, which will facilitate the training of machine learning models and accelerate progress in the field. Notable papers in this area include:

• LeMat-Synth, which provides a multi-modal toolbox for curating synthesis procedure databases from scientific literature.
• A Synthesizability-Guided Pipeline for Materials Discovery, which develops a combined compositional and structural synthesizability score to predict which compounds can be synthesized in a laboratory.
• RxnCaption, which reformulates reaction diagram parsing as a visual prompt guided captioning problem, achieving state-of-the-art performance on multiple metrics.