arXiv subjects

Andrew Salij

Publications and source records attributed to Andrew Salij.

3 recordsLinked to original sources

arXiv2026

Generative Chemical Language Models for Energetic Materials Discovery

The discovery of new energetic materials remains a pressing challenge hindered by limited availability of high-quality data. To address this, we have developed generative molecular language models that have been pretrained on extensive chemical data and then fine-tuned with curated energetic materials datasets. This transfer-learning strategy extends the chemical language model capabilities beyond the pharmacological space in which they have been predominantly developed, offering a framework applicable to other data-spare discovery problems. Furthermore, we discuss the benefits of fragment-based molecular encodings for chemical language models, in particular in constructing synthetically accessible structures. Together, these advances provide a foundation for accelerating the design of next-generation energetic materials with demanding performance requirements.

physics.chem-ph↗

arXiv2025

Meta-GPT: Decoding the Metasurface Genome with Generative Artificial Intelligence

Advancing artificial intelligence for physical sciences requires representations that are both interpretable and compatible with the underlying laws of nature. We introduce METASTRINGS, a symbolic language for photonics that expresses nanostructures as textual sequences encoding materials, geometries, and lattice configurations. Analogous to molecular textual representations in chemistry, METASTRINGS provides a framework connecting human interpretability with computational design by capturing the structural hierarchy of photonic metasurfaces. Building on this representation, we develop Meta-GPT, a foundation transformer model trained on METASTRINGS and finetuned with physics-informed supervised, reinforcement, and chain-of-thought learning. Across various design tasks, the model achieves <3% mean-squared spectral error and maintains >98% syntactic validity, generating diverse metasurface prototypes whose experimentally measured optical responses match their target spectra. These results demonstrate that Meta-GPT can learn the compositional rules of light-matter interactions through METASTRINGS, laying a rigorous foundation for AI-driven photonics and representing an important step toward a metasurface genome project.

physics.optics↗

arXiv2020

Microscopic theory of cavity-confined monolayer semiconductors: polariton-induced valley relaxation and the prospect of enhancing and controlling the valley pseudospin by chiral strong coupling

We apply a microscopic theory of exciton-polaritons in cavity-confined monolayer transition-metal dichalcogenides including both optical polarizations in the monolayer plane, allowing to describe how chiral cavity photons interact with the valley degrees of freedom of the active material. Upon polariton formation, the degenerate excitons inhabiting the two inequivalent valleys are shown to assume bonding and antibonding superpositions as a result of cavity-mediated intravalley interactions combined with intervalley Coulomb interactions. This is representative of a polariton-induced coherent mixing of the valley polarization. In combination with disorder, this mixing is prone to open a new valley relaxation channel which attains significance with increasing cavity coupling. Importantly, we show that optical cavities with an asymmetric reflectance of left- and right-handed circularly-polarized photons offer a considerably more robust platform to realize a conserved valley polarization, as the valley localization of excitons is reinstated by an asymmetric Rabi splitting which lifts their degeneracy. Moreover, we show this degeneracy lifting to allow for wavelength-selective access to the valley pseudospin by means of a polariton-induced chiral Stark effect, offering interesting opportunities for valleytronic applications.

cond-mat.mtrl-sci↗