Saved in:
Bibliographic Details
Main Authors: Meng, Jiuchun, Sun, Lichao, Wang, Xiumei, Zhu, Dandan, Zhou, Xingping
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.06998
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910227672072192
author Meng, Jiuchun
Sun, Lichao
Wang, Xiumei
Zhu, Dandan
Zhou, Xingping
author_facet Meng, Jiuchun
Sun, Lichao
Wang, Xiumei
Zhu, Dandan
Zhou, Xingping
contents The emergence of the non-Hermitian skin effect, distinguished by the exponential localization of bulk states onto boundaries in open systems, has redefined the conventional band theory. It can be established through the generalized Brillouin zone framework, the amoeba formulation or generalized Fermi surface in the different dimensions. However, its algorithmic implementation is still challenging in the high-dimensional cases. The large language models (LLM), functioning as the new paradigm in machine learning, can help tack scientific problems. Here, we propose a framework composed by domain-adaptive Multimodal model for mathematics to identify topological invariants. We feed the eigenvalues and eigenvectors of the Hamiltonian in momentum space into our model as two input modalities. Since our research requires the MLLM to process complex numerical calculations and mathematical reasoning simultaneously, we replace the general reasoning backbone with a specific mathematic LLM. This design decouples front-end physical representation alignment from back-end mathematical inference, allowing our model to extract topological information more effectively. Our results provide a paradigm for future studies on topological invariants identification via LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06998
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Identifying Topological Invariants of Non-Hermitian Systems via Domain-Adaptive Multimodal Model for Mathematics
Meng, Jiuchun
Sun, Lichao
Wang, Xiumei
Zhu, Dandan
Zhou, Xingping
Other Condensed Matter
The emergence of the non-Hermitian skin effect, distinguished by the exponential localization of bulk states onto boundaries in open systems, has redefined the conventional band theory. It can be established through the generalized Brillouin zone framework, the amoeba formulation or generalized Fermi surface in the different dimensions. However, its algorithmic implementation is still challenging in the high-dimensional cases. The large language models (LLM), functioning as the new paradigm in machine learning, can help tack scientific problems. Here, we propose a framework composed by domain-adaptive Multimodal model for mathematics to identify topological invariants. We feed the eigenvalues and eigenvectors of the Hamiltonian in momentum space into our model as two input modalities. Since our research requires the MLLM to process complex numerical calculations and mathematical reasoning simultaneously, we replace the general reasoning backbone with a specific mathematic LLM. This design decouples front-end physical representation alignment from back-end mathematical inference, allowing our model to extract topological information more effectively. Our results provide a paradigm for future studies on topological invariants identification via LLMs.
title Identifying Topological Invariants of Non-Hermitian Systems via Domain-Adaptive Multimodal Model for Mathematics
topic Other Condensed Matter
url https://arxiv.org/abs/2604.06998