Recovering topological information of light by topological learning
Abstract
The evolution of modern-day communication networks towards enhanced capacity and robustness is driving interest in topological light wave as a next-generation information carrier. However, harnessing its potential is hindered by the lack of an effective topological reader, particularly when strong disorder renders conventional readout intractable. Here we address this by introducing TOPO2, an artificial intelligence framework that leverages on topological learning to recover topological information from light. We demonstrate it on highly distorted optical fields with embedded Skyrmion topologies, showing that we can extract the topological numbers in a single shot with just a conventional camera. We showcase its capability in a TOPO2-based communication scheme, sending and recovering information encoded in a topological alphabet, confirming that it outperforms conventional approaches. Our connection of topological photonics with topological AI as a powerful paradigm for robust high-capacity information encoding and processing opens a new path towards topological information optics.
Related
- Bicircular light tunable topological phases and nonlinear Hall responses in odd-parity magnets
- Spatial Engineering of Topological Quantum Matter with Structured Light
- Spin response of a magnetic monopole and quantum Hall response in topological lattice models through local invariants and light
- Tunable topological enhancement of covariant quantum Fisher information via non-Bloch skin effect in non-Hermitian SSH lattices
- Observation of light-induced topological state in graphene
BibTeX
@misc{wang2026recovering,
title = {{Recovering topological information of light by topological learning}},
author = {Benquan Wang and Trishita Das and Yuhan Peng and Tatjana Kleine and Shanshan Chang and Jinhui Chen and Nilo Mata-Cervera and Chunyu Li and Kelin Xia and Andrew Forbes and Yijie Shen},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.06542},
eprint = {2609.06542},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.06542},
}
RIS
TY - UNPB
TI - Recovering topological information of light by topological learning
AU - Benquan Wang
AU - Trishita Das
AU - Yuhan Peng
AU - Tatjana Kleine
AU - Shanshan Chang
AU - Jinhui Chen
AU - Nilo Mata-Cervera
AU - Chunyu Li
AU - Kelin Xia
AU - Andrew Forbes
AU - Yijie Shen
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2609.06542
UR - https://arxiv.org/abs/2609.06542
AB - The evolution of modern-day communication networks towards enhanced capacity and robustness is driving interest in topological light wave as a next-generation information carrier. However, harnessing its potential is hindered by the lack of an effective topological reader, particularly when strong disorder renders conventional readout intractable. Here we address this by introducing TOPO^2, an artificial intelligence framework that leverages on topological learning to recover topological information from light. We demonstrate it on highly distorted optical fields with embedded Skyrmion topologies, showing that we can extract the topological numbers in a single shot with just a conventional camera. We showcase its capability in a TOPO^2-based communication scheme, sending and recovering information encoded in a topological alphabet, confirming that it outperforms conventional approaches. Our connection of topological photonics with topological AI as a powerful paradigm for robust high-capacity information encoding and processing opens a new path towards topological information optics.
ER -