EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BioLAMR: A Biomimetically Inspired Large Language Model Adaptation Framework for Automatic Modulation Recognition

Yubo Mao iD, Wei Xu, Jijia Sang iD, Haoan Liu iD

Biomimetics · 21.04.2026 · 11 (4) · 288

DOI: 10.3390/biomimetics11040288 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomimetics, online erschienen am 21.04.2026. Verfasst von Yubo Mao und 3 weiteren Autor:innen. Beteiligte Einrichtung: China Academy of Information and Communication Technology, Beijing 100191, China. Die Arbeit nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automatic modulation recognition (AMR) is increasingly relevant to communication-sensing front ends in robotic and human–robot collaborative systems, where reliable spectrum awareness and adaptive wireless reception are desired. However, existing methods often degrade sharply at low signal-to-noise ratios (SNRs), and large language models (LLMs) are not natively compatible with continuous I/Q signals due to the inherent modality gap. We propose BioLAMR, a GPT-2 adaptation framework for AMR inspired by the auditory system’s parallel time–frequency processing and cortical hierarchy. The framework combines bio-inspired dual-domain feature extraction with parameter-efficient LLM adaptation. BioLAMR includes three components. First, a lightweight dual-domain fusion (LDDF) module extracts complementary time- and frequency-domain features and fuses them through channel and spatial attention. Second, a convolutional embedding module converts continuous I/Q signals into GPT-2-compatible sequences without discrete tokenization. Third, a hierarchical fine-tuning strategy updates only 8.9% of parameters to preserve pretrained knowledge while adapting to modulation recognition. Experiments on the RadioML2016.10a and RadioML2016.10b benchmarks show that BioLAMR achieves overall accuracies of 64.99% and 67.43%, outperforming the strongest competing method by 2.60 and 2.47 percentage points, respectively. Under low-SNR conditions, it reaches 36.78% and 38.14%, the best results among the compared methods. Ablation studies verify the contribution of each component. These results demonstrate that combining dual-domain signal modeling with parameter-efficient GPT-2 adaptation is an effective route to robust AMR in challenging wireless environments.

Schlagwörter

Stichwörter der Autor:innen

automatic modulation recognitioncommunicationlarge language modelsignal processing

Autor:innen und Institutionen

  • China Academy of Information and Communication Technology, Beijing 100191, China.
  • School of Engineering and Design, Technical University of Munich, 80333 Munich, Germany.
  • University of Chinese Academy of Sciences, Beijing 100049, China.

ORCID-Profile: Yubo Mao, Jijia Sang, Haoan Liu

Zitieren

APA

Mao, Y., Xu, W., Sang, J., & Liu, H. (2026). BioLAMR: A Biomimetically Inspired Large Language Model Adaptation Framework for Automatic Modulation Recognition. Biomimetics, 11(4), 288. https://doi.org/10.3390/biomimetics11040288

Vancouver

Mao Y, Xu W, Sang J, Liu H. BioLAMR: A Biomimetically Inspired Large Language Model Adaptation Framework for Automatic Modulation Recognition. Biomimetics. 2026;11(4):288. doi:10.3390/biomimetics11040288

BibTeX
@article{Mao2026,
  author = {Mao, Yubo and Xu, Wei and Sang, Jijia and Liu, Haoan},
  title = {BioLAMR: A Biomimetically Inspired Large Language Model Adaptation Framework for Automatic Modulation Recognition},
  journal = {Biomimetics},
  year = {2026},
  volume = {11},
  number = {4},
  pages = {288},
  doi = {10.3390/biomimetics11040288}
}
Kostenlos starten →