Paperdoi:10.1609/aaai.v40i34.40088

PPGPT: Transferring Next-Token Modeling from Language to PPG Signals

Venue listedDated Mar 14, 2026Added Nov 16, 2026

Authors: Zexing Zhang, Huimin Lu, Qingxin Zhao

AAAI 2026 (Proceedings of the AAAI Conference on Artificial Intelligence, 40(34), 28573–28581)

TL;DR

PPGPT is a photoplethysmography foundation model described in AAAI 2026. The authors reformulate next-token prediction as next-feature token prediction (NFTP) and use a dual-stream encoder that jointly models temporal dynamics and local-global morphological patterns. The official repository names that encoder Hierarchical Spatio-Temporal Fusion (HSTF) and pairs it with a DeepSeekMoE decoder. The paper says the model was pre-trained on a mixed dataset of 1.6 billion data points and evaluated on the authors' BioMTL benchmark: 172 subjects over 285 days, seven tasks. The official README specifies 1,808 four-second fingertip-PPG windows at 1000 Hz, with regression labels for SBP, DBP, blood glucose, heart rate and BMI, and classification labels for mental stress, hypertension and type-2 diabetes. The authors report a 16.5% improvement in F1-score and a 25.9% reduction in MAE versus competing methods, plus few-shot results. Code is on GitHub under MIT; the repository has no trained weights, and BioMTL is released under a data-use agreement.

  • Authors: Zexing Zhang, Huimin Lu, Qingxin Zhao (Changchun University of Technology)
  • Architecture: dual-stream Hierarchical Spatio-Temporal Fusion (HSTF) encoder with a DeepSeekMoE decoder; pre-training objective is next-feature token prediction (NFTP). Official code at https://github.com/PPGPT/AAAI2026 (MIT).
  • Pretraining data: a mixed dataset of 1.6 billion data points (composition not itemized on the publisher abstract or the official repository README).
  • Evaluation: authors’ BioMTL benchmark, 1,808 four-second fingertip-PPG windows (1000 Hz) from 172 subjects over 285 days, seven tasks (SBP, DBP, blood glucose, heart rate, BMI; mental stress, hypertension, type-2 diabetes). Dataset access is by data-use agreement. The repository does not include trained weights.
  • Result: the authors report a 16.5% improvement in F1-score and a 25.9% reduction in MAE versus competing methods on BioMTL, plus few-shot results. Baselines and per-task scores are in the paper.

Results on ChatPPG leaderboards

All leaderboards

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

Tasks & signals

Signals

Keywords

Foundation ModelAAAI

Models

How it works

How PPGPT works: Setup → Method → ResultSetup: PPG (Photoplethysmogram). Method: PPGPT, dual-stream Hierarchical Spatio-Temporal Fusion (HSTF) encoder with a DeepSeekMoE decoder; pre-training objective is next-feature token prediction (NFTP). Official code at https://github.com/PPGPT/AAAI2026 (MIT).. Result: Evaluation (authors’ BioMTL benchmark, 1,808 four-second fingertip-PPG windows (1000 Hz) from 172 subjects over 285 days, seven tasks (SBP, DBP, blood glucose, heart rate, BMI; mental stress, hypertension, type-2 diabetes). Dataset access is by data-use agreement. The repository does not include trained weights.); Result (the authors report a 16.5% improvement in F1-score and a 25.9% reduction in MAE versus competing methods on BioMTL, plus few-shot results. Baselines and per-task scores are in the paper.).SetupPPG: PhotoplethysmogramPPGPhotoplethysmogramMethodPPGPTdual-stream Hierarchical Spatio-Temporal…ResultEvaluation: authors’ BioMTL benchmark, 1,808 four-second fingertip-PPG windows (1000 Hz) from 172 subjects over 285 days, seven tasks (SBP, DBP, blood glucose, heart rate, BMI; mental stress, hypertension, type-2 diabetes). Dataset access is by data-use agreement. The repository does not include trained weights.Evaluationauthors’ BioMTL benchmark, 1,808…Result: the authors report a 16.5% improvement in F1-score and a 25.9% reduction in MAE versus competing methods on BioMTL, plus few-shot results. Baselines and per-task scores are in the paper.Resultthe authors report a 16.5% improvement…

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Zhang, Z., Lu, H., & Zhao, Q. (2026). PPGPT: Transferring Next-Token Modeling from Language to PPG Signals. AAAI 2026. https://doi.org/10.1609/aaai.v40i34.40088
Zhang, Zexing, Huimin Lu, and Qingxin Zhao. 2026. "PPGPT: Transferring Next-Token Modeling from Language to PPG Signals." AAAI 2026. https://doi.org/10.1609/aaai.v40i34.40088.
Zhang, Z., Lu, H. and Zhao, Q. (2026) 'PPGPT: Transferring Next-Token Modeling from Language to PPG Signals', AAAI 2026. doi: 10.1609/aaai.v40i34.40088.
Zhang, Zexing, et al. "PPGPT: Transferring Next-Token Modeling from Language to PPG Signals." AAAI 2026, 2026. https://doi.org/10.1609/aaai.v40i34.40088.
Z. Zhang, H. Lu, and Q. Zhao, "PPGPT: Transferring Next-Token Modeling from Language to PPG Signals," AAAI 2026, 2026, doi: 10.1609/aaai.v40i34.40088.
@inproceedings{zhang2026ppgpt,
  title         = {{PPGPT: Transferring Next-Token Modeling from Language to PPG Signals}},
  author        = {Zhang, Zexing and Lu, Huimin and Zhao, Qingxin},
  year          = {2026},
  booktitle     = {AAAI 2026},
  doi           = {10.1609/aaai.v40i34.40088}
}

Added to the ChatPPG research hub