Tag
GeoRVQ introduces a decoder-aware masked token model for physiological signals that improves accuracy and reduces decoded distortion by accounting for local response and residual dependencies in residual vector quantization.
PhysioBench introduces a unified benchmark for physiological signal question answering, harmonizing 22 datasets into 61.4 million questions across 30 tasks to evaluate the performance of various AI models.
The paper proposes CoMA-DiT, a bidirectional cross-modal Diffusion Transformer for latent augmentation in multimodal brain state decoding, which enhances performance in tasks like auditory attention decoding and emotion recognition by using paired modalities as mutual supervisory signals.
This paper evaluates the use of self-supervised learning on PPG data for real-life emotion detection, finding that general representations fail without individual personalization.
Proposes ReCoGen, a two-stage framework for multimodal-conditioned time-series generation under irregular missingness, achieving state-of-the-art downstream utility on physiological benchmarks.
Proposes using remote photoplethysmography (rPPG) waveforms to detect talking-face deepfakes, achieving AUC of 0.806 on the Celeb-DF++ TF subset, competitive with the best general-purpose detectors.
Timesynth introduces a controlled benchmarking framework for health-signal digital twins, including a physiological signal generator and diagnostics to evaluate temporal fidelity, revealing that pointwise metrics fail to capture phase and frequency distortions in forecasting models.
This paper introduces a retrieval-augmented personalization method for wearable stress detection using frozen foundation models, achieving near-supervised fine-tuning performance without requiring labeled user data.
This paper evaluates deep learning models (LSTM, TCN, Transformer) on the WESAD dataset for multimodal emotion recognition from physiological signals, showing that an ensemble achieves 98.91% accuracy.
This study investigates machine learning models to predict exam outcomes using physiological data such as electrodermal activity, heart rate, and skin temperature, finding that both deep learning approaches and simpler models like random forests can be effective.
The paper proposes Synheart Capacity, a theory-driven multimodal learning framework that models cognitive capacity dynamics from wearable cardiac and electrodermal signals, enabling continuous estimation of mental effort and stress states.
Google researchers propose SensorFM, a foundation model trained on over 1 trillion minutes of unlabeled wearable data from 5 million people, which learns general physiological patterns and outperforms engineered features on 34 of 35 health prediction tasks.
Introduces Peak-Detector, a framework that uses instruction-tuned large language models for robust, cross-modal, and explainable peak detection in physiological signals like ECG, PPG, BCG, and BSG. The method transforms time-series data into a condensed 'peak-representation' format and is optimized via supervised fine-tuning followed by reinforcement learning with a multi-objective reward.
Introduces NormWear-2, a world model that encodes multivariate physiological signals and clinical interventions into a shared latent space, using chaos-theoretic balancing to improve long-horizon forecasting across daily life, point-of-care, and clinical settings.