The authors collected and released over 350 hours of multi-site PPG, acceleration, and temperature data from four body-worn devices during free-living activities, with benchmarks showing site-dependent heart-rate estimation errors ranging from 2.3 bpm (earring) to 8.7 bpm (necklace).
Weighted sparsity regular- ization for solving the inverse eeg problem: A case study
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
MUFASA, an information utility-aware preprocessing framework, consistently improves computational pathology model performance and interpretability by selectively excluding artifacts and low-utility tiles while preserving diagnostically relevant tissue.
A context-fusion framework that combines retrieved image-report examples and learned prompt tokens lets a frozen VLM produce accurate endoscopic polyp reports with very few trainable parameters.
In noiseless simulations, EEG source reconstructions are most accurate when the forward source model matches the inverse method's source prior, e.g., the point-like Local subtraction model paired with the sparse SHAL1R solver.
citing papers explorer
-
Multi-site PPG: An In-the-Wild Physiological Dataset from Emerging Multi-site Wearables
The authors collected and released over 350 hours of multi-site PPG, acceleration, and temperature data from four body-worn devices during free-living activities, with benchmarks showing site-dependent heart-rate estimation errors ranging from 2.3 bpm (earring) to 8.7 bpm (necklace).
-
MUFASA: An Information Utility-Aware Preprocessing Framework for Reliable Model Reasoning in Computational Pathology
MUFASA, an information utility-aware preprocessing framework, consistently improves computational pathology model performance and interpretability by selectively excluding artifacts and low-utility tiles while preserving diagnostically relevant tissue.
-
From Generalist to Specialist: A Context-Fusion Framework for Endoscopic Polyp Reporting with a Frozen VLM
A context-fusion framework that combines retrieved image-report examples and learned prompt tokens lets a frozen VLM produce accurate endoscopic polyp reports with very few trainable parameters.
-
Forward--Inverse Interplay in FEM-Based EEG Source Imaging: Distributional Signatures of Advanced Source Models and Inverse Solvers
In noiseless simulations, EEG source reconstructions are most accurate when the forward source model matches the inverse method's source prior, e.g., the point-like Local subtraction model paired with the sparse SHAL1R solver.