Brief

last 24h

[2/2] 224 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

TOOL · arXiv cs.LG English(EN) · 19h

When Calibration Fails the Vulnerable Hospital: Federated Conformal Risk Control via Risk-Curve Shrinkage

A new research paper introduces Federated Conformal Risk Control (CRC) to address calibration failures in federated AI deployments, particularly in healthcare settings. The proposed method, utilizing risk-curve shrinkage, aims to provide distribution-free guarantees on segmentation quality without sharing sensitive patient data. This approach is designed to protect individual institutions rather than just the average, preventing the concentration of risk on vulnerable hospitals. AI

IMPACT This research could improve the reliability and fairness of AI models in critical applications like healthcare by ensuring robust risk control across all participating institutions.
RESEARCH · arXiv cs.LG English(EN) · 1mo · [2 sources]

Decoding High-Dimensional Finger Motion from EMG Using Riemannian Features and RNNs

Researchers have developed a new framework for decoding high-dimensional finger motion from electromyography (EMG) signals using consumer-grade hardware. This system combines an EMG armband and a webcam to collect a new dataset, EMG-FK, featuring synchronized EMG and 15 finger joint angles from 20 participants. The Temporal Riemannian Regressor (TRR) model, a GRU-based network, processes Riemannian covariance features to achieve state-of-the-art regression accuracy and real-time performance on a Raspberry Pi 5, enabling intuitive control of robotic hands. AI

IMPACT Enables more natural control of prosthetics and AR/XR interfaces through improved EMG decoding.

Brief

When Calibration Fails the Vulnerable Hospital: Federated Conformal Risk Control via Risk-Curve Shrinkage

Decoding High-Dimensional Finger Motion from EMG Using Riemannian Features and RNNs