PulseAugur / Brief
EN
LIVE 11:22:49

Brief

last 24h
[2/2] 221 sources

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

  1. RESEARCH · arXiv cs.AI English(EN) · · [2 sources]

    MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data

    Researchers have developed MambaGaze, a new framework designed to accurately assess cognitive load using eye-gaze tracking data. This system utilizes bidirectional Mamba-2 to efficiently model long-range temporal dependencies and an XMD encoding method to explicitly handle missing data, such as that caused by blinks. MambaGaze demonstrated superior performance over existing models on benchmark datasets and is feasible for real-time deployment on edge devices like NVIDIA Jetson platforms. AI

    IMPACT Introduces a novel approach for real-time cognitive load assessment, potentially enabling more responsive human-AI interaction in safety-critical systems.

  2. RESEARCH · arXiv cs.AI English(EN) · · [2 sources]

    CogAdapt: Transferring Clinical ECG Foundation Models to Wearable Cognitive Load Assessment via Lead Adaptation

    Researchers have developed CogAdapt, a framework designed to adapt existing clinical ECG foundation models for use in wearable cognitive load assessment. This is necessary because models trained on clinical data don't directly translate to wearable sensors due to differences in signal configuration and task objectives. CogAdapt utilizes a 'LeadBridge' adapter to convert 3-lead wearable signals to 12-lead representations and a 'ProFine' strategy for progressive fine-tuning, achieving improved performance on public datasets. AI

    IMPACT Enables more accurate and personalized cognitive load assessment from wearable devices by leveraging pre-trained foundation models.