On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “question-centric”

qDKT: Question-centric Deep Knowledge Tracingcs.LG

qDKT improves KT models by considering individual question outcomes.

problem Ignoring question-specific outcomes leads to inaccurate learner skill tracking.

method qDKT incorporates graph Laplacian regularization and uses a fastText-inspired initialization scheme.

result qDKT achieves state-of-the-art performance in predicting learner outcomes.

knowledge tracing deep learning question-centric graph Laplacian fastText

2020-05-25abs ↗pdf ↗

A Question-Centric Model for Visual Question Answering in Medical Imagingcs.CV

A new model answers questions about medical images.

problem Lack of transparency in deep learning models for medical imaging.

method A question-centric model that queries image models directly.

result The model achieves equal or higher accuracy than existing methods.

medical imaging deep learning question answering transparency image analysis

2020-03-02abs ↗pdf ↗