FRACTAL integrates fractional recurrent architecture into SSMs using a tunable singularity index to capture multi-scale temporal features, reporting 87.11% average on Long Range Arena and outperforming S5.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
HELIX uses learnable feature identities and hybrid temporal-feature attention to achieve state-of-the-art time series imputation across multiple datasets and settings.
A multitask deep learning model using autoencoders for personalized stress prediction from mobile sensors reports 45.6% higher F1 score than prior work on the StudentLife dataset.
citing papers explorer
-
FRACTAL: SSM with Fractional Recurrent Architecture for Computational Temporal Analysis of Long Sequences
FRACTAL integrates fractional recurrent architecture into SSMs using a tunable singularity index to capture multi-scale temporal features, reporting 87.11% average on Long Range Arena and outperforming S5.
-
HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputation
HELIX uses learnable feature identities and hybrid temporal-feature attention to achieve state-of-the-art time series imputation across multiple datasets and settings.
-
Personalized Student Stress Prediction with Deep Multitask Network
A multitask deep learning model using autoencoders for personalized stress prediction from mobile sensors reports 45.6% higher F1 score than prior work on the StudentLife dataset.