VORT assigns learnable fractional orders to tokens and approximates their power-law retention kernels via sum-of-exponentials for efficient long-range dependency modeling in transformers.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A modular neural architecture learns complete Kleene three-valued logic from task data and exhibits uncertainty-preserving propagation plus superior 500-step generalization under Gumbel-softmax training where flat MLPs and transformers fail.
citing papers explorer
-
VORT: Adaptive Power-Law Memory for NLP Transformers
VORT assigns learnable fractional orders to tokens and approximates their power-law retention kernels via sum-of-exponentials for efficient long-range dependency modeling in transformers.
-
THEIA: Learning Complete Kleene Three-Valued Logic in a Pure-Neural Modular Architecture
A modular neural architecture learns complete Kleene three-valued logic from task data and exhibits uncertainty-preserving propagation plus superior 500-step generalization under Gumbel-softmax training where flat MLPs and transformers fail.