Uncert estimates token importance via temporal uncertainty statistics from Dirichlet-modeled class evidence to enable pruning in spiking transformers.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Uncertainty-Aware Token Importance Estimation in Spiking Transformers
Uncert estimates token importance via temporal uncertainty statistics from Dirichlet-modeled class evidence to enable pruning in spiking transformers.