SSM/Mamba long-range dependency decays exponentially with the time gap by construction; a proposed interaction-based hidden state update can break this decay, but its proven stability covers only a restrictive special case.
Bert: Pre-training of deep bidirectional transformers for language understanding
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
2025 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Rethinking the long-range dependency in Mamba/SSM and transformer models
SSM/Mamba long-range dependency decays exponentially with the time gap by construction; a proposed interaction-based hidden state update can break this decay, but its proven stability covers only a restrictive special case.