A spectral-dictionary VLM claims to match mid-scale baselines without convolutions or self-attention, but its O(L log L) complexity argument is not supported by the equations as written.
Graph Laplacian Wavelet Transformer via Learnable Spectral Decomposition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Existing sequence to sequence models for structured language tasks rely heavily on the dot product self attention mechanism, which incurs quadratic complexity in both computation and memory for input length N. We introduce the Graph Wavelet Transformer (GWT), a novel architecture that replaces this bottleneck with a learnable, multi scale wavelet transform defined over an explicit graph Laplacian derived from syntactic or semantic parses. Our analysis shows that multi scale spectral decomposition offers an interpretable, efficient, and expressive alternative to quadratic self attention for graph structured sequence modeling.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
From Pixels and Words to Waves: A Unified Framework for Spectral Dictionary vLLMs
A spectral-dictionary VLM claims to match mid-scale baselines without convolutions or self-attention, but its O(L log L) complexity argument is not supported by the equations as written.