FlashMorph formulates hybrid layer selection as budget-constrained optimization, trains per-layer gates on synthetic retrieval data with linearization regularization, then discretizes and distills to produce efficient hybrid architectures.
Dijiang: Efficient large language models through compact kernelization.arXiv preprint arXiv:2403.19928, 2024
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Functional Attention replaces pairwise softmax attention with structured linear operators inspired by geometric functional maps to produce compact, resolution-invariant representations for operator learning.
citing papers explorer
-
Morphing into Hybrid Attention Models
FlashMorph formulates hybrid layer selection as budget-constrained optimization, trains per-layer gates on synthetic retrieval data with linearization regularization, then discretizes and distills to produce efficient hybrid architectures.
-
Functional Attention: From Pairwise Affinities to Functional Correspondences
Functional Attention replaces pairwise softmax attention with structured linear operators inspired by geometric functional maps to produce compact, resolution-invariant representations for operator learning.