NEST is a nested transformer for sequences of multisets that uses masked set modeling to learn improved set-level representations from hierarchical event streams like EHRs.
An exploration of hierarchical attention transformers for efficient long document classification
3 Pith papers cite this work, alongside 17 external citations. Polarity classification is still indexing.
3
Pith papers citing it
17
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A two-level overlapping-Schwarz attention operator approximates the inverse 1-D Poisson operator more accurately and with about 8.6x fewer parameters than global low-rank attention on synthetic Fourier tests.
The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.
citing papers explorer
-
NEST: Nested Event Stream Transformer for Sequences of Multisets
NEST is a nested transformer for sequences of multisets that uses masked set modeling to learn improved set-level representations from hierarchical event streams like EHRs.
-
Overlapping Schwarz Attention: Hierarchical Attention via Domain Decomposition
A two-level overlapping-Schwarz attention operator approximates the inverse 1-D Poisson operator more accurately and with about 8.6x fewer parameters than global low-rank attention on synthetic Fourier tests.
-
The Rise and Potential of Large Language Model Based Agents: A Survey
The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.