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.
Hdt: Hierarchical document transformer
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative 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.
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.