DiMP uses diffusion to infer clean masked positions from visible context and to model full distributions of point displacements rather than means, delivering 11.21% and 13.65% absolute gains on offline and online action segmentation.
Masked autoencoders are scalable vision learners
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
Sparse autoencoders on EEG transformers extract clinical features, identify three steering regimes, expose age-pathology entanglements and wrecking-ball failures, and map interventions to frequency spectra.
citing papers explorer
-
Diffusion Masked Pretraining for Dynamic Point Cloud
DiMP uses diffusion to infer clean masked positions from visible context and to model full distributions of point displacements rather than means, delivering 11.21% and 13.65% absolute gains on offline and online action segmentation.
-
Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
Sparse autoencoders on EEG transformers extract clinical features, identify three steering regimes, expose age-pathology entanglements and wrecking-ball failures, and map interventions to frequency spectra.