pith. sign in

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

fields

cs.CV 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

roles

method 1

polarities

use method 1

representative citing papers

Diffusion Masked Pretraining for Dynamic Point Cloud

cs.CV · 2026-05-05 · unverdicted · novelty 7.0 · 2 refs

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.

citing papers explorer

Showing 2 of 2 citing papers.

  • Diffusion Masked Pretraining for Dynamic Point Cloud cs.CV · 2026-05-05 · unverdicted · none · ref 1 · 2 links

    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 cs.LG · 2026-05-13 · unverdicted · none · ref 22 · 3 links

    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.