A boundary-forcing masked modeling paradigm for self-supervised vision pretraining yields a 1B model rivaling 7B models on dense spatial perception tasks.
BEiT: BERT pre-training of image transformers
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative 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
-
Vision Pretraining for Dense Spatial Perception
A boundary-forcing masked modeling paradigm for self-supervised vision pretraining yields a 1B model rivaling 7B models on dense spatial perception tasks.
-
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.