SpecTM uses spectral targeted masking in multi-task self-supervised pretraining to reach R²=0.695 current-week and R²=0.620 8-day-ahead microcystin predictions on NASA PACE Lake Erie data, beating baselines with 2.2x better label efficiency.
Masked autoencoders are scalable vision learners
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SpecTM: Spectral Targeted Masking for Trustworthy Foundation Models
SpecTM uses spectral targeted masking in multi-task self-supervised pretraining to reach R²=0.695 current-week and R²=0.620 8-day-ahead microcystin predictions on NASA PACE Lake Erie data, beating baselines with 2.2x better label efficiency.