Revision History
Masked autoencoder (MAE) · 5 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected MAE's ViT-L linear-probe accuracy (75.8%, not 76.0%), the paper's three stated vision-vs-language differences, its alternative reconstruction targets (PCA, not 'high-frequency-aware variants'), the COCO comparison (no DINO or ViT-H entries), and the linear-probe vs fine-tuning gap for contrastive methods (about 5 to 7 points, not 1 to 3) (plus 14 minor fixes)
Version 5 · Nov 4, 2026, 10:46 PM
- Improve internal links (2026-10-13)
Version 4 · Oct 13, 2026, 10:18 AM
- Added 6 contextual internal links
Version 3 · Jul 23, 2026, 03:28 PM