MAE (Masked Autoencoder)
Open in the interactive archive →
Download the covers: Floppy card · VHS cover · Vinyl cover
A to Z
- A · App
- No
- B · Built By
- Meta AI
- C · CEO & Politics
- Mark Zuckerberg — Centrist / shifted right 2024–26; accommodative of Trump admin; July 2026 WSJ op-ed on distributed superintelligence
- D · Date
- 2021
- E · Expertise
- Intermediate+
- F · Free Tier
- Yes
- G · Generates
- Text only
- H · Deployment
- Cloud + Local (open weights)
- I · Inputs
- Text
- J · Jurisdiction
- USA
- K · Key Staffers
- Alexandr Wang (Chief AI Officer, Meta Superintelligence Labs), Nat Friedman (MSL co-lead), Chris Cox (Chief Product Officer)
- L · Languages
- English-primary
- M · Model Type
- Vision/CV
- N · Safety Issues
- None reported
- O · Open Source
- Yes — open weights
- P · Pricing
- Free for non-commercial use (open weights, CC BY-NC 4.0)
- Q · AIDb Rating
- 6/10 · AIDb v2.0 (rule-based): Capability 6/10 · Currency 4/10 · Access 9/10 · Significance 7/10 → 6.2
- R · What Makes It Special
- Meta AI's MAE (Masked Autoencoders), a self-supervised vision method that masks a high share of image patches (such as 75%) and reconstructs the missing pixels, using an asymmetric encoder that sees only the visible patches and a lightweight decoder; it trains large models 3x or more faster, and a vanilla ViT-Huge reached 87.8% ImageNet accuracy, the best among methods using only ImageNet-1K data.
- S · Stock / Status
- $752 (META, Sep 25, 2026)
- T · Training Cutoff
- [UNKNOWN]
- U · Users
- [UNKNOWN]
- V · Voice Chat
- No
- W · Weights
- Downloadable
- X · X Handle
- @AIatMeta
- Y · Year Founded
- [UNKNOWN]
- Z · Bottom Line
- Open-weights Vision/CV from Meta AI, released 2021.
Data completeness 88% · Last verified 2026-08-09 · Primary source ↗
Cite this
“MAE (Masked Autoencoder).” AIDb — The AI Database. Verified 2026-08-09. https://theaidatabase.com/m/mae-masked-autoencoder.html
More from Meta AI
AudioCraft · BLT · Chameleon · CM3Leon · Code Llama · Code Llama 13B · Code Llama 34B · Code Llama 70B