AI models
Cross-lingual alignment
Training compute
2.6×10¹⁸ FLOP
Published
Apr 4, 2019
Cross-lingual alignment is an AI model developed by Tel Aviv University and Massachusetts Institute of Technology (MIT) (Israel and United States), first published in April 2019. It works in the language domain, on tasks such as translation.
Training it took an estimated 2.6×10¹⁸ FLOP of compute (estimation method: hardware). Training ran on NVIDIA GeForce GTX 1080 Ti.
Access: Open weights (unrestricted). Its weights are openly available. It is built on top of ELMo. The reference paper has 221 citations. Epoch AI rates the confidence of this record as speculative.
Full record
- Organization
- Tel Aviv University, Massachusetts Institute of Technology (MIT)
- Country of organization
- Israel, United States
- Domain
- Language
- Task
- Translation
- Training compute
- 2.6×10¹⁸ FLOP
- Compute estimation method
- Hardware
- Training hardware
- NVIDIA GeForce GTX 1080 Ti
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Base model
- ELMo
- Citations
- 221
- Epoch confidence
- Speculative
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models