RobertCsordas/transformer_generalization
The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.
PythonMIT
Stargazers
- aabzalievUniversity of Michigan
- abodacsOpenCoast
- akeapen
- AlanHassen
- aseifertVienna, Austria
- astariulFleksy
- awhillasLife
- beamiter
- cfoster0
- ChanBongDelhi, India
- cin-hubertDa Nang, Vietnam
- farleylaiQualcomm Technology Inc.
- fly51flyPRIS
- guanfuchenZhejiang University
- him4318Delhi
- josecohenca
- jsilotoUCI
- ku21fanThe University of Tokyo
- lan956
- LinkToPast1900
- masayahingpunoAvante AI
- mdiephuisGeneve, La Suisse
- owenzx
- PrithivirajDamodaranBangkok
- rainfalj
- saichand07
- SharathRaparthy@facebookresearch
- SivilTaramResearcher @ TikTok
- srandouxedgemme.ai
- stjordanisGreece
- teelinsanSapienza University of Rome
- TheodoreGalanosAustrian Institute of Technology
- trangham283
- vahbuna
- ycliu93Georgia Tech
- yilunliaoMIT