build1 publisher
Removing Mamba-2 from a four-mixer stack cost more than making the stack uniform
VIDRAFT AI Research spread seven sequence mixers over 49 layers on a 7x7 Latin square so depth placement could not confound composition. The ablation that carries the finding ran on a 16-layer proxy at 700.9M parameters.
Publishers:dev.to
Reality
- Evidence48
- Adoption20
- Hype gap+15
- Incentives40
- Confidence55