The authors claim that more attention heads improve transformer conditioning enough to replace depth with width, yielding 30-50% parameter reductions at matched accuracy.
Davit: Dual attention vision transform- ers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Leaner Transformers: More Heads, Less Depth
The authors claim that more attention heads improve transformer conditioning enough to replace depth with width, yielding 30-50% parameter reductions at matched accuracy.