Shawn Tan
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1
Frequent co-authors
Research Timeline
2026
Variable-Width Transformers
This paper proposes a new architecture for transformer-based language models called 'former', which allocates capacity non-uniformly across network depth by maintaining wider early and late layers while narrowing middle layers.
Highlighted terms show continued research focus across papers
Papers
cs.CLEmpiricalRecentJun 16, 2026
Variable-Width Transformers
Zhaofeng Wu, Oliver Sieberling, Shawn Tan, Rameswar Panda +2 more
This paper proposes a new architecture for transformer-based language models called 'former', which allocates capacity non-uniformly across network depth by maintaining wider early and late layers whi…
View →