CoFrGeNets implement a continued-fraction function class as plug-in replacements for transformer blocks, delivering competitive or superior downstream performance on GPT2-xl and Llama3-scale models with one-half to two-thirds the parameters.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CoFrGeNet: Continued Fraction Architectures for Language Generation
CoFrGeNets implement a continued-fraction function class as plug-in replacements for transformer blocks, delivering competitive or superior downstream performance on GPT2-xl and Llama3-scale models with one-half to two-thirds the parameters.