2 papers
cs.LG2026
HARP: Efficient Data Selection for Finetuning Large Language Models
Ning Wang, Zhengxin Zhang, Maosen Tang +3
Finetuning data selection requires balancing two competing goals: selecting examples that improve the downstream objective, and doing so without repeatedly finetuning models. Train…
cs.LG2026
Rational Neural Networks have Expressivity Advantages
Maosen Tang, Alex Townsend
We study neural networks with trainable low-degree rational activation functions and show that they are more expressive and parameter-efficient than modern piecewise-linear and smo…