Search Results for author:
Found 2 papers, 1 papers with code
Pearls from Pebbles: Improved Confidence Functions for Auto-labeling
We develop a tractable version of the framework to obtain \texttt{Colander} (Confidence functions for Efficient and Reliable Auto-labeling), a new post-hoc method specifically designed to maximize performance in TBAL systems.
The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models
Two standard compression techniques are pruning and quantization, with the former eliminating redundant connections in model layers and the latter representing model parameters with fewer bits.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
