Scholar Feed

Parameter-efficient fine-tuning (LoRA family)

greedy layer selection (kaplun2023less)

Superseded baseline#671 of 1,113 most-superseded

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

1 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites greedy layer selection (kaplun2023less) as a baseline.

demanding considerable computational resources and time for initiation
— Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.