Parameter-efficient fine-tuning (LoRA family)

SNGP

Superseded baseline#211 of 1,113 most-superseded

Superseded — cited as a baseline and beaten by newer methods

1 papers critique it · 1 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites SNGP as a baseline.

However, SNGP's bi-Lipschitz assumptions do not hold for transformers, as dot-product self-attention has an unbounded Lipschitz constant.
LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks

Beaten on benchmarks

Head-to-head results where a newer method reports beating SNGP. Values are copied from the source paper's tables — verify against the cited paper.