SAFE (Parameter-efficient fine-tuning (LoRA family)): superseded — cited as a baseline and beaten by newer methods. 0 paper(s) critique it, 1 beat it on benchmarks — #362 of 1113 most-superseded. Sub-problem: cluster led by TimeSformer. Newer alternatives in the same sub-problem include local vision-language models (VLMs) with LoRA fine-tuning.

Parameter-efficient fine-tuning (LoRA family)

SAFE

SAFE: Machine Unlearning With Shard Graphs

Superseded baseline#362 of 1,113 most-superseded · first seen Apr 25, 2023

Superseded — cited as a baseline and beaten by newer methods

0 papers critique it · 1 beat it on benchmarks

Beaten on benchmarks

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

VELoRA beats SAFE
50.89 vs 50.17
Precision · [HARDVS benchmark]
VELoRA: A Low-Rank Adaptation Approach for Efficient RGB-Event based Recognition

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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.

local vision-language models (VLMs) with LoRA fine-tuningCan Local Vision-Language Models improve Activity Recognition over Vision Transformers? -- Case Study on Newborn Resuscitation
Feb 12, 2026