L2P (Parameter-efficient fine-tuning (LoRA family)): superseded — cited as a baseline and beaten by newer methods. 1 paper(s) critique it, 7 beat it on benchmarks — #31 of 1113 most-superseded. Sub-problem: cluster led by InfLoRA. Newer alternatives in the same sub-problem include G2LoRA, CoDyRA, Janus-LoRA, E^2-LoRA, Beyond Feature Fusion.

Method Drift›Parameter-efficient fine-tuning (LoRA family)

Superseded baseline#31 of 1,113 most-superseded

L2P

Parameter-efficient fine-tuning (LoRA family)

superseded — cited as a baseline and beaten by newer methods

1 papers critique it · 7 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites L2P as a baseline.

“a training trick is employed to mask out the classes not relevant to the current task. This trick contradicts the task-free OCL setting”
— Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation

Beaten on benchmarks

Head-to-head results where a newer method reports beating L2P. Values are copied from the source paper's tables — verify against the cited paper.

E$^2$-LoRA beats L2P · Last-Acc [Office-Home]
88.25 vs 80.03
Energy-Structured Low-Rank Adaptation for Continual Learning
E$^2$-LoRA beats L2P · Last-Acc [DomainNet]
69.63 vs 48.72
Energy-Structured Low-Rank Adaptation for Continual Learning
E$^2$-LoRA beats L2P · Last-Acc [ImageNet-R 10-task]
82.77 vs 66.49
Energy-Structured Low-Rank Adaptation for Continual Learning
E$^2$-LoRA beats L2P · Last-Acc [CIFAR-100 10-task]
92.13 vs 82.76
Energy-Structured Low-Rank Adaptation for Continual Learning
E$^2$-LoRA beats L2P · Last-Acc [CUB-200 10-task]
89.77 vs 62.21
Energy-Structured Low-Rank Adaptation for Continual Learning
E$^2$-LoRA beats L2P · Last-Acc [Cars-196 10-task]
75.82 vs 38.18
Energy-Structured Low-Rank Adaptation for Continual Learning
L2L beats L2P · Average Accuracy [memory-free continual learning]
95.75 vs 90.34
Choice of PEFT Technique in Continual Learning: Prompt Tuning is Not All You Need
DualLoRA+ beats L2P · ACC [5-Split ImageNet-R]
79.88 vs 61.60
Replay-Free Continual Low-Rank Adaptation with Dynamic Memory
DualLoRA+ beats L2P · FT [5-Split ImageNet-R]
1.10 vs 5.36
Replay-Free Continual Low-Rank Adaptation with Dynamic Memory
DualLoRA+ beats L2P · ACC [10-Split ImageNet-R]
81.17 vs 59.21
Replay-Free Continual Low-Rank Adaptation with Dynamic Memory
DualLoRA+ beats L2P · FT [10-Split ImageNet-R]
2.04 vs 7.59
Replay-Free Continual Low-Rank Adaptation with Dynamic Memory
DualLoRA+ beats L2P · ACC [20-Split ImageNet-R]
74.73 vs 56.36
Replay-Free Continual Low-Rank Adaptation with Dynamic Memory

Newer alternatives

Recent methods in the same sub-problem, not yet superseded in the knowledge base.