Parameter-efficient fine-tuning (LoRA family)
MoLoRA
Superseded baseline#76 of 1,113 most-superseded
Superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 2 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites MoLoRA as a baseline.
However, MoLoRA introduces additional challenges, such as increased training latency and parameter redundancy.
Beaten on benchmarks
Head-to-head results where a newer method reports beating MoLoRA. Values are copied from the source paper's tables — verify against the cited paper.
VLA-GSE beats MoLoRA
81.2 vs 76.2
Total success rate · [Comparable parameter budget (~2.5%)]
VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized ExpertsMALoRA beats MoLoRA
56.3 vs 55.3
AVG · [inter-domain multi-task]
MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning
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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.