CNN (Parameter-efficient fine-tuning (LoRA family)): superseded — cited as a baseline and beaten by newer methods. 2 paper(s) critique it, 2 beat it on benchmarks — #51 of 1113 most-superseded. Sub-problem: cluster led by CNN. Newer alternatives in the same sub-problem include Structured Convolutional Projection + LoRA, LEGO, layer-selective multimodal large language models (MLLMs) with contrastive LoRA tuning and layer sensitivity analysis (LSA), AdaptPrompt.

Parameter-efficient fine-tuning (LoRA family)

CNN

Superseded baseline#51 of 1,113 most-superseded

Superseded — cited as a baseline and beaten by newer methods

2 papers critique it · 2 beat it on benchmarks

What papers say

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

CNNs often struggle to capture semantic dependencies in sequences of substantial length due to their limited capacity to extract local features based on filter size.

— LoRA-BERT: a Natural Language Processing Model for Robust and Accurate Prediction of long non-coding RNAs

“Convolutional Neural Networks (CNNs)~zhuang2020comprehensive were among the first approaches applied to vehicle aerodynamics~sae2026010600 but showed limited success due to their inherent requirement for constant-distance pixel or voxel grids, an unnatural representation for complex 3D geometries.”

— Adapting Automotive Aerodynamics Surrogates to New Vehicle Families via Transfer Learning

Beaten on benchmarks

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

HARLLM beats CNN
94.16 vs 92.62
F1-score · [CNN baseline]
Efficient and Adaptive Human Activity Recognition via LLM Backbones

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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.