Method Drift›Parameter-efficient fine-tuning (LoRA family)
Superseded baseline#550 of 1,113 most-superseded
domain-specific fine-tuning
Parameter-efficient fine-tuning (LoRA family)
superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 0 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites domain-specific fine-tuning as a baseline.
“Existing solutions often rely on domain-specific fine-tuning, explicit alignment objectives, or invariant representation learning. While effective in controlled scenarios, these approaches frequently introduce additional training complexity and remain sensitive to the availability of labeled data in the target domain.”
— Efficient and Adaptive Human Activity Recognition via LLM Backbones
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.
- Structured Convolutional Projection + LoRAEfficient and Adaptive Human Activity Recognition via LLM BackbonesMay 12, 2026
- May 6, 2026
- layer-selective multimodal large language models (MLLMs) with contrastive LoRA tuning and layer sensitivity analysis (LSA)Fine-Grained Human Pose Editing Assessment via Layer-Selective MLLMsJan 15, 2026
- Dec 19, 2025