Method Drift›Parameter-efficient fine-tuning (LoRA family)
Superseded baseline#270 of 1,113 most-superseded
Dita
Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action PolicyParameter-efficient fine-tuning (LoRA family) · first seen Mar 25, 2025
superseded — cited as a baseline and beaten by newer methods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 Dita. Values are copied from the source paper's tables — verify against the cited paper.
- VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts
VLA-GSE beats Dita · Average success rate [LIBERO simulation evaluation]
98.4 vs 92.3
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.