Parameter-efficient fine-tuning (LoRA family)
Dita
Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy
Superseded baseline#270 of 1,113 most-superseded · first seen Mar 25, 2025
Superseded — cited as a baseline and beaten by newer methods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 beats Dita
98.4 vs 92.3
Average success rate · [LIBERO simulation evaluation]
VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts
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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.