2026
Building a Robot Learning Pipeline with SO-101
Part II: adapting GR00T N1.7 to the SO-101 carrot-to-box dataset with a full-scope LoRA interface, evaluation, and deployment.
Tags
LoRA
2026
VLA Post-Training
Part I: a controlled comparison of LoRA, QLoRA, and DoRA for post-training GR00T N1.7 on LIBERO-10 Long.
2026
Parameter-Efficient Fine-Tuning
Part I: LoRA, QLoRA, and DoRA—three ways to adapt a large frozen model without fully fine-tuning it.