Tag
PorTAL is a novel architecture that decouples task fine-tuning from specific base model weights, enabling portable task adapters that can be transferred to new models with minimal retraining. It achieves ~98% of LoRA's accuracy gain on unseen models using only half the calibration data.
Introduces WIZARD, a weight-space meta-learning framework that generates task-specific LoRA parameters for frozen VLA policies from language instructions and demonstration videos, enabling efficient task adaptation without fine-tuning.