AI & softwareResearch findings
Primitive representations enable few-shot transfer in new tasks
Original published 2026.05.29 09:37 KSTAdded to Blackdeck 2026.11.22 20:38 KST
What has changed?
Models trained with primitive awareness achieve task transfer with only three demonstrations
Key points
- Models with primitive-aware training can perform new tasks with only three demonstrations
- Primitive-trained models reach 78% of fine-tuned performance with just three demonstrations, while flat-trained models require ten
- Ablation of primitive-decodable subspaces reduces transfer performance by 32 percentage points
Connect it to your work
Task transfer is possible with minimal demonstrations
What remains unproven
This research note is based on an abstract; check the original for test conditions and application scope.
Originals used for this note
Links open the original publisher in a new tab.