LoRN Method Steers Initial Noise in Generative Robot Policies Without Weight Updates
A new arXiv paper introduces LoRN, a low-rank noise steering approach that improves pretrained generative robot policies by learning to select their initial noise without updating model weights.
Read the full story at arXiv cs.RO ↗
Timeline · 1 report
- 2026-11-19 05:00 · arXiv cs.RO
LoRN: Low-Rank Noise Steering for Generative Robot Policies