RAG-Diff Uses Retrieval to Steer Frozen Policies

Nekovowo · x · 2026-07-13

RAG-Diff proposes a novel framework that uses retrieval at test time to steer frozen policies, aiming to help pre-trained policies better adapt to individual preferences in tasks like caregiving.

The author notes that while pre-trained policies can handle some caregiving tasks, real-world care requires "person-specific adjustments":

Related event: RAG-Diff Framework Adapts Robot Caregiving to Human Preferences(4 posts)→

Original post →

More from Research

Research channel →