Skip to main content
Search

# HeMeR

1 related articles

Subscribe to updates
  1. arXiv

    Embodied agents stop rebuilding the whole KV cache on every memory update: HeMeR cuts real robot-arm inference from 2.94 to 1.87 seconds per step

    At every step an embodied agent's declarative, procedural and working memory contents change, yet most contents persist between consecutive decisions; separate memory interfaces previously forced each updated memory context to be treated as a new input, so the full KV cache was recomputed. HeMeR anchors memory contents as typed chunks with KV ranges, recomputes only ranges affected by content updates and adapter switches, and applies RoPE remapping to chunks that merely shift position. On a real UR7e tabletop deployment it reached an 83.20% goal-conditioned success rate at 1.87 seconds per step across two long-horizon tasks, versus 64.28% and 2.94 seconds for MemRL.

You’re all caught up