Presentation
KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning
DescriptionWe propose KEEP, a KV-cache-centric memory management system for efficient embodied planning. To reduce cache invalidation caused by memory updates, we propose Static-Dynamic Memory Construction, which groups memory by update frequency and manages memory at different granularities. To reduce the impact of cross-attention ignorance between different groups, we propose Multi-hop Memory Re-computation, which dynamically identifies and recovers critical memory interactions through iterative memory importance propagation. We also propose Layer-balanced Memory Loading, a scheduling strategy that eliminates unbalanced KV loading and computation overhead between different layers caused by KV recomputation.
Event Type
Research Manuscript
TimeWednesday, July 292:08pm - 2:21pm PDT
LocationMtg Room 203C