NestedKV is a new training-free KV cache compression technique using nested memory anchors and multi-time-scale anomaly scoring that outperforms prior methods like KeyDiff on long-context benchmarks when the retained cache fraction is small.
FlowKV: Enhancing multi-turn conversational coherence in LLMs via isolated key-value cache management
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
LLM inference should be reframed and evaluated as energy-to-token production with a Token Production Function that accounts for power, cooling, and efficiency ceilings.
citing papers explorer
-
NestedKV: Nested Memory Routing for Long-Context KV Cache Compression
NestedKV is a new training-free KV cache compression technique using nested memory anchors and multi-time-scale anomaly scoring that outperforms prior methods like KeyDiff on long-context benchmarks when the retained cache fraction is small.
-
Position: LLM Inference Should Be Evaluated as Energy-to-Token Production
LLM inference should be reframed and evaluated as energy-to-token production with a Token Production Function that accounts for power, cooling, and efficiency ceilings.