ZoomR reduces KV cache memory by more than 4x during long-output reasoning by using summary keys for coarse indexing and dynamic fine-grained retrieval.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval
ZoomR reduces KV cache memory by more than 4x during long-output reasoning by using summary keys for coarse indexing and dynamic fine-grained retrieval.