IntentKV prunes KV cache using cross-turn intent memory and attention scoring, achieving up to 77.8% reduction in worst-case peak tokens and 92.6% in KV reads at 8k budget with negligible accuracy drop on Qwen models.
arXiv preprint arXiv:2512.03324 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 4years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Spherical KV combines angle-domain attention using spherical key codes with rate-distortion retention to cut KV cache residency and HBM traffic while keeping a paged, fusion-friendly decode path.
A unified learnable KV eviction policy with cross-layer calibration reduces memory and matches or exceeds full-cache performance on long-context tasks by retaining useful tokens and limiting attention dilution.
Structural protection of boundary tokens in globally capped KV cache eviction recovers 69-90% of full-cache quality at 13% retention and dominates differences among scoring policies.
citing papers explorer
-
IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference
IntentKV prunes KV cache using cross-turn intent memory and attention scoring, achieving up to 77.8% reduction in worst-case peak tokens and 92.6% in KV reads at 8k budget with negligible accuracy drop on Qwen models.
-
SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference
Spherical KV combines angle-domain attention using spherical key codes with rate-distortion retention to cut KV cache residency and HBM traffic while keeping a paged, fusion-friendly decode path.
-
Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction
A unified learnable KV eviction policy with cross-layer calibration reduces memory and matches or exceeds full-cache performance on long-context tasks by retaining useful tokens and limiting attention dilution.
-
Protection Is (Nearly) All You Need: Structural Protection Dominates Scoring in Globally Capped KV Eviction
Structural protection of boundary tokens in globally capped KV cache eviction recovers 69-90% of full-cache quality at 13% retention and dominates differences among scoring policies.