Papers by Peiyuan Zong
ContrastKV: Robust KV Cache Eviction via Contrastive Signal Fusion for Multi-Query Generalization (2026.acl-long)
Copied to clipboard
| Challenge: | Existing query-agnostic approaches rely on a single proxy query, leading to fragile eviction decisions under high evict ratios. |
| Approach: | They propose a query-agnostic KV cache eviction algorithm that exploits complementary semantic and non-semantic signals. |
| Outcome: | Experiments show that the proposed algorithm outperforms state-of-the-art methods while retaining up to 92% accuracy with only 20% of the KV cache budget. |