Seer: Efficient KV Cache Management for LLM Acceleration via Mitigating Semantic Search Inefficiency

@article{yiwei2026,
  title = {Seer: Efficient KV Cache Management for LLM Acceleration via Mitigating Semantic Search Inefficiency},
  author = {Hu, Yiwei and Liu, Fangxin and Liang, Yue and Wang, Xuan and Li, Cheng and Li, Gezi and Jiang, Li and Guan, Haibing},
  journal = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
  year = {2026},
  month = {Jan},
}

Hu, Yiwei et al. (2026). Seer: Efficient KV Cache Management for LLM Acceleration via Mitigating Semantic Search Inefficiency. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing.

Hu, Yiwei, et al.. "Seer: Efficient KV Cache Management for LLM Acceleration via Mitigating Semantic Search Inefficiency." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026.

Hu, Yiwei, et al.. "Seer: Efficient KV Cache Management for LLM Acceleration via Mitigating Semantic Search Inefficiency." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (2026).

Hu, Yiwei et al., 2026. Seer: Efficient KV Cache Management for LLM Acceleration via Mitigating Semantic Search Inefficiency. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing.

TY  - JOUR
TI  - Seer: Efficient KV Cache Management for LLM Acceleration via Mitigating Semantic Search Inefficiency
AU  - Hu, Yiwei
AU  - Liu, Fangxin
AU  - Liang, Yue
AU  - Wang, Xuan
AU  - Li, Cheng
AU  - Li, Gezi
AU  - Jiang, Li
AU  - Guan, Haibing
PY  - 2026
JO  - Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
ER  -