# LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference

> Research article (Findings of the Association for Computational Linguistics: EMNLP 2024, 2024) · cited 11× · AI/ML

**Wikidata**: [openalex:W4404782265](https://www.wikidata.org/wiki/openalex:W4404782265)  
**Source**: https://4ort.xyz/entity/look-m-look-once-optimization-in-kv-cache-for-efficient-multimodal-long-context-inference