{"labels":{"en":"CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference"},"descriptions":{"en":"scientific paper published in CEUR-WS Volume 4275"},"claims":{"P31":"Q13442814","P1433":"Q141603371","P1476":{"text":"CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference","language":"en"},"P407":"Q1860","P953":"https://ceur-ws.org/Vol-4275/paper13.pdf","P50":[],"P2093":[{"value":"Xiaolin Lin","qualifiers":{"P1545":"1"}},{"value":"Jingcun Wang","qualifiers":{"P1545":"2"}},{"value":"Olga Kondrateva","qualifiers":{"P1545":"3"}},{"value":"Yiyu Shi","qualifiers":{"P1545":"4"}},{"value":"Bing Li","qualifiers":{"P1545":"5"}},{"value":"Grace Li Zhang","qualifiers":{"P1545":"6"}}]}}