{"paper":{"title":"QwenLong-CPRS: Towards $\\infty$-LLMs with Dynamic Context Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Yang, Bo Zhang, Chenliang Li, Fanqi Wan, Fei Huang, Gang Fu, Jingren Zhou, Ji Zhang, Ming Yan, Shaopeng Lai, Shengyi Liao, Weizhou Shen, Yingcheng Shi, Yuning Wu, Zhansheng Li","submitted_at":"2025-05-23T16:47:00Z","abstract_excerpt":"This technical report presents QwenLong-CPRS, a context compression framework designed for explicit long-context optimization, addressing prohibitive computation overhead during the prefill stage and the \"lost in the middle\" performance degradation of large language models (LLMs) during long sequence processing. Implemented through a novel dynamic context optimization mechanism, QwenLong-CPRS enables multi-granularity context compression guided by natural language instructions, achieving both efficiency gains and improved performance.\n  Evolved from the Qwen architecture series, QwenLong-CPRS "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18092","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.18092/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}