{"paper":{"title":"Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bojian Hou, Chao Chen, Chunzhi Yang, Darren Liu, Ellie Wen, Han Xu, Huaqing Xiong, Huayu Li, Jade Nie, Jiaqi Xu, Jiasheng Zhang, Jiyan Yang, Junqing Zhou, Laming Chen, Mengyue Hang, Qiuling Suo, Santanu Kolay, Shuo Chang, Sudhanshu Chanpuriya, Wenlin Chen, Xiaolong Liu, Xiaorui Gan, Xiaoyi Liu, Yasmine Badr, Yi Yang, Yue Dong, Yuhang Yang, Yuxi Hu, Yuzhen Huang","submitted_at":"2026-02-10T17:37:55Z","abstract_excerpt":"Deriving predictable scaling laws that govern the relationship between model performance and computational investment is crucial for designing and allocating resources in massive-scale recommendation systems. While such laws are established for large language models, they remain challenging for recommendation systems, especially those processing both user history and context features. We identify poor scaling efficiency as the main barrier to predictable power-law scaling, stemming from inefficient modules with low Model FLOPs Utilization (MFU) and suboptimal resource allocation. We introduce "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.10016","kind":"arxiv","version":3},"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/2602.10016/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"}