{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:58Z","timestamp":1786120858542,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818448","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"7588-7599","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MixLM: High-Throughput and Effective LLM Ranking via Text-Embedding Mix-Interaction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3593-8758","authenticated-orcid":false,"given":"Guoyao","family":"Li","sequence":"first","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2325-9042","authenticated-orcid":false,"given":"Ran","family":"He","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7281-2062","authenticated-orcid":false,"given":"Shusen","family":"Jing","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3482-0421","authenticated-orcid":false,"given":"Kayhan","family":"Behdin","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1822-4229","authenticated-orcid":false,"given":"Yubo","family":"Wang","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3698-8759","authenticated-orcid":false,"given":"Sundara Raman","family":"Ramachandran","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8611-9919","authenticated-orcid":false,"given":"Chanh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3188-5390","authenticated-orcid":false,"given":"Jian","family":"Sheng","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1184-2477","authenticated-orcid":false,"given":"Xiaojing","family":"Ma","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6445-2829","authenticated-orcid":false,"given":"Chuanrui","family":"Zhu","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8744-2164","authenticated-orcid":false,"given":"Sriram","family":"Vasudevan","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4140-0958","authenticated-orcid":false,"given":"Muchen","family":"Wu","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6035-5984","authenticated-orcid":false,"given":"Sayan","family":"Ghosh","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4307-0725","authenticated-orcid":false,"given":"Qingquan","family":"Song","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1402-0241","authenticated-orcid":false,"given":"Xiaoqing","family":"Wang","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5703-5560","authenticated-orcid":false,"given":"Zhipeng","family":"Wang","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6223-4160","authenticated-orcid":false,"given":"Qing","family":"Lan","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8265-5771","authenticated-orcid":false,"given":"Yanning","family":"Chen","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5751-9389","authenticated-orcid":false,"given":"Jingwei","family":"Wu","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4560-6361","authenticated-orcid":false,"given":"Luke","family":"Simon","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6510-1222","authenticated-orcid":false,"given":"Wenjing","family":"Zhang","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0078-1533","authenticated-orcid":false,"given":"Qi","family":"Guo","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8171-7656","authenticated-orcid":false,"given":"Fedor","family":"Borisyuk","sequence":"additional","affiliation":[{"name":"LinkedIn, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems V35 (2022) 23716-23736.","DOI":"10.52202\/068431-1723"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608857"},{"key":"e_1_3_2_1_3_1","unstructured":"Kayhan Behdin Qingquan Song Sriram Vasudevan Jian Sheng Xiaojing Ma Z Zhou Chuanrui Zhu Guoyao Li Chanh Nguyen Sayan Ghosh et al. 2025. Scaling Up Efficient Small Language Models Serving and Deployment for Semantic Job Search. arXiv preprint arXiv:2510.22101 (2025)."},{"key":"e_1_3_2_1_4_1","volume-title":"Hllm: Enhancing sequential recommendations via hierarchical large language models for item and user modeling. arXiv preprint arXiv:2409.12740","author":"Chen Junyi","year":"2024","unstructured":"Junyi Chen, Lu Chi, Bingyue Peng, and Zehuan Yuan. 2024. Hllm: Enhancing sequential recommendations via hierarchical large language models for item and user modeling. arXiv preprint arXiv:2409.12740 (2024)."},{"key":"e_1_3_2_1_5_1","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171-4186."},{"key":"e_1_3_2_1_6_1","volume-title":"LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBay. arXiv preprint arXiv:2508.03628","author":"Dey Soumik","year":"2025","unstructured":"Soumik Dey, Benjamin Braun, Naveen Ravipati, Hansi Wu, and Binbin Li. 2025. LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBay. arXiv preprint arXiv:2508.03628 (2025)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3409256.3409838"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"key":"e_1_3_2_1_9_1","volume-title":"NIPS Deep Learning and Representation Learning Workshop.","author":"Hinton Geoffrey","year":"2014","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2014. Distilling the Knowledge in a Neural Network. In NIPS Deep Learning and Representation Learning Workshop."},{"key":"e_1_3_2_1_10_1","volume-title":"Improving efficient neural ranking models with cross-architecture knowledge distillation. arXiv preprint arXiv:2010.02666","author":"Hofst\u00e4tter Sebastian","year":"2020","unstructured":"Sebastian Hofst\u00e4tter, Sophia Althammer, Michael Schr\u00f6der, Mete Sertkan, and Allan Hanbury. 2020. Improving efficient neural ranking models with cross-architecture knowledge distillation. arXiv preprint arXiv:2010.02666 (2020)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56060-6_24"},{"key":"e_1_3_2_1_12_1","volume-title":"Liger kernel: Efficient triton kernels for llm training. arXiv preprint arXiv:2410.10989","author":"Hsu Pin-Lun","year":"2024","unstructured":"Pin-Lun Hsu, Yun Dai, Vignesh Kothapalli, Qingquan Song, Shao Tang, Siyu Zhu, Steven Shimizu, Shivam Sahni, Haowen Ning, and Yanning Chen. 2024. Liger kernel: Efficient triton kernels for llm training. arXiv preprint arXiv:2410.10989 (2024)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403305"},{"key":"e_1_3_2_1_14_1","volume-title":"Barun Patra, et al.","author":"Huang Shaohan","year":"2023","unstructured":"Shaohan Huang, Li Dong, Wenhui Wang, Yaru Hao, Saksham Singhal, Shuming Ma, Tengchao Lv, Lei Cui, Owais Khan Mohammed, Barun Patra, et al., 2023. Language is not all you need: Aligning perception with language models. Advances in Neural Information Processing Systems, V36 (2023), 72096-72109."},{"key":"e_1_3_2_1_15_1","volume-title":"Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick SH Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. In EMNLP (1). 6769-6781."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_17_1","volume-title":"Jianqiang Shen, Raghavan Muthuregunathan, Abhinav Gupta, Mathew Teoh, Andrew Kirk, Thomas Kwan, Jingwei Wu, and Wenjing Zhang.","author":"Le Benjamin","year":"2026","unstructured":"Benjamin Le, Xueying Lu, Nick Stern, Wenqiong Liu, Igor Lapchuk, Xiang Li, Baofen Zheng, Kevin Rosenberg, Jiewen Huang, Zhe Zhang, Abraham Cabangbang, Satej Milind Wagle, Jianqiang Shen, Raghavan Muthuregunathan, Abhinav Gupta, Mathew Teoh, Andrew Kirk, Thomas Kwan, Jingwei Wu, and Wenjing Zhang. 2026. SAGE: Scalable AI Governance & Evaluation. arXiv preprint arXiv:2602.07840 (2026)."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML). PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In Proceedings of the 40th International Conference on Machine Learning (ICML). PMLR, 19730-19742."},{"key":"e_1_3_2_1_19_1","volume-title":"SyNeg: LLM-Driven Synthetic Hard-Negatives for Dense Retrieval. CoRR","author":"Li Xiaopeng","year":"2024","unstructured":"Xiaopeng Li, Xiangyang Li, Hao Zhang, Zhaocheng Du, Pengyue Jia, Yichao Wang, Xiangyu Zhao, Huifeng Guo, and Ruiming Tang. 2024. SyNeg: LLM-Driven Synthetic Hard-Negatives for Dense Retrieval. CoRR (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645467"},{"key":"e_1_3_2_1_21_1","volume-title":"Anshumali Shrivastava, and Vijai Mohan.","author":"Lin Xiaoqiang","year":"2025","unstructured":"Xiaoqiang Lin, Aritra Ghosh, Bryan Kian Hsiang Low, Anshumali Shrivastava, and Vijai Mohan. 2025. REFRAG: Rethinking RAG based Decoding. arXiv preprint arXiv:2509.01092 (2025)."},{"key":"e_1_3_2_1_22_1","volume-title":"V36","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, V36 (2023), 34892-34916."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"e_1_3_2_1_24_1","volume-title":"V43, 4","author":"Meng Chuan","year":"2025","unstructured":"Chuan Meng, Negar Arabzadeh, Arian Askari, Mohammad Aliannejadi, and Maarten de Rijke. 2025. Query performance prediction using relevance judgments generated by large language models. ACM Transactions on Information Systems, V43, 4 (2025), 1-35."},{"key":"e_1_3_2_1_25_1","volume-title":"Introducing the Perplexity Search API. https:\/\/www.perplexity.ai\/hub\/blog\/introducing-the-perplexity-search-api. Blog post","author":"Perplexity AI.","unstructured":"Perplexity AI. 2025. Introducing the Perplexity Search API. https:\/\/www.perplexity.ai\/hub\/blog\/introducing-the-perplexity-search-api. Blog post; discusses cost of LLM-based reranking.."},{"key":"e_1_3_2_1_26_1","volume-title":"Rankvicuna: Zero-shot listwise document reranking with open-source large language models. arXiv preprint arXiv:2309.15088","author":"Pradeep Ronak","year":"2023","unstructured":"Ronak Pradeep, Sahel Sharifymoghaddam, and Jimmy Lin. 2023. Rankvicuna: Zero-shot listwise document reranking with open-source large language models. arXiv preprint arXiv:2309.15088 (2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.97"},{"key":"e_1_3_2_1_28_1","volume-title":"Honglei Zhuang, He Zhang, Aijun Bai, Kai Hui, Le Yan, and Xuanhui Wang.","author":"Qin Zhen","year":"2023","unstructured":"Zhen Qin, Rolf Jagerman, Rama Kumar Pasumarthi, Honglei Zhuang, He Zhang, Aijun Bai, Kai Hui, Le Yan, and Xuanhui Wang. 2023. Rd-suite: A benchmark for ranking distillation. Advances in Neural Information Processing Systems, V36 (2023), 35748-35760."},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 2368-2376","author":"Reddi Sashank","year":"2021","unstructured":"Sashank Reddi, Rama Kumar Pasumarthi, Aditya Menon, Ankit Singh Rawat, Felix Yu, Seungyeon Kim, Andreas Veit, and Sanjiv Kumar. 2021. Rankdistil: Knowledge distillation for ranking. In International Conference on Artificial Intelligence and Statistics. PMLR, 2368-2376."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.249"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"e_1_3_2_1_32_1","first-page":"449","volume-title":"Knowledge Distillation for Enhancing Walmart E-commerce Search Relevance Using Large Language Models. In Companion Proceedings of the ACM on Web Conference","author":"Shang Hongwei","year":"2025","unstructured":"Hongwei Shang, Nguyen Vo, Nitin Yadav, Tian Zhang, Ajit Puthenputhussery, Xunfan Cai, Shuyi Chen, Prijith Chandran, and Changsung Kang. 2025. Knowledge Distillation for Enhancing Walmart E-commerce Search Relevance Using Large Language Models. In Companion Proceedings of the ACM on Web Conference 2025. 449-457."},{"key":"e_1_3_2_1_33_1","unstructured":"Sundara Raman Ramachandran. 2025. [Generative Score API] Multi-Item scoring with custom attention mask (Pull request #10979). https:\/\/github.com\/sgl-project\/sglang\/pull\/10979. Pull request #10979 in the SGLang project."},{"key":"e_1_3_2_1_34_1","volume-title":"Distilling task-specific knowledge from bert into simple neural networks. arXiv preprint arXiv:1903.12136","author":"Tang Raphael","year":"2019","unstructured":"Raphael Tang, Yao Lu, Linqing Liu, Lili Mou, Olga Vechtomova, and Jimmy Lin. 2019. Distilling task-specific knowledge from bert into simple neural networks. arXiv preprint arXiv:1903.12136 (2019)."},{"key":"e_1_3_2_1_35_1","volume-title":"Onur Gungor, Yu Xu, Krishna Kamath, Rakesh Chalasani, Kurchi Subhra Hazra, and Jinfeng Rao.","author":"Wang Han","year":"2024","unstructured":"Han Wang, Mukuntha Narayanan Sundararaman, Onur Gungor, Yu Xu, Krishna Kamath, Rakesh Chalasani, Kurchi Subhra Hazra, and Jinfeng Rao. 2024. Improving Pinterest Search Relevance Using Large Language Models. arXiv preprint arXiv:2410.17152 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, V35 (2022), 24824-24837."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-024-01291-2"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645494"},{"key":"e_1_3_2_1_39_1","volume-title":"From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance. arXiv preprint arXiv:2510.11056","author":"Xia Runze","year":"2025","unstructured":"Runze Xia, Yupeng Ji, Yuxi Zhou, Haodong Liu, Teng Zhang, and Piji Li. 2025. From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance. arXiv preprint arXiv:2510.11056 (2025)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737193"},{"key":"e_1_3_2_1_41_1","volume-title":"V43, 5","author":"Zhang Junjie","year":"2025","unstructured":"Junjie Zhang, Ruobing Xie, Yupeng Hou, Xin Zhao, Leyu Lin, and Ji-Rong Wen. 2025b. Recommendation as instruction following: A large language model empowered recommendation approach. ACM Transactions on Information Systems, V43, 5 (2025), 1-37."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Longhui Zhang Yanzhao Zhang Dingkun Long Pengjun Xie Meishan Zhang and Min Zhang. 2024. A Two-Stage Adaptation of Large Language Models for Text Ranking. In ACL (Findings).","DOI":"10.18653\/v1\/2024.findings-acl.706"},{"key":"e_1_3_2_1_43_1","volume-title":"Collm: Integrating collaborative embeddings into large language models for recommendation","author":"Zhang Yang","year":"2025","unstructured":"Yang Zhang, Fuli Feng, Jizhi Zhang, Keqin Bao, Qifan Wang, and Xiangnan He. 2025a. Collm: Integrating collaborative embeddings into large language models for recommendation. IEEE Transactions on Knowledge and Data Engineering (2025)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611569"},{"key":"e_1_3_2_1_45_1","volume-title":"Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark Barrett, and Ying Sheng.","author":"Zheng Lianmin","year":"2024","unstructured":"Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun, Jeff Huang, Cody Hao Yu, Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark Barrett, and Ying Sheng. 2024. SGLang: Efficient Execution of Structured Language Model Programs. Advances in Neural Information Processing Systems, V37 (2024), 62557-62583."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657813"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:28:30Z","timestamp":1786066110000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818448"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":46,"alternative-id":["10.1145\/3770855.3818448","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818448","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}