{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:42Z","timestamp":1786120842706,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":52,"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"}],"funder":[{"name":"National Key R&amp;D Program of China","award":["2022ZD0160501"],"award-info":[{"award-number":["2022ZD0160501"]}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2024J011001"],"award-info":[{"award-number":["2024J011001"]}]},{"name":"the Public Technology Service Platform Project of Xiamen","award":["3502Z20231043"],"award-info":[{"award-number":["3502Z20231043"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818308","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:47Z","timestamp":1786036547000},"page":"8167-8178","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["m\n                    <sup>3<\/sup>\n                    BERT: A Modern, Multi-lingual, Matryoshka Bidirectional Encoder"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8238-8647","authenticated-orcid":false,"given":"Yaoxiang","family":"Wang","sequence":"first","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China and Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan, Ministry of Culture and Tourism, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8014-3150","authenticated-orcid":false,"given":"Simiao","family":"Zuo","sequence":"additional","affiliation":[{"name":"Microsoft, Bellevue, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0912-4744","authenticated-orcid":false,"given":"Qingguo","family":"Hu","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6095-4947","authenticated-orcid":false,"given":"Yucheng","family":"Ding","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9954-9674","authenticated-orcid":false,"given":"Yeyun","family":"Gong","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4779-9588","authenticated-orcid":false,"given":"Jian","family":"Jiao","sequence":"additional","affiliation":[{"name":"Microsoft, Bellevue, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5606-7122","authenticated-orcid":false,"given":"Jinsong","family":"Su","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China and Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan, Ministry of Culture and Tourism, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv:1611.09268 [cs.CL]","author":"Bajaj Payal","year":"2018","unstructured":"Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, and Tong Wang. 2018. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. arXiv:1611.09268 [cs.CL]"},{"key":"e_1_3_2_1_3_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Cai Mu","year":"2025","unstructured":"Mu Cai, Jianwei Yang, Jianfeng Gao, and Yong Jae Lee. 2025. Matryoshka multimodal models. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_4_1","volume-title":"Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss. arXiv preprint arXiv:2410.17243","author":"Cheng Zesen","year":"2024","unstructured":"Zesen Cheng, Hang Zhang, Kehan Li, Sicong Leng, Zhiqiang Hu, Fei Wu, Deli Zhao, Xin Li, and Lidong Bing. 2024. Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss. arXiv preprint arXiv:2410.17243 (2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691","author":"Dao Tri","year":"2023","unstructured":"Tri Dao. 2023. Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in neural information processing systems, V35","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in neural information processing systems, V35 (2022), 16344-16359."},{"key":"e_1_3_2_1_7_1","first-page":"10088","volume-title":"Levine (Eds.)","volume":"36","author":"Dettmers Tim","year":"2023","unstructured":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. QLoRA: Efficient Finetuning of Quantized LLMs. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. V36. Curran Associates, Inc., 10088-10115."},{"key":"e_1_3_2_1_8_1","volume-title":"Matformer: Nested transformer for elastic inference. Advances in Neural Information Processing Systems","author":"Devvrit Fnu","year":"2024","unstructured":"Fnu Devvrit, Sneha Kudugunta, Aditya Kusupati, Tim Dettmers, Kaifeng Chen, Inderjit Dhillon, Yulia Tsvetkov, Hanna Hajishirzi, Sham Kakade, Ali Farhadi, et al., 2024. Matformer: Nested transformer for elastic inference. Advances in Neural Information Processing Systems (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Machine Learning, ICML 2023 (Proceedings of Machine Learning Research","volume":"10337","author":"Frantar Elias","year":"2023","unstructured":"Elias Frantar and Dan Alistarh. 2023. SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot. In International Conference on Machine Learning, ICML 2023 (Proceedings of Machine Learning Research, Vol. V202). PMLR, 10323-10337."},{"key":"e_1_3_2_1_10_1","volume-title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers. In International Conference on Learning Representations.","author":"Frantar Elias","year":"2023","unstructured":"Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2023. GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_11_1","volume-title":"Tool Graph Retriever: Exploring Dependency Graph-based Tool Retrieval for Large Language Models. arXiv preprint arXiv:2508.05152","author":"Gao Linfeng","year":"2025","unstructured":"Linfeng Gao, Yaoxiang Wang, Minlong Peng, Jialong Tang, Yuzhe Shang, Mingming Sun, and Jinsong Su. 2025. Tool Graph Retriever: Exploring Dependency Graph-based Tool Retrieval for Large Language Models. arXiv preprint arXiv:2508.05152 (2025)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"e_1_3_2_1_13_1","volume-title":"Hamish Ivison, Ian Magnusson, Yizhong Wang, et al.","author":"Groeneveld Dirk","year":"2024","unstructured":"Dirk Groeneveld, Iz Beltagy, Pete Walsh, Akshita Bhagia, Rodney Kinney, Oyvind Tafjord, Ananya Harsh Jha, Hamish Ivison, Ian Magnusson, Yizhong Wang, et al., 2024. Olmo: Accelerating the science of language models. arXiv preprint arXiv:2402.00838 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"MiniLLM: Knowledge Distillation of Large Language Models. In International Conference on Learning Representations.","author":"Gu Yuxian","year":"2024","unstructured":"Yuxian Gu, Li Dong, Furu Wei, and Minlie Huang. 2024. MiniLLM: Knowledge Distillation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han, Huizi Mao, and William J Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)."},{"key":"e_1_3_2_1_16_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"e_1_3_2_1_18_1","volume-title":"Matryoshka query transformer for large vision-language models. Advances in Neural Information Processing Systems","author":"Hu Wenbo","year":"2024","unstructured":"Wenbo Hu, Zi-Yi Dou, Liunian Li, Amita Kamath, Nanyun Peng, and Kai-Wei Chang. 2024. Matryoshka query transformer for large vision-language models. Advances in Neural Information Processing Systems (2024)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2010.88"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT, Vol. V1. Minneapolis, Minnesota."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Aditya Kusupati Gantavya Bhatt Aniket Rege Matthew Wallingford Aditya Sinha Vivek Ramanujan William Howard-Snyder Kaifeng Chen Sham Kakade Prateek Jain et al. 2022. Matryoshka representation learning. Advances in Neural Information Processing Systems V35 (2022) 30233-30249.","DOI":"10.52202\/068431-2192"},{"key":"e_1_3_2_1_23_1","volume-title":"Natural Questions: A Benchmark for Question Answering Research. Transactions of the Association for Computational Linguistics, V7","author":"Kwiatkowski Tom","year":"2019","unstructured":"Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. Natural Questions: A Benchmark for Question Answering Research. Transactions of the Association for Computational Linguistics, V7 (2019)."},{"key":"e_1_3_2_1_24_1","volume-title":"Matryoshka Representation Learning for Recommendation. arXiv preprint arXiv:2406.07432","author":"Lai Riwei","year":"2024","unstructured":"Riwei Lai, Li Chen, Weixin Chen, and Rui Chen. 2024. Matryoshka Representation Learning for Recommendation. arXiv preprint arXiv:2406.07432 (2024)."},{"key":"e_1_3_2_1_25_1","volume-title":"Llave: Large language and vision embedding models with hardness-weighted contrastive learning. arXiv preprint arXiv:2503.04812","author":"Lan Zhibin","year":"2025","unstructured":"Zhibin Lan, Liqiang Niu, Fandong Meng, Jie Zhou, and Jinsong Su. 2025a. Llave: Large language and vision embedding models with hardness-weighted contrastive learning. arXiv preprint arXiv:2503.04812 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings. arXiv preprint arXiv:2511.00405","author":"Lan Zhibin","year":"2025","unstructured":"Zhibin Lan, Liqiang Niu, Fandong Meng, Jie Zhou, and Jinsong Su. 2025b. UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings. arXiv preprint arXiv:2511.00405 (2025)."},{"key":"e_1_3_2_1_27_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_28_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.178"},{"key":"e_1_3_2_1_30_1","volume-title":"Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation.","author":"Multi-Functionality Multi-Linguality","year":"2024","unstructured":"Multi-Linguality Multi-Functionality Multi-Granularity. 2024. M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation. (2024)."},{"key":"e_1_3_2_1_31_1","unstructured":"OrdalieTech. [n.d.]. Solon Embeddings Large 0.1. https:\/\/huggingface.co\/OrdalieTech\/Solon-embeddings-large-0.1."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3266377"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_34_1","first-page":"17456","volume-title":"Oh (Eds.)","volume":"35","author":"Schuster Tal","year":"2022","unstructured":"Tal Schuster, Adam Fisch, Jai Gupta, Mostafa Dehghani, Dara Bahri, Vinh Tran, Yi Tay, and Donald Metzler. 2022. Confident Adaptive Language Modeling. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. V35. Curran Associates, Inc., 17456-17472."},{"key":"e_1_3_2_1_35_1","volume-title":"Glu variants improve transformer. arXiv preprint arXiv:2002.05202","author":"Shazeer Noam","year":"2020","unstructured":"Noam Shazeer. 2020. Glu variants improve transformer. arXiv preprint arXiv:2002.05202 (2020)."},{"key":"e_1_3_2_1_36_1","volume-title":"Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset. arXiv preprint arXiv:2412.02595","author":"Su Dan","year":"2024","unstructured":"Dan Su, Kezhi Kong, Ying Lin, Joseph Jennings, Brandon Norick, Markus Kliegl, Mostofa Patwary, Mohammad Shoeybi, and Bryan Catanzaro. 2024. Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset. arXiv preprint arXiv:2412.02595 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"International Conference on Representation Learning, B. Kim, Y. Yue, S. Chaudhuri, K. Fragkiadaki, M. Khan, and Y. Sun (Eds.). 4942-4964","author":"Sun Mingjie","year":"2024","unstructured":"Mingjie Sun, Zhuang Liu, Anna Bair, and Zico Kolter. 2024. A Simple and Effective Pruning Approach for Large Language Models. In International Conference on Representation Learning, B. Kim, Y. Yue, S. Chaudhuri, K. Fragkiadaki, M. Khan, and Y. Sun (Eds.). 4942-4964."},{"key":"e_1_3_2_1_38_1","volume-title":"Juliette Love, et al., [n.d.]. Gemma: Open models based on gemini research and technology","author":"Team Gemma","year":"2024","unstructured":"Gemma Team, Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivi\u00e8re, Mihir Sanjay Kale, Juliette Love, et al., [n.d.]. Gemma: Open models based on gemini research and technology, 2024. URL https:\/\/arxiv.org\/abs\/2403.08295, V2 ([n.d.]), 10-19."},{"key":"e_1_3_2_1_39_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Ellen Voorhees Tasmeer Alam Steven Bedrick Dina Demner-Fushman William R Hersh Kyle Lo Kirk Roberts Ian Soboroff and Lucy Lu Wang. 2020. TREC-COVID: Constructing a Pandemic Information Retrieval Test Collection. arXiv:2005.04474","DOI":"10.1145\/3451964.3451965"},{"key":"e_1_3_2_1_41_1","volume-title":"Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533","author":"Wang Liang","year":"2022","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533 (2022)."},{"key":"e_1_3_2_1_42_1","volume-title":"Learning deep transformer models for machine translation. arXiv preprint arXiv:1906.01787","author":"Wang Qiang","year":"2019","unstructured":"Qiang Wang, Bei Li, Tong Xiao, Jingbo Zhu, Changliang Li, Derek F Wong, and Lidia S Chao. 2019. Learning deep transformer models for machine translation. arXiv preprint arXiv:1906.01787 (2019)."},{"key":"e_1_3_2_1_43_1","volume-title":"Training Matryoshka Mixture-of-Experts for Elastic Inference-Time Expert Utilization. arXiv preprint arXiv:2509.26520","author":"Wang Yaoxiang","year":"2025","unstructured":"Yaoxiang Wang, Qingguo Hu, Yucheng Ding, Ruizhe Wang, Yeyun Gong, Jian Jiao, Yelong Shen, Peng Cheng, and Jinsong Su. 2025. Training Matryoshka Mixture-of-Experts for Elastic Inference-Time Expert Utilization. arXiv preprint arXiv:2509.26520 (2025)."},{"key":"e_1_3_2_1_44_1","volume-title":"Train once, deploy anywhere: Matryoshka representation learning for multimodal recommendation. arXiv preprint arXiv:2409.16627","author":"Wang Yueqi","year":"2024","unstructured":"Yueqi Wang, Zhenrui Yue, Huimin Zeng, Dong Wang, and Julian McAuley. 2024. Train once, deploy anywhere: Matryoshka representation learning for multimodal recommendation. arXiv preprint arXiv:2409.16627 (2024)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Benjamin Warner Antoine Chaffin Benjamin Clavi\u00e9 Orion Weller Oskar Hallstr\u00f6m Said Taghadouini Alexis Gallagher Raja Biswas Faisal Ladhak Tom Aarsen Nathan Cooper Griffin Adams Jeremy Howard and Iacopo Poli. 2024. Smarter Better Faster Longer: A Modern Bidirectional Encoder for Fast Memory Efficient and Long Context Finetuning and Inference. arXiv:2412.13663","DOI":"10.18653\/v1\/2025.acl-long.127"},{"key":"e_1_3_2_1_46_1","volume-title":"Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le.","author":"Wei Jason","year":"2021","unstructured":"Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. 2021. Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)."},{"key":"e_1_3_2_1_47_1","volume-title":"Should you mask 15% in masked language modeling? arXiv preprint arXiv:2202.08005","author":"Wettig Alexander","year":"2022","unstructured":"Alexander Wettig, Tianyu Gao, Zexuan Zhong, and Danqi Chen. 2022. Should you mask 15% in masked language modeling? arXiv preprint arXiv:2202.08005 (2022)."},{"key":"e_1_3_2_1_48_1","volume-title":"When to use graphs in rag: A comprehensive analysis for graph retrieval-augmented generation. arXiv preprint arXiv:2506.05690","author":"Xiang Zhishang","year":"2025","unstructured":"Zhishang Xiang, Chuanjie Wu, Qinggang Zhang, Shengyuan Chen, Zijin Hong, Xiao Huang, and Jinsong Su. 2025. When to use graphs in rag: A comprehensive analysis for graph retrieval-augmented generation. arXiv preprint arXiv:2506.05690 (2025)."},{"key":"e_1_3_2_1_49_1","unstructured":"Liping Yi Han Yu Chao Ren Gang Wang Xiaoxiao Li et al. 2024. Federated model heterogeneous matryoshka representation learning. Advances in Neural Information Processing Systems (2024)."},{"key":"e_1_3_2_1_50_1","volume-title":"V323","author":"Yin Yongjing","year":"2023","unstructured":"Yongjing Yin, Jiali Zeng, Jinsong Su, Chulun Zhou, Fandong Meng, Jie Zhou, Degen Huang, and Jiebo Luo. 2023. Multi-modal graph contrastive encoding for neural machine translation. Artificial Intelligence, V323 (2023), 103986."},{"key":"e_1_3_2_1_51_1","volume-title":"V32","author":"Zhang Biao","year":"2019","unstructured":"Biao Zhang and Rico Sennrich. 2019. Root mean square layer normalization. Advances in Neural Information Processing Systems, V32 (2019)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2751420"}],"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":"2026-08-07T01:24:06Z","timestamp":1786065846000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818308"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":52,"alternative-id":["10.1145\/3770855.3818308","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818308","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"}}]}}