{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T01:08:25Z","timestamp":1789434505511,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","funder":[{"name":"National Key R&D Program of China","award":["2023YFB4503600"],"award-info":[{"award-number":["2023YFB4503600"]}]},{"name":"NSF of China","award":["62232009"],"award-info":[{"award-number":["62232009"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1145\/3722212.3725641","type":"proceedings-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T09:00:26Z","timestamp":1750150826000},"page":"837-843","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Data+AI: LLM4Data and Data4LLM"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1398-0621","authenticated-orcid":false,"given":"Guoliang","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9700-9751","authenticated-orcid":false,"given":"Jiayi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7627-6359","authenticated-orcid":false,"given":"Chenyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8229-3622","authenticated-orcid":false,"given":"Jiannan","family":"Wang","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Burnaby, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"https:\/\/google.github.io\/tensorstore\/","year":"2024","unstructured":"Tensorstore. https:\/\/google.github.io\/tensorstore\/, 2024."},{"key":"e_1_3_2_1_2_1","volume-title":"https:\/\/zarr.dev\/","year":"2024","unstructured":"Zarr. https:\/\/zarr.dev\/, 2024."},{"key":"e_1_3_2_1_3_1","unstructured":"A. E. abd Nick Comly and T. Johnsen. 5x faster time to first token with nvidia tensorrt-llm kv cache early reuse. https:\/\/developer.nvidia.com\/blog\/5x-faster-time-to-first-token-with-nvidia-tensorrt-llm-kv-cache-early-reuse\/ 2024."},{"key":"e_1_3_2_1_4_1","first-page":"117","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Agrawal A.","year":"2024","unstructured":"A. Agrawal, N. Kedia, A. Panwar, J. Mohan, N. Kwatra, B. Gulavani, A. Tumanov, and R. Ramjee. Taming Throughput-Latency tradeoff in LLM inference with Sarathi-Serve. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24), pages 117--134, Santa Clara, CA, July 2024. USENIX Association."},{"key":"e_1_3_2_1_5_1","volume-title":"The design of an llm-powered unstructured analytics system. arXiv:2409.00847","author":"Anderson E.","year":"2024","unstructured":"E. Anderson, J. Fritz, A. Lee, and et al. The design of an llm-powered unstructured analytics system. arXiv:2409.00847, 2024."},{"key":"e_1_3_2_1_6_1","first-page":"2023","article-title":"Extremely efficient collective communication for large model training","author":"Anonymous","year":"2023","unstructured":"Anonymous. ZeRO: Extremely efficient collective communication for large model training. In Machine Learning for Systems 2023, 2023.","journal-title":"Machine Learning for Systems"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.14778\/3626292.3626294"},{"key":"e_1_3_2_1_8_1","volume-title":"ICLR 2024","author":"Asai A.","year":"2024","unstructured":"A. Asai, Z. Wu, Y. Wang, A. Sil, and H. Hajishirzi. Self-rag: Learning to retrieve, generate, and critique through self-reflection. ICLR 2024, 2024."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3709705"},{"key":"e_1_3_2_1_10_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Brown T. B.","year":"2020","unstructured":"T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, S. Agarwal, A. Herbert-Voss, G. Krueger, T. Henighan, R. Child, A. Ramesh, D. M. Ziegler, J. Wu, C. Winter, C. Hesse, M. Chen, E. Sigler, M. Litwin, S. Gray, B. Chess, J. Clark, C. Berner, S. McCandlish, A. Radford, I. Sutskever, and D. Amodei. Language models are few-shot learners. In H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6--12, 2020, virtual, 2020."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589302"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599326"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626246.3653385"},{"key":"e_1_3_2_1_14_1","volume-title":"Towards effective and efficient continual pre-training of large language models. CoRR, abs\/2407.18743","author":"Chen J.","year":"2024","unstructured":"J. Chen, Z. Chen, J. Wang, K. Zhou, Y. Zhu, J. Jiang, Y. Min, W. X. Zhao, Z. Dou, J. Mao, Y. Lin, R. Song, J. Xu, X. Chen, R. Yan, Z. Wei, D. Hu, W. Huang, and J. Wen. Towards effective and efficient continual pre-training of large language models. CoRR, abs\/2407.18743, 2024."},{"key":"e_1_3_2_1_15_1","volume-title":"13th Conference on Innovative Data Systems Research, CIDR 2023","author":"Chen Z.","year":"2023","unstructured":"Z. Chen, Z. Gu, L. Cao, J. Fan, S. Madden, and N. Tang. Symphony: Towards natural language query answering over multi-modal data lakes. In 13th Conference on Innovative Data Systems Research, CIDR 2023, Amsterdam, The Netherlands, January 8--11, 2023. www.cidrdb.org, 2023."},{"key":"e_1_3_2_1_16_1","series-title":"Proceedings of Machine Learning Research","first-page":"5547","volume-title":"International Conference on Machine Learning, ICML","author":"Du N.","year":"2022","unstructured":"N. Du, Y. Huang, A. M. Dai, S. Tong, D. Lepikhin, Y. Xu, M. Krikun, Y. Zhou, A. W. Yu, O. Firat, B. Zoph, L. Fedus, M. P. Bosma, Z. Zhou, T. Wang, Y. E. Wang, K. Webster, M. Pellat, K. Robinson, K. S. Meier-Hellstern, T. Duke, L. Dixon, K. Zhang, Q. V. Le, Y. Wu, Z. Chen, and C. Cui. Glam: Efficient scaling of language models with mixture-of-experts. In K. Chaudhuri, S. Jegelka, L. Song, C. Szepesv\u00e1ri, G. Niu, and S. Sabato, editors, International Conference on Machine Learning, ICML 2022, 17--23 July 2022, Baltimore, Maryland, USA, volume 162 of Proceedings of Machine Learning Research, pages 5547--5569. PMLR, 2022."},{"key":"e_1_3_2_1_17_1","first-page":"929","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Eisenman A.","year":"2022","unstructured":"A. Eisenman, K. K. Matam, S. Ingram, D. Mudigere, R. Krishnamoorthi, K. Nair, M. Smelyanskiy, and M. Annavaram. Check-N-Run: a checkpointing system for training deep learning recommendation models. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22), pages 929--943, Renton, WA, Apr. 2022. USENIX Association."},{"key":"e_1_3_2_1_18_1","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","author":"Fan S.","year":"2024","unstructured":"S. Fan, M. Pagliardini, and M. Jaggi. DOGE: domain reweighting with generalization estimation. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21--27, 2024. OpenReview.net, 2024."},{"key":"e_1_3_2_1_19_1","volume-title":"Cost-efficient large language model serving for multi-turn conversations with cachedattention","author":"Gao B.","year":"2024","unstructured":"B. Gao, Z. He, P. Sharma, Q. Kang, D. Jevdjic, J. Deng, X. Yang, Z. Yu, and P. Zuo. Cost-efficient large language model serving for multi-turn conversations with cachedattention, 2024."},{"key":"e_1_3_2_1_20_1","volume-title":"The pile: An 800gb dataset of diverse text for language modeling. CoRR, abs\/2101.00027","author":"Gao L.","year":"2021","unstructured":"L. Gao, S. Biderman, S. Black, L. Golding, T. Hoppe, C. Foster, J. Phang, H. He, A. Thite, N. Nabeshima, S. Presser, and C. Leahy. The pile: An 800gb dataset of diverse text for language modeling. CoRR, abs\/2101.00027, 2021."},{"key":"e_1_3_2_1_21_1","volume-title":"Retrieval-augmented generation for large language models: A survey. CoRR, abs\/2312.10997","author":"Gao Y.","year":"2023","unstructured":"Y. Gao, Y. Xiong, X. Gao, K. Jia, and et al. Retrieval-augmented generation for large language models: A survey. CoRR, abs\/2312.10997, 2023."},{"key":"e_1_3_2_1_22_1","first-page":"325","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Gim I.","year":"2024","unstructured":"I. Gim, G. Chen, S.-s. Lee, N. Sarda, A. Khandelwal, and L. Zhong. Prompt cache: Modular attention reuse for low-latency inference. In P. Gibbons, G. Pekhimenko, and C. D. Sa, editors, Proceedings of Machine Learning and Systems, volume 6, pages 325--338, 2024."},{"key":"e_1_3_2_1_23_1","volume-title":"Scaling laws and interpretability of learning from repeated data. CoRR, abs\/2205.10487","author":"Hernandez D.","year":"2022","unstructured":"D. Hernandez, T. B. Brown, T. Conerly, N. DasSarma, D. Drain, S. E. Showk, N. Elhage, Z. Hatfield-Dodds, T. Henighan, T. Hume, S. Johnston, B. Mann, C. Olah, C. Olsson, D. Amodei, N. Joseph, J. Kaplan, and S. McCandlish. Scaling laws and interpretability of learning from repeated data. CoRR, abs\/2205.10487, 2022."},{"key":"e_1_3_2_1_24_1","volume-title":"NeurIPS 2022","author":"Hoffmann J.","year":"2022","unstructured":"J. Hoffmann, S. Borgeaud, A. Mensch, E. Buchatskaya, T. Cai, E. Rutherford, D. de Las Casas, and et al. An empirical analysis of compute-optimal large language model training. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh, editors, NeurIPS 2022, 2022."},{"key":"e_1_3_2_1_25_1","volume-title":"Inference without interference: Disaggregate llm inference for mixed downstream workloads","author":"Hu C.","year":"2024","unstructured":"C. Hu, H. Huang, L. Xu, X. Chen, J. Xu, S. Chen, H. Feng, C. Wang, S. Wang, Y. Bao, N. Sun, and Y. Shan. Inference without interference: Disaggregate llm inference for mixed downstream workloads, 2024."},{"key":"e_1_3_2_1_26_1","volume-title":"Curran Associates Inc.","author":"Huang Y.","year":"2019","unstructured":"Y. Huang, Y. Cheng, A. Bapna, O. Firat, M. X. Chen, D. Chen, H. Lee, J. Ngiam, Q. V. Le, Y. Wu, and Z. Chen. GPipe: efficient training of giant neural networks using pipeline parallelism. Curran Associates Inc., Red Hook, NY, USA, 2019."},{"key":"e_1_3_2_1_27_1","first-page":"745","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Jiang Z.","year":"2024","unstructured":"Z. Jiang, H. Lin, Y. Zhong, Q. Huang, Y. Chen, Z. Zhang, Y. Peng, X. Li, C. Xie, S. Nong, Y. Jia, S. He, H. Chen, Z. Bai, Q. Hou, S. Yan, D. Zhou, Y. Sheng, Z. Jiang, H. Xu, H. Wei, Z. Zhang, P. Nie, L. Zou, S. Zhao, L. Xiang, Z. Liu, Z. Li, X. Jia, J. Ye, X. Jin, and X. Liu. MegaScale: Scaling large language model training to more than 10,000 GPUs. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24), pages 745--760, Santa Clara, CA, Apr. 2024. USENIX Association."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_29_1","first-page":"8424","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022","author":"Lee K.","year":"2022","unstructured":"K. Lee, D. Ippolito, A. Nystrom, C. Zhang, D. Eck, C. Callison-Burch, and N. Carlini. Deduplicating training data makes language models better. In S. Muresan, P. Nakov, and A. Villavicencio, editors, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22--27, 2022, pages 8424--8445. Association for Computational Linguistics, 2022."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539147"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685838"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605613"},{"key":"e_1_3_2_1_33_1","volume-title":"Universal checkpointing: Efficient and flexible checkpointing for large scale distributed training","author":"Lian X.","year":"2024","unstructured":"X. Lian, S. A. Jacobs, L. Kurilenko, M. Tanaka, S. Bekman, O. Ruwase, and M. Zhang. Universal checkpointing: Efficient and flexible checkpointing for large scale distributed training, 2024."},{"key":"e_1_3_2_1_34_1","volume-title":"Towards accurate and efficient document analytics with large language models. CoRR, abs\/2405.04674","author":"Lin Y.","year":"2024","unstructured":"Y. Lin, M. Hulsebos, R. Ma, S. Shankar, S. Zeighami, A. G. Parameswaran, and E. Wu. Towards accurate and efficient document analytics with large language models. CoRR, abs\/2405.04674, 2024."},{"key":"e_1_3_2_1_35_1","volume-title":"A declarative system for optimizing AI workloads. CoRR, abs\/2405.14696","author":"Liu C.","year":"2024","unstructured":"C. Liu, M. Russo, M. J. Cafarella, L. Cao, P. B. Chen, Z. Chen, M. J. Franklin, T. Kraska, S. Madden, and G. Vitagliano. A declarative system for optimizing AI workloads. CoRR, abs\/2405.14696, 2024."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685916"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3625549.3658685"},{"key":"e_1_3_2_1_38_1","first-page":"203","volume-title":"19th USENIX Conference on File and Storage Technologies (FAST 21)","author":"Mohan J.","year":"2021","unstructured":"J. Mohan, A. Phanishayee, and V. Chidambaram. CheckFreq: Frequent, Fine-Grained DNN checkpointing. In 19th USENIX Conference on File and Storage Technologies (FAST 21), pages 203--216. USENIX Association, Feb. 2021."},{"key":"e_1_3_2_1_39_1","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Muennighoff N.","year":"2023","unstructured":"N. Muennighoff, A. M. Rush, B. Barak, T. L. Scao, N. Tazi, A. Piktus, S. Pyysalo, T. Wolf, and C. A. Raffel. Scaling data-constrained language models. In A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, 2023."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_1_41_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Nijkamp E.","year":"2023","unstructured":"E. Nijkamp, B. Pang, H. Hayashi, L. Tu, H. Wang, Y. Zhou, S. Savarese, and C. Xiong. Codegen: An open large language model for code with multi-turn program synthesis. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1--5, 2023. OpenReview.net, 2023."},{"key":"e_1_3_2_1_42_1","volume-title":"https:\/\/github.com\/NVIDIA\/TensorRT-LLM","author":"NVIDIA.","year":"2024","unstructured":"NVIDIA. Tensorrt-llm. https:\/\/github.com\/NVIDIA\/TensorRT-LLM, 2024."},{"key":"e_1_3_2_1_43_1","volume-title":"LOTUS: enabling semantic queries with llms over tables of unstructured and structured data. CoRR, abs\/2407.11418","author":"Patel L.","year":"2024","unstructured":"L. Patel, S. Jha, C. Guestrin, and M. Zaharia. LOTUS: enabling semantic queries with llms over tables of unstructured and structured data. CoRR, abs\/2407.11418, 2024."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"e_1_3_2_1_45_1","volume-title":"Mooncake: A kvcache-centric disaggregated architecture for llm serving","author":"Qin R.","year":"2024","unstructured":"R. Qin, Z. Li, W. He, M. Zhang, Y. Wu, W. Zheng, and X. Xu. Mooncake: A kvcache-centric disaggregated architecture for llm serving, 2024."},{"key":"e_1_3_2_1_46_1","first-page":"140","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel C.","year":"2020","unstructured":"C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W. Li, and P. J. Liu. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21:140:1--140:67, 2020.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_48_1","volume-title":"https:\/\/github.com\/microsoft\/DeepSpeed","author":"Team D.","year":"2024","unstructured":"D. Team. Deepspeed. https:\/\/github.com\/microsoft\/DeepSpeed, 2024."},{"key":"e_1_3_2_1_49_1","volume-title":"https:\/\/huggingface.co\/docs\/safetensors\/index","author":"Team H. F.","year":"2024","unstructured":"H. F. Team. Safetensors. https:\/\/huggingface.co\/docs\/safetensors\/index, 2024."},{"key":"e_1_3_2_1_50_1","volume-title":"https:\/\/docs.nvidia.com\/megatron-core\/developer-guide\/latest\/api-guide\/dist_checkpointing.html","author":"Team N. M.","year":"2024","unstructured":"N. M. Team. dist_checkpointing package. https:\/\/docs.nvidia.com\/megatron-core\/developer-guide\/latest\/api-guide\/dist_checkpointing.html, 2024."},{"key":"e_1_3_2_1_51_1","volume-title":"https:\/\/pytorch.org\/tutorials\/recipes\/distributed_checkpoint_recipe.html","author":"Team P.","year":"2023","unstructured":"P. Team. Getting started with distributed checkpoint (dcp). https:\/\/pytorch.org\/tutorials\/recipes\/distributed_checkpoint_recipe.html, 2023."},{"key":"e_1_3_2_1_52_1","volume-title":"Llama: Open and efficient foundation language models. CoRR, abs\/2302.13971","author":"Touvron H.","year":"2023","unstructured":"H. Touvron, T. Lavril, G. Izacard, X. Martinet, M. Lachaux, T. Lacroix, B. Rozi\u00e8re, N. Goyal, E. Hambro, F. Azhar, A. Rodriguez, A. Joulin, E. Grave, and G. Lample. Llama: Open and efficient foundation language models. CoRR, abs\/2302.13971, 2023."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626246.3654732"},{"key":"e_1_3_2_1_54_1","volume-title":"Efficient learned query execution over text and tables [technical report]. arXiv preprint arXiv:2410.22522","author":"Urban M.","year":"2024","unstructured":"M. Urban and C. Binnig. Efficient learned query execution over text and tables [technical report]. arXiv preprint arXiv:2410.22522, 2024."},{"key":"e_1_3_2_1_55_1","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. u. Kaiser, and I. Polosukhin. Attention is all you need. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017."},{"key":"e_1_3_2_1_56_1","volume-title":"Bytecheckpoint: A unified checkpointing system for large foundation model development","author":"Wan B.","year":"2024","unstructured":"B. Wan, M. Han, Y. Sheng, Y. Peng, H. Lin, M. Zhang, Z. Lai, M. Yu, J. Zhang, Z. Song, X. Liu, and C. Wu. Bytecheckpoint: A unified checkpointing system for large foundation model development, 2024."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.14778\/3561261.3561267"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE65448.2025.00374"},{"key":"e_1_3_2_1_59_1","volume-title":"CIDR 2025","author":"Wang J.","year":"2025","unstructured":"J. Wang and G. Li. Aop: Automated and interactive llm pipeline orchestration for answering complex queries. In CIDR 2025, 2025."},{"key":"e_1_3_2_1_60_1","unstructured":"J. Wang G. Li and J. Feng. idatalake: An llm-powered analytics system on data lakes. Data Engineering page 57."},{"key":"e_1_3_2_1_61_1","volume-title":"Fault-tolerant hybrid-parallel training at scale with reliable and efficient in-memory checkpointing","author":"Wang Y.","year":"2024","unstructured":"Y. Wang, X. Kang, S. Shi, X. He, Z. Tang, X. Pan, Y. Zheng, X. Wu, A. C. Zhou, B. He, and X. Chu. Fault-tolerant hybrid-parallel training at scale with reliable and efficient in-memory checkpointing, 2024."},{"key":"e_1_3_2_1_62_1","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","author":"Wettig A.","year":"2024","unstructured":"A. Wettig, A. Gupta, S. Malik, and D. Chen. Qurating: Selecting high-quality data for training language models. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21--27, 2024. OpenReview.net, 2024."},{"key":"e_1_3_2_1_63_1","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","author":"Xia M.","year":"2024","unstructured":"M. Xia, S. Malladi, S. Gururangan, S. Arora, and D. Chen. LESS: selecting influential data for targeted instruction tuning. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21--27, 2024. OpenReview.net, 2024."},{"key":"e_1_3_2_1_64_1","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Xie S. M.","year":"2023","unstructured":"S. M. Xie, S. Santurkar, T. Ma, and P. Liang. Data selection for language models via importance resampling. In A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, 2023."},{"key":"e_1_3_2_1_65_1","volume-title":"ICLR","author":"Yao S.","year":"2023","unstructured":"S. Yao, J. Zhao, D. Yu, N. Du, and et al. React: Synergizing reasoning and acting in language models. In ICLR, 2023."},{"key":"e_1_3_2_1_66_1","first-page":"521","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu G.-I.","year":"2022","unstructured":"G.-I. Yu, J. S. Jeong, G.-W. Kim, S. Kim, and B.-G. Chun. Orca: A distributed serving system for Transformer-Based generative models. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22), pages 521--538, Carlsbad, CA, July 2022. USENIX Association."},{"key":"e_1_3_2_1_67_1","volume-title":"Harnessing diversity for important data selection in pretraining large language models. CoRR, abs\/2409.16986","author":"Zhang C.","year":"2024","unstructured":"C. Zhang, H. Zhong, K. Zhang, C. Chai, R. Wang, X. Zhuang, T. Bai, J. Qiu, L. Cao, Y. Yuan, G. Wang, and C. He. Harnessing diversity for important data selection in pretraining large language models. CoRR, abs\/2409.16986, 2024."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611569"},{"key":"e_1_3_2_1_69_1","first-page":"193","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Zhong Y.","year":"2024","unstructured":"Y. Zhong, S. Liu, J. Chen, J. Hu, Y. Zhu, X. Liu, X. Jin, and H. Zhang. DistServe: Disaggregating prefill and decoding for goodput-optimized large language model serving. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24), pages 193--210, Santa Clara, CA, July 2024. USENIX Association. graphy"}],"event":{"name":"SIGMOD\/PODS '25: International Conference on Management of Data","location":"Berlin Germany","acronym":"SIGMOD\/PODS '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Companion of the 2025 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3722212.3725641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:37:53Z","timestamp":1757543873000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3722212.3725641"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":69,"alternative-id":["10.1145\/3722212.3725641","10.1145\/3722212"],"URL":"https:\/\/doi.org\/10.1145\/3722212.3725641","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]},"assertion":[{"value":"2025-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}