{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T12:26:22Z","timestamp":1769775982329,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556397","type":"print"},{"value":"9789819556403","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-5640-3_15","type":"book-chapter","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:07:33Z","timestamp":1769720853000},"page":"220-238","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pioneer: A Method for\u00a0Enhancing GPU Utilization in\u00a0Workloads Through Potential-Aware Prioritization"],"prefix":"10.1007","author":[{"given":"Qing","family":"Guo","sequence":"first","affiliation":[]},{"given":"Wei","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Tingting","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"15_CR1","unstructured":"Bai, J., et al.: Ofasys: a multi-modal multi-task learning system for building generalist models (2022). https:\/\/arxiv.org\/abs\/2212.04408"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Chang, J.X., Lee, C.P., Lim, K.M., Lim, J.Y.: Facial expression recognition with machine learning. In: 2023 11th International Conference on Information and Communication Technology (ICoICT), pp. 125\u2013130. IEEE (2023)","DOI":"10.1109\/ICoICT58202.2023.10262748"},{"key":"15_CR3","doi-asserted-by":"publisher","unstructured":"Chen, H., Yu, C.H., Zheng, S., Zhang, Z., Zhang, Z., Wang, Y.: Slapo: a schedule language for progressive optimization of large deep learning model training. In: Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, vol. 2 (2023). https:\/\/doi.org\/10.1145\/3620665.3640399","DOI":"10.1145\/3620665.3640399"},{"issue":"1","key":"15_CR4","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1007\/s13278-024-01271-4","volume":"14","author":"M Dhawan","year":"2024","unstructured":"Dhawan, M., Sharma, S., Kadam, A., Sharma, R., Kumaraguru, P.: Game-on: graph attention network based multimodal fusion for fake news detection. Soc. Netw. Anal. Min. 14(1), 114 (2024)","journal-title":"Soc. Netw. Anal. Min."},{"key":"15_CR5","doi-asserted-by":"publisher","unstructured":"Gale, T., Narayanan, D., Young, C., Zaharia, M.: Megablocks: efficient sparse training with mixture-of-experts. ArXiv abs\/2211.15841 (2022). https:\/\/doi.org\/10.48550\/arXiv.2211.15841","DOI":"10.48550\/arXiv.2211.15841"},{"key":"15_CR6","doi-asserted-by":"publisher","first-page":"63373","DOI":"10.1109\/ACCESS.2019.2916887","volume":"7","author":"W Guo","year":"2019","unstructured":"Guo, W., Wang, J., Wang, S.: Deep multimodal representation learning: a survey. IEEE Access 7, 63373\u201363394 (2019)","journal-title":"IEEE Access"},{"key":"15_CR7","unstructured":"Hoffmann, J., et al.: Training compute-optimal large language models (2022). http:\/\/arxiv.org\/abs\/2203.15556, cite arxiv:2203.15556"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Jani, Y.: Efficiency and efficacy: Aws instance benchmarking of stable diffusion 1.4 for ai image generation. North Am. J. Eng. Res. 4(2) (2023)","DOI":"10.1109\/AIBThings63359.2024.10863390"},{"key":"15_CR9","unstructured":"Kaplan, J., et al.: Scaling laws for neural language models (2020). https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"15_CR10","unstructured":"Lamy-Poirier, J.: Breadth-first pipeline parallelism (2022)"},{"key":"15_CR11","doi-asserted-by":"publisher","unstructured":"Li, S., Ben-Nun, T., Girolamo, S.D., Alistarh, D., Hoefler, T.: Taming unbalanced training workloads in deep learning with partial collective operations. In: Proceedings of the 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2020, pp. 45\u201361. ACM, February 2020. https:\/\/doi.org\/10.1145\/3332466.3374528, http:\/\/dx.doi.org\/10.1145\/3332466.3374528","DOI":"10.1145\/3332466.3374528"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y., Min, K., Tripathi, S., Vasconcelos, N.: Svitt: temporal learning of sparse video-text transformers (2023). https:\/\/arxiv.org\/abs\/2304.08809","DOI":"10.1109\/CVPR52729.2023.01814"},{"key":"15_CR13","unstructured":"Li, Y., et\u00a0al.: Static batching of irregular workloads on gpus: framework and application to efficient moe model inference. arXiv preprint arXiv:2501.16103 (2025)"},{"key":"15_CR14","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context (2015). https:\/\/arxiv.org\/abs\/1405.0312"},{"key":"15_CR15","doi-asserted-by":"publisher","unstructured":"Miao, X., et al.: Galvatron: efficient transformer training over multiple gpus using automatic parallelism. Proc. VLDB Endow. 16(3), 470\u2013479 (2022). https:\/\/doi.org\/10.14778\/3570690.3570697, https:\/\/www.vldb.org\/pvldb\/vol16\/p470-miao.pdf","DOI":"10.14778\/3570690.3570697"},{"key":"15_CR16","unstructured":"OpenAI: Gpt-4 technical report. ArXiv abs\/2303.08774 (2023). https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"15_CR17","doi-asserted-by":"publisher","unstructured":"Peng, H., et al.: Fp8-lm: training fp8 large language models. ArXiv abs\/2310.18313 (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.18313","DOI":"10.48550\/arXiv.2310.18313"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10684\u201310695, June 2022","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"15_CR19","doi-asserted-by":"publisher","unstructured":"Roumeliotis, K.I., Tselikas, N.D.: Chatgpt and open-ai models: A preliminary review. Future Internet 15(6) (2023). https:\/\/doi.org\/10.3390\/fi15060192, https:\/\/www.mdpi.com\/1999-5903\/15\/6\/192","DOI":"10.3390\/fi15060192"},{"issue":"5\u20136","key":"15_CR20","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1080\/01691864.2022.2035253","volume":"36","author":"M Suzuki","year":"2022","unstructured":"Suzuki, M., Matsuo, Y.: A survey of multimodal deep generative models. Adv. Robot. 36(5\u20136), 261\u2013278 (2022)","journal-title":"Adv. Robot."},{"key":"15_CR21","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"15_CR22","unstructured":"Unger, C., Jia, Z., Wu, W., et\u00a0al.: Unity: accelerating dnn training through joint optimization of algebraic transformations and parallelization. In: OSDI, pp. 267\u2013284 (2022)"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Wang, B., Xu, Q., Bian, Z., You, Y.: Tesseract: parallelize the tensor parallelism efficiently. In: Proceedings of the 51st International Conference on Parallel Processing, pp. 1\u201311 (2022)","DOI":"10.1145\/3545008.3545087"},{"key":"15_CR24","unstructured":"Wang, X., et al.: Large-scale multi-modal pre-trained models: a comprehensive survey (2024). https:\/\/arxiv.org\/abs\/2302.10035"},{"issue":"6","key":"15_CR25","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.3390\/rs16061055","volume":"16","author":"W Zhang","year":"2024","unstructured":"Zhang, W., Wang, X., Wang, H., Cheng, Y.: Causal meta-reinforcement learning for multimodal remote sensing data classification. Remote Sens. 16(6), 1055 (2024)","journal-title":"Remote Sens."},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Disttrain: addressing model and data heterogeneity with disaggregated training for multimodal large language models. arXiv preprint arXiv:2408.04275 (2024)","DOI":"10.1145\/3718958.3750472"},{"key":"15_CR27","doi-asserted-by":"publisher","unstructured":"Zhao, P., et al.: Efficiently training 7b llm with 1 million sequence length on 8 gpus. ArXiv abs\/2407.12117 (2024). https:\/\/doi.org\/10.48550\/arXiv.2407.12117","DOI":"10.48550\/arXiv.2407.12117"}],"container-title":["Lecture Notes in Computer Science","Web and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5640-3_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:07:39Z","timestamp":1769720859000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5640-3_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556397","9789819556403"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5640-3_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"30 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenyang","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/apweb2025.sau.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}