{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:16:07Z","timestamp":1783106167629,"version":"3.54.6"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533459","type":"print"},{"value":"9789819533466","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"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\/978-981-95-3346-6_10","type":"book-chapter","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:49:45Z","timestamp":1763790585000},"page":"128-140","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["How Do Shared Experts Dynamically Adapt to\u00a0Routing Constraints in\u00a0Mixture-of-Experts?"],"prefix":"10.1007","author":[{"given":"Huayang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingjie","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaowu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongfei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,23]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","first-page":"32897","DOI":"10.52202\/068431-2384","volume":"35","author":"H Bao","year":"2022","unstructured":"Bao, H., et al.: VLMO: unified vision-language pre-training with mixture-of-modality-experts. Adv. Neural. Inf. Process. Syst. 35, 32897\u201332912 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR2","unstructured":"Belrose, N., et al.: Eliciting latent predictions from transformers with the tuned lens. arXiv preprint arXiv:2303.08112 (2023)"},{"key":"10_CR3","unstructured":"Bordes, F., et\u00a0al.: An introduction to vision-language modeling. arXiv preprint arXiv:2405.17247 (2024)"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Dai, D., et\u00a0al.: DeepSeekMoe: towards ultimate expert specialization in mixture-of-experts language models. arXiv preprint arXiv:2401.06066 (2024)","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"10_CR6","unstructured":"Du, N., et\u00a0al.: Glam: efficient scaling of language models with mixture-of-experts. In: International Conference on Machine Learning, pp. 5547\u20135569. PMLR (2022)"},{"issue":"120","key":"10_CR7","first-page":"1","volume":"23","author":"W Fedus","year":"2022","unstructured":"Fedus, W., Zoph, B., Shazeer, N.: Switch transformers: scaling to trillion parameter models with simple and efficient sparsity. J. Mach. Learn. Res. 23(120), 1\u201339 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR8","unstructured":"Gou, Y., et al.: Mixture of cluster-conditional LORA experts for vision-language instruction tuning. arXiv preprint arXiv:2312.12379 (2023)"},{"key":"10_CR9","unstructured":"Komatsuzaki, A., et al.: Sparse upcycling: training mixture-of-experts from dense checkpoints. arXiv preprint arXiv:2212.05055 (2022)"},{"key":"10_CR10","unstructured":"Lepikhin, D., et al.: GSHARD: scaling giant models with conditional computation and automatic sharding. arXiv preprint arXiv:2006.16668 (2020)"},{"key":"10_CR11","unstructured":"Lin, B., et\u00a0al.: Moe-LLAVA: mixture of experts for large vision-language models. arXiv preprint arXiv:2401.15947 (2024)"},{"key":"10_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"10_CR13","unstructured":"Liu, A., et\u00a0al.: DeepSeek-V2: a strong, economical, and efficient mixture-of-experts language model. arXiv preprint arXiv:2405.04434 (2024)"},{"key":"10_CR14","unstructured":"Lu, H., et\u00a0al.: DeepSeek-VL: towards real-world vision-language understanding. arXiv preprint arXiv:2403.05525 (2024)"},{"key":"10_CR15","unstructured":"Neo, C., Ong, L., Torr, P., Geva, M., Krueger, D., Barez, F.: Towards interpreting visual information processing in vision-language models. arXiv preprint arXiv:2410.07149 (2024)"},{"key":"10_CR16","unstructured":"Nostalgebraist: Interpreting GPT: the logit lens. Blog Post (2020)"},{"key":"10_CR17","unstructured":"Shazeer, N., et al.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538 (2017)"},{"key":"10_CR18","unstructured":"Wang, L., Gao, H., Zhao, C., Sun, X., Dai, D.: Auxiliary-loss-free load balancing strategy for mixture-of-experts. arXiv preprint arXiv:2408.15664 (2024)"},{"key":"10_CR19","unstructured":"Wang, P., et\u00a0al.: QWEN2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"10_CR20","unstructured":"Wu, Z., et\u00a0al.: DeepSeek-VL2: mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint arXiv:2412.10302 (2024)"},{"key":"10_CR21","doi-asserted-by":"publisher","first-page":"7103","DOI":"10.52202\/068431-0515","volume":"35","author":"Y Zhou","year":"2022","unstructured":"Zhou, Y., et al.: Mixture-of-experts with expert choice routing. Adv. Neural. Inf. Process. Syst. 35, 7103\u20137114 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3346-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:23:35Z","timestamp":1783103015000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3346-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"ISBN":["9789819533459","9789819533466"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3346-6_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,23]]},"assertion":[{"value":"23 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","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":"7 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}