{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:07:10Z","timestamp":1788934030808,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373687","type":"print"},{"value":"9783032373694","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\/978-3-032-37369-4_26","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:44:27Z","timestamp":1788932667000},"page":"478-495","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GeMoE: Gating Entropy Is All You Need for\u00a0Uncertainty-Aware Adaptive Routing in\u00a0MoE-Based Large Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Chaoxiang","family":"Cai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghe","family":"Weng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yibo","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longrong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zequn","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Aminabadi, R.Y., et\u00a0al.: Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale. In: SC22: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201315. IEEE (2022)","DOI":"10.1109\/SC41404.2022.00051"},{"key":"26_CR2","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"26_CR3","unstructured":"Bai, J., et al.: Qwen-vl: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966$$\\textbf{1}(2)$$, 3 (2023)"},{"key":"26_CR4","unstructured":"Bai, S., et\u00a0al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"26_CR5","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"26_CR6","doi-asserted-by":"crossref","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)","DOI":"10.52202\/068431-2384"},{"key":"26_CR7","unstructured":"Cai, C., Yang, L., Chen, K., Yang, F., Li, X.: Long-tailed distribution-aware router for mixture-of-experts in large vision-language model. arXiv preprint arXiv:2507.01351 (2025)"},{"key":"26_CR8","unstructured":"Chen, J., et al.: Minigpt-v2: large language model as a unified interface for vision-language multi-task learning. arxiv 2023. arXiv preprint arXiv:2310.09478 (2023)"},{"key":"26_CR9","unstructured":"Chen, W., et al.: Lifelong language pretraining with distribution-specialized experts. In: International Conference on Machine Learning, pp. 5383\u20135395. PMLR (2023)"},{"key":"26_CR10","unstructured":"Chen, Z., et al.: Octavius: mitigating task interference in mllms via lora-moe. arXiv preprint arXiv:2311.02684 (2023)"},{"key":"26_CR11","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":"26_CR12","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Dai, D., et\u00a0al.: Deepseekmoe: towards ultimate expert specialization in mixture-of-experts language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1280\u20131297 (2024)","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Molmo and pixmo: open weights and open data for state-of-the-art vision-language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 91\u2013104 (2025)","DOI":"10.1109\/CVPR52734.2025.00018"},{"key":"26_CR15","unstructured":"Du, N., et al.: Glam: efficient scaling of language models with mixture-of-experts. In: International Conference on Machine Learning, pp. 5547\u20135569. PMLR (2022)"},{"key":"26_CR16","unstructured":"Eliseev, A., Mazur, D.: Fast inference of mixture-of-experts language models with offloading. arXiv preprint arXiv:2312.17238 (2023)"},{"issue":"120","key":"26_CR17","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":"26_CR18","unstructured":"Gou, Y., et al.: Mixture of cluster-conditional lora experts for vision-language instruction tuning. arXiv preprint arXiv:2312.12379 (2023)"},{"key":"26_CR19","unstructured":"Guo, Y., Cheng, Z., Tang, X., Tu, Z., Lin, T.: Dynamic mixture of experts: an auto-tuning approach for efficient transformer models. arXiv preprint arXiv:2405.14297 (2024)"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Huang, Q., et al.: Harder task needs more experts: dynamic routing in moe models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12883\u201312895 (2024)","DOI":"10.18653\/v1\/2024.acl-long.696"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"issue":"1","key":"26_CR22","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79\u201387 (1991)","journal-title":"Neural Comput."},{"key":"26_CR23","unstructured":"Jiang, A.Q., et\u00a0al.: Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)"},{"key":"26_CR24","unstructured":"Jin, P., Zhu, B., Yuan, L., Yan, S.: Moe++: accelerating mixture-of-experts methods with zero-computation experts. arXiv preprint arXiv:2410.07348 (2024)"},{"key":"26_CR25","unstructured":"Komatsuzaki, A., et al.: Sparse upcycling: training mixture-of-experts from dense checkpoints. arXiv preprint arXiv:2212.05055 (2022)"},{"key":"26_CR26","unstructured":"Lepikhin, D., et al.: Gshard: scaling giant models with conditional computation and automatic sharding. arXiv preprint arXiv:2006.16668 (2020)"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, W.X., Wen, J.R.: Evaluating object hallucination in large vision-language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 292\u2013305 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"26_CR28","unstructured":"Li, Y., et\u00a0al.: Uni-moe-2.0-omni: scaling language-centric omnimodal large model with advanced moe, training and data. arXiv preprint arXiv:2511.12609 (2025)"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Uni-moe: scaling unified multimodal llms with mixture of experts. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3532688"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Lin, B., et al.: Moe-llava: mixture of experts for large vision-language models. IEEE Trans. Multimed. (2026)","DOI":"10.1109\/TMM.2026.3654458"},{"key":"26_CR31","unstructured":"Liu, F., Lin, K., Li, L., Wang, J., Yacoob, Y., Wang, L.: Aligning large multi-modal model with robust instruction tuning. arXiv preprint arXiv:2306.14565$$\\textbf{2}(3)$$, 6 (2023)"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural Inf. Process. Syst. 36, 34892\u201334916 (2023)","DOI":"10.52202\/075280-1516"},{"key":"26_CR33","doi-asserted-by":"publisher","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player?. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15064, pp. 216\u2013233. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72658-3_13","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"26_CR34","unstructured":"Liu, Z., Luo, J.: Adamole: fine-tuning large language models with adaptive mixture of low-rank adaptation experts. arXiv preprint arXiv:2405.00361 (2024)"},{"key":"26_CR35","doi-asserted-by":"publisher","first-page":"2507","DOI":"10.52202\/068431-0182","volume":"35","author":"P Lu","year":"2022","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. Adv. Neural. Inf. Process. Syst. 35, 2507\u20132521 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR36","unstructured":"Puigcerver, J., Riquelme, C., Mustafa, B., Houlsby, N.: From sparse to soft mixtures of experts. arXiv preprint arXiv:2308.00951 (2023)"},{"issue":"8","key":"26_CR37","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"26_CR38","unstructured":"Shazeer, N., et al.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538 (2017)"},{"key":"26_CR39","unstructured":"Shen, S., et al.: Mixture-of-experts meets instruction tuning: a winning combination for large language models. arXiv preprint arXiv:2305.14705 (2023)"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards vqa models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"26_CR41","unstructured":"Song, C., et al.: Blockffn: towards end-side acceleration-friendly mixture-of-experts with chunk-level activation sparsity (2025). https:\/\/arxiv.org\/abs\/2507.08771"},{"key":"26_CR42","unstructured":"Wang, Z., Zhu, J., Chen, J.: Remoe: fully differentiable mixture-of-experts with relu routing. arXiv preprint arXiv:2412.14711 (2024)"},{"key":"26_CR43","unstructured":"Wei, T., et\u00a0al.: Skywork-moe: a deep dive into training techniques for mixture-of-experts language models. arXiv preprint arXiv:2406.06563 (2024)"},{"key":"26_CR44","unstructured":"Wu, Z., et\u00a0al.: Deepseek-vl2: mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint arXiv:2412.10302 (2024)"},{"key":"26_CR45","unstructured":"Xue, F., et al.: Openmoe: an early effort on open mixture-of-experts language models. arXiv preprint arXiv:2402.01739 (2024)"},{"key":"26_CR46","unstructured":"Xue, L., Fu, Y., Lu, Z., Mai, L., Marina, M.: Moe-infinity: offloading-efficient moe model serving. arXiv e-prints, pp. arXiv\u20132401 (2024)"},{"key":"26_CR47","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"26_CR48","unstructured":"Yu, W., et al.: Mm-vet: evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490 (2023)"},{"key":"26_CR49","unstructured":"Yue, T., Guo, L., Cheng, J., Gao, X., Huang, H., Liu, J.: Ada-k routing: boosting the efficiency of moe-based llms. In: The Thirteenth International Conference on Learning Representations (2024)"},{"key":"26_CR50","doi-asserted-by":"crossref","unstructured":"Zeng, Z., Miao, Y., Gao, H., Zhang, H., Deng, Z.: Adamoe: token-adaptive routing with null experts for mixture-of-experts language models. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 6223\u20136235 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.361"},{"key":"26_CR51","unstructured":"Zhang, Y., et al.: Llavar: enhanced visual instruction tuning for text-rich image understanding. arXiv preprint arXiv:2306.17107 (2023)"},{"key":"26_CR52","doi-asserted-by":"crossref","unstructured":"Zhong, S., Gao, S., Huang, Z., Wen, W., \u017ditnik, M., Zhou, P.: Moextend: tuning new experts for modality and task extension. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pp. 494\u2013505 (2024)","DOI":"10.18653\/v1\/2024.acl-srw.8"},{"key":"26_CR53","unstructured":"Zhou, Y., et al.: Exploring training on heterogeneous data with mixture of low-rank adapters. arXiv preprint arXiv:2406.09679 (2024)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37369-4_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:44:37Z","timestamp":1788932677000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37369-4_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373687","9783032373694"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37369-4_26","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":"10 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}