{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T05:20:26Z","timestamp":1777180826443,"version":"3.51.4"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051134","type":"print"},{"value":"9783032051141","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"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\/978-3-032-05114-1_55","type":"book-chapter","created":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T14:11:28Z","timestamp":1758377488000},"page":"573-583","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Surgical-MambaLLM: Mamba2-Enhanced Multimodal Large Language Model for\u00a0VQLA in\u00a0Robotic Surgery"],"prefix":"10.1007","author":[{"given":"Pengfei","family":"Hao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongqiu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuaibo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaohu","family":"Xing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaishun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,21]]},"reference":[{"key":"55_CR1","unstructured":"Allan, M., Kondo, S., Bodenstedt, S., Leger, S., Kadkhodamohammadi, R., Luengo, I., Fuentes, F., Flouty, E., Mohammed, A., Pedersen, M., et\u00a0al.: 2018 robotic scene segmentation challenge. arXiv preprint arXiv:2001.11190 (2020)"},{"key":"55_CR2","unstructured":"Allan, M., Shvets, A., Kurmann, T., Zhang, Z., Duggal, R., Su, Y.H., Rieke, N., Laina, I., Kalavakonda, N., Bodenstedt, S., et\u00a0al.: 2017 robotic instrument segmentation challenge. arXiv preprint arXiv:1902.06426 (2019)"},{"key":"55_CR3","doi-asserted-by":"crossref","unstructured":"Bai, L., Islam, M., Ren, H.: Cat-vil: co-attention gated vision-language embedding for visual question localized-answering in robotic surgery. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 397\u2013407. Springer (2023)","DOI":"10.1007\/978-3-031-43996-4_38"},{"key":"55_CR4","doi-asserted-by":"crossref","unstructured":"Bai, L., Islam, M., Seenivasan, L., Ren, H.: Surgical-vqla: Transformer with gated vision-language embedding for visual question localized-answering in robotic surgery. In: 2023 IEEE International Conference on Robotics and Automation (ICRA). pp. 6859\u20136865. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160403"},{"key":"55_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102602","volume":"113","author":"L Bai","year":"2025","unstructured":"Bai, L., Wang, G., Islam, M., Seenivasan, L., Wang, A., Ren, H.: Surgical-vqla++: Adversarial contrastive learning for calibrated robust visual question-localized answering in robotic surgery. Information Fusion 113, 102602 (2025)","journal-title":"Information Fusion"},{"key":"55_CR6","doi-asserted-by":"crossref","unstructured":"Ben-Younes, H., Cadene, R., Cord, M., Thome, N.: Mutan: Multimodal tucker fusion for visual question answering. In: Proceedings of the IEEE international conference on computer vision. pp. 2612\u20132620 (2017)","DOI":"10.1109\/ICCV.2017.285"},{"key":"55_CR7","doi-asserted-by":"crossref","unstructured":"Ben-Younes, H., Cadene, R., Thome, N., Cord, M.: Block: Bilinear superdiagonal fusion for visual question answering and visual relationship detection. In: Proceedings of the AAAI conference on artificial intelligence. vol.\u00a033, pp. 8102\u20138109 (2019)","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"55_CR8","doi-asserted-by":"crossref","unstructured":"Chen, K., Du, Y., You, T., Islam, M., Guo, Z., Jin, Y., Chen, G., Heng, P.A.: Llm-assisted multi-teacher continual learning for visual question answering in robotic surgery. arXiv preprint arXiv:2402.16664 (2024)","DOI":"10.1109\/ICRA57147.2024.10610603"},{"key":"55_CR9","unstructured":"Dao, T., Gu, A.: Transformers are ssms: Generalized models and efficient algorithms through structured state space duality. arXiv preprint arXiv:2405.21060 (2024)"},{"key":"55_CR10","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"55_CR11","unstructured":"Hao, P., Li, S., Wang, H., Kou, Z., Zhang, J., Yang, G., Zhu, L.: Surgery-r1: Advancing surgical-vqla with reasoning multimodal large language model via reinforcement learning. arXiv preprint arXiv:2506.19469 (2025)"},{"key":"55_CR12","doi-asserted-by":"crossref","unstructured":"Hao, P., Wang, H., Yang, G., Zhu, L.: Enhancing visual reasoning with llm-powered knowledge graphs for visual question localized-answering in robotic surgery. IEEE Journal of Biomedical and Health Informatics (2025)","DOI":"10.1109\/JBHI.2025.3538324"},{"issue":"2","key":"55_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5121\/ijdkp.2015.5201","volume":"5","author":"M Hossin","year":"2015","unstructured":"Hossin, M., Sulaiman, M.N.: A review on evaluation metrics for data classification evaluations. International journal of data mining & knowledge management process 5(2), 1 (2015)","journal-title":"International journal of data mining & knowledge management process"},{"key":"55_CR14","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"55_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, X., Han, C., Mesgarani, N.: Dual-path mamba: Short and long-term bidirectional selective structured state space models for speech separation. arXiv preprint arXiv:2403.18257 (2024)","DOI":"10.1109\/ICASSP49660.2025.10888514"},{"key":"55_CR16","doi-asserted-by":"crossref","unstructured":"Kalman, R.E.: A new approach to linear filtering and prediction problems (1960)","DOI":"10.1115\/1.3662552"},{"issue":"5","key":"55_CR17","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1109\/TRA.2003.817086","volume":"19","author":"A Krupa","year":"2003","unstructured":"Krupa, A., Gangloff, J., Doignon, C., De Mathelin, M.F., Morel, G., Leroy, J., Soler, L., Marescaux, J.: Autonomous 3-d positioning of surgical instruments in robotized laparoscopic surgery using visual servoing. IEEE Trans. Robot. Autom. 19(5), 842\u2013853 (2003)","journal-title":"IEEE Trans. Robot. Autom."},{"key":"55_CR18","doi-asserted-by":"crossref","unstructured":"Li, S., Ma, W., Guo, J., Xu, S., Li, B., Zhang, X.: Unionformer: Unified-learning transformer with multi-view representation for image manipulation detection and localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12523\u201312533 (2024)","DOI":"10.1109\/CVPR52733.2024.01190"},{"key":"55_CR19","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., Liu, Y.: Vmamba: Visual state space model 2024. arXiv preprint arXiv:2401.10166 (2024)"},{"key":"55_CR20","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"55_CR21","unstructured":"OpenAI, R.: Gpt-4 technical report. arxiv 2303.08774. View in Article 2(5) (2023)"},{"issue":"4","key":"55_CR22","doi-asserted-by":"publisher","first-page":"1636","DOI":"10.1007\/s00464-018-6079-2","volume":"32","author":"BS Peters","year":"2018","unstructured":"Peters, B.S., Armijo, P.R., Krause, C., Choudhury, S.A., Oleynikov, D.: Review of emerging surgical robotic technology. Surg. Endosc. 32(4), 1636\u20131655 (2018). https:\/\/doi.org\/10.1007\/s00464-018-6079-2","journal-title":"Surg. Endosc."},{"key":"55_CR23","unstructured":"Qiao, Y., Yu, Z., Guo, L., Chen, S., Zhao, Z., Sun, M., Wu, Q., Liu, J.: Vl-mamba: Exploring state space models for multimodal learning. arXiv preprint arXiv:2403.13600 (2024)"},{"key":"55_CR24","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International conference on machine learning. pp. 8748\u20138763. PMLR (2021)"},{"key":"55_CR25","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: A metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"55_CR26","doi-asserted-by":"crossref","unstructured":"Seenivasan, L., Islam, M., Krishna, A.K., Ren, H.: Surgical-vqa: Visual question answering in surgical scenes using transformer. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 33\u201343. Springer (2022)","DOI":"10.1007\/978-3-031-16449-1_4"},{"key":"55_CR27","unstructured":"Team, I.: Internlm: A multilingual language model with progressively enhanced capabilities (2023)"},{"key":"55_CR28","unstructured":"Vaswani, A.: Attention is all you need. Advances in Neural Information Processing Systems (2017)"},{"key":"55_CR29","doi-asserted-by":"crossref","unstructured":"Wang, H., Jin, Y., Zhu, L.: Dynamic interactive relation capturing via scene graph learning for robotic surgical report generation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA). pp. 2702\u20132709. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160647"},{"key":"55_CR30","doi-asserted-by":"crossref","unstructured":"Wang, H., Yang, G., Zhang, S., Qin, J., Guo, Y., Xu, B., Jin, Y., Zhu, L.: Video-instrument synergistic network for referring video instrument segmentation in robotic surgery. IEEE Transactions on Medical Imaging (2024)","DOI":"10.1109\/TMI.2024.3426953"},{"key":"55_CR31","doi-asserted-by":"crossref","unstructured":"Wu, H., Yang, Y., Xu, H., Wang, W., Zhou, J., Zhu, L.: Rainmamba: Enhanced locality learning with state space models for video deraining. In: Proceedings of the 32nd ACM International Conference on Multimedia. pp. 7881\u20137890 (2024)","DOI":"10.1145\/3664647.3680916"},{"key":"55_CR32","doi-asserted-by":"crossref","unstructured":"Xing, Z., Ye, T., Yang, Y., Liu, G., Zhu, L.: Segmamba: Long-range sequential modeling mamba for 3d medical image segmentation. arXiv preprint arXiv:2401.13560 (2024)","DOI":"10.1007\/978-3-031-72111-3_54"},{"issue":"12","key":"55_CR33","doi-asserted-by":"publisher","first-page":"5947","DOI":"10.1109\/TNNLS.2018.2817340","volume":"29","author":"Z Yu","year":"2018","unstructured":"Yu, Z., Yu, J., Xiang, C., Fan, J., Tao, D.: Beyond bilinear: Generalized multimodal factorized high-order pooling for visual question answering. IEEE transactions on neural networks and learning systems 29(12), 5947\u20135959 (2018)","journal-title":"IEEE transactions on neural networks and learning systems"},{"key":"55_CR34","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhang, M., Zhao, W., Ding, P., Huang, S., Wang, D.: Cobra: Extending mamba to multi-modal large language model for efficient inference. arXiv preprint arXiv:2403.14520 (2024)","DOI":"10.1609\/aaai.v39i10.33131"},{"key":"55_CR35","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: Efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417 (2024)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05114-1_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T14:11:40Z","timestamp":1758377500000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05114-1_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,21]]},"ISBN":["9783032051134","9783032051141"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05114-1_55","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,21]]},"assertion":[{"value":"21 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have\u00a0no competing interests to declare that are relevant to the content\u00a0of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}