{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T21:35:47Z","timestamp":1781213747572,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100002920","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","award":["RIF R4020-22, CRF C4026-21GF, GRF 14203323, GRF 14216022, GRF 14211420 and GRF 14204524"],"award-info":[{"award-number":["RIF R4020-22, CRF C4026-21GF, GRF 14203323, GRF 14216022, GRF 14211420 and GRF 14204524"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation China\/Research Grants Council Joint Research Scheme","award":["N_CUHK420\/22"],"award-info":[{"award-number":["N_CUHK420\/22"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758200","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:39:06Z","timestamp":1761377946000},"page":"12636-12643","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["CoPESD: A Multi-Level Surgical Motion Dataset for Training Large Vision-Language Models to Co-Pilot Endoscopic Submucosal Dissection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2440-4950","authenticated-orcid":false,"given":"Guankun","family":"Wang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8884-5344","authenticated-orcid":false,"given":"Han","family":"Xiao","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong and Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4503-5277","authenticated-orcid":false,"given":"Renrui","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong and Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8700-560X","authenticated-orcid":false,"given":"Huxin","family":"Gao","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9762-6821","authenticated-orcid":false,"given":"Long","family":"Bai","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1497-0628","authenticated-orcid":false,"given":"Xiaoxiao","family":"Yang","sequence":"additional","affiliation":[{"name":"The Qilu Hospital of Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9783-169X","authenticated-orcid":false,"given":"Zhen","family":"Li","sequence":"additional","affiliation":[{"name":"The Qilu Hospital of Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2664-7975","authenticated-orcid":false,"given":"Hongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong and Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6488-1551","authenticated-orcid":false,"given":"Hongliang","family":"Ren","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231209338"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2018.01.068"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gie.2014.12.010"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gie.2022.05.019"},{"key":"e_1_3_2_1_5_1","first-page":"61","article-title":"A dvrk-based framework for surgical subtask automation","author":"Nagy T. D.","year":"2019","unstructured":"T. D. Nagy and T. Haidegger, ''A dvrk-based framework for surgical subtask automation,'' Acta Polytechnica Hungarica, pp. 61-78, 2019.","journal-title":"Acta Polytechnica Hungarica"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0149174"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/136457001753192222"},{"key":"e_1_3_2_1_8_1","first-page":"3","article-title":"Jhu-isi gesture and skill assessment working set (jigsaws): A surgical activity dataset for human motion modeling","volume":"3","author":"Gao Y.","year":"2014","unstructured":"Y. Gao, S. S. Vedula, C. E. Reiley, N. Ahmidi, B. Varadarajan, H. C. Lin, L. Tao, L. Zappella, B. B\u00e9jar, D. D. Yuh et al., ''Jhu-isi gesture and skill assessment working set (jigsaws): A surgical activity dataset for human motion modeling,'' in MICCAI workshop: M2cai, vol. 3, no. 2014, 2014, p. 3.","journal-title":"MICCAI workshop: M2cai"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"L. Bai T. Chen Y. Wu A. Wang M. Islam and H. Ren ''Llcaps: Learning to illuminate low-light capsule endoscopy with curved wavelet attention and reverse diffusion '' in International Conference on Medical Image Computing and Computer-Assisted Intervention. hskip 1em plus 0.5em minus 0.4emrelax Springer 2023 pp. 34-44.","DOI":"10.1007\/978-3-031-43999-5_4"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gie.2020.09.042"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.21037\/atm.2017.02.12"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1055\/s-0029-1215129"},{"key":"e_1_3_2_1_13_1","volume-title":"Ossar: Towards open-set surgical activity recognition in robot-assisted surgery,'' arXiv preprint arXiv:2402.06985","author":"Bai L.","year":"2024","unstructured":"L. Bai, G. Wang, J. Wang, X. Yang, H. Gao, X. Liang, A. Wang, M. Islam, and H. Ren, ''Ossar: Towards open-set surgical activity recognition in robot-assisted surgery,'' arXiv preprint arXiv:2402.06985, 2024."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-42451-8"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gie.2023.12.037"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"K. Huang X. Yuan R. Liu Y. Zhou B. Hu and Z. Yi ''An experimental study of nmode in recognizing endoscopic submucosal dissection workflow '' in 2023 International Annual Conference on Complex Systems and Intelligent Science (CSIS-IAC). hskip 1em plus 0.5em minus 0.4emrelax IEEE 2023 pp. 603-608.","DOI":"10.1109\/CSIS-IAC60628.2023.10364057"},{"key":"e_1_3_2_1_17_1","volume-title":"Anadkat et al., ''Gpt-4 technical report,'' arXiv preprint arXiv:2303.08774","author":"Achiam J.","year":"2023","unstructured":"J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F. L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat et al., ''Gpt-4 technical report,'' arXiv preprint arXiv:2303.08774, 2023."},{"key":"e_1_3_2_1_18_1","first-page":"787","volume-title":"Referitgame: Referring to objects in photographs of natural scenes,'' in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Kazemzadeh S.","year":"2014","unstructured":"S. Kazemzadeh, V. Ordonez, M. Matten, and T. Berg, ''Referitgame: Referring to objects in photographs of natural scenes,'' in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014, pp. 787-798."},{"key":"e_1_3_2_1_19_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks,'' Advances in Neural Information Processing Systems","author":"Lu J.","year":"2019","unstructured":"J. Lu, D. Batra, D. Parikh, and S. Lee, ''Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks,'' Advances in Neural Information Processing Systems, vol. 32, 2019."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-101119-071628"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"J. Hatori Y. Kikuchi S. Kobayashi K. Takahashi Y. Tsuboi Y. Unno W. Ko and J. Tan ''Interactively picking real-world objects with unconstrained spoken language instructions '' in 2018 IEEE International Conference on Robotics and Automation (ICRA). hskip 1em plus 0.5em minus 0.4emrelax IEEE 2018 pp. 3774-3781.","DOI":"10.1109\/ICRA.2018.8460699"},{"key":"e_1_3_2_1_22_1","volume-title":"Robot object retrieval with contextual natural language queries,'' arXiv preprint arXiv:2006.13253","author":"Nguyen T.","year":"2020","unstructured":"T. Nguyen, N. Gopalan, R. Patel, M. Corsaro, E. Pavlick, and S. Tellex, ''Robot object retrieval with contextual natural language queries,'' arXiv preprint arXiv:2006.13253, 2020."},{"key":"e_1_3_2_1_23_1","volume-title":"Invigorate: Interactive visual grounding and grasping in clutter,'' arXiv preprint arXiv:2108.11092","author":"Zhang H.","year":"2021","unstructured":"H. Zhang, Y. Lu, C. Yu, D. Hsu, X. La, and N. Zheng, ''Invigorate: Interactive visual grounding and grasping in clutter,'' arXiv preprint arXiv:2108.11092, 2021."},{"key":"e_1_3_2_1_24_1","volume-title":"Language conditioned imitation learning over unstructured data,'' arXiv preprint arXiv:2005.07648","author":"Lynch C.","year":"2020","unstructured":"C. Lynch and P. Sermanet, ''Language conditioned imitation learning over unstructured data,'' arXiv preprint arXiv:2005.07648, 2020."},{"key":"e_1_3_2_1_25_1","first-page":"13","article-title":"imitation learning for robot manipulation tasks","volume":"33","author":"Stepputtis S.","year":"2020","unstructured":"S. Stepputtis, J. Campbell, M. Phielipp, S. Lee, C. Baral, and H. Ben Amor, ''Language-conditioned imitation learning for robot manipulation tasks,'' Advances in Neural Information Processing Systems, vol. 33, pp. 13,139-13,150, 2020.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_26_1","first-page":"991","volume-title":"Bc-z: Zero-shot task generalization with robotic imitation learning,'' in Conference on Robot Learning. hskip 1em plus 0.5em minus 0.4emrelax PMLR","author":"Jang E.","year":"2022","unstructured":"E. Jang, A. Irpan, M. Khansari, D. Kappler, F. Ebert, C. Lynch, S. Levine, and C. Finn, ''Bc-z: Zero-shot task generalization with robotic imitation learning,'' in Conference on Robot Learning. hskip 1em plus 0.5em minus 0.4emrelax PMLR, 2022, pp. 991-1002."},{"key":"e_1_3_2_1_27_1","first-page":"1303","volume-title":"Finn et al., ''Learning language-conditioned robot behavior from offline data and crowd-sourced annotation,'' in Conference on Robot Learning. hskip 1em plus 0.5em minus 0.4emrelax PMLR","author":"Nair S.","year":"2022","unstructured":"S. Nair, E. Mitchell, K. Chen, S. Savarese, C. Finn et al., ''Learning language-conditioned robot behavior from offline data and crowd-sourced annotation,'' in Conference on Robot Learning. hskip 1em plus 0.5em minus 0.4emrelax PMLR, 2022, pp. 1303-1315."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211046285"},{"key":"e_1_3_2_1_29_1","first-page":"505","volume-title":"Mapping navigation instructions to continuous control actions with position-visitation prediction,'' in Conference on Robot Learning. hskip 1em plus 0.5em minus 0.4emrelax PMLR","author":"Blukis V.","year":"2018","unstructured":"V. Blukis, D. Misra, R. A. Knepper, and Y. Artzi, ''Mapping navigation instructions to continuous control actions with position-visitation prediction,'' in Conference on Robot Learning. hskip 1em plus 0.5em minus 0.4emrelax PMLR, 2018, pp. 505-518."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-021-01344-y"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"T. Nguyen N. D. Nguyen F. Bello and S. Nahavandi ''A new tensioning method using deep reinforcement learning for surgical pattern cutting '' in 2019 IEEE International Conference on Industrial Technology (ICIT). hskip 1em plus 0.5em minus 0.4emrelax IEEE 2019 pp. 1339-1344.","DOI":"10.1109\/ICIT.2019.8755235"},{"key":"e_1_3_2_1_33_1","volume-title":"Finn et al., ''Rt-2: Vision-language-action models transfer web knowledge to robotic control,'' arXiv preprint arXiv:2307.15818","author":"Brohan A.","year":"2023","unstructured":"A. Brohan, N. Brown, J. Carbajal, Y. Chebotar, X. Chen, K. Choromanski, T. Ding, D. Driess, A. Dubey, C. Finn et al., ''Rt-2: Vision-language-action models transfer web knowledge to robotic control,'' arXiv preprint arXiv:2307.15818, 2023."},{"key":"e_1_3_2_1_34_1","volume-title":"Language-driven representation learning for robotics,'' arXiv preprint arXiv:2302.12766","author":"Karamcheti S.","year":"2023","unstructured":"S. Karamcheti, S. Nair, A. S. Chen, T. Kollar, C. Finn, D. Sadigh, and P. Liang, ''Language-driven representation learning for robotics,'' arXiv preprint arXiv:2302.12766, 2023."},{"key":"e_1_3_2_1_35_1","volume-title":"Jin et al., ''Sphinx-x: Scaling data and parameters for a family of multi-modal large language models,'' arXiv preprint arXiv:2402.05935","author":"Gao P.","year":"2024","unstructured":"P. Gao, R. Zhang, C. Liu, L. Qiu, S. Huang, W. Lin, S. Zhao, S. Geng, Z. Lin, P. Jin et al., ''Sphinx-x: Scaling data and parameters for a family of multi-modal large language models,'' arXiv preprint arXiv:2402.05935, 2024."},{"key":"e_1_3_2_1_36_1","first-page":"11","volume-title":"A convnet for the","author":"Liu Z.","year":"2020","unstructured":"Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, ''A convnet for the 2020s,'' in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11,976-11,986."},{"key":"e_1_3_2_1_37_1","first-page":"9650","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron M.","year":"2021","unstructured":"M. Caron, H. Touvron, I. Misra, H. J\u00e9gou, J. Mairal, P. Bojanowski, and A. Joulin, ''Emerging properties in self-supervised vision transformers,'' in Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 9650-9660.","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"e_1_3_2_1_38_1","volume-title":"Improved baselines with visual instruction tuning,'' arXiv preprint arXiv:2310.03744","author":"Liu H.","year":"2023","unstructured":"H. Liu, C. Li, Y. Li, and Y. J. Lee, ''Improved baselines with visual instruction tuning,'' arXiv preprint arXiv:2310.03744, 2023."},{"key":"e_1_3_2_1_39_1","first-page":"8748","volume-title":"Clark et al., ''Learning transferable visual models from natural language supervision,'' in International Conference on Machine Learning. hskip 1em plus 0.5em minus 0.4emrelax PMLR","author":"Radford A.","year":"2021","unstructured":"A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark et al., ''Learning transferable visual models from natural language supervision,'' in International Conference on Machine Learning. hskip 1em plus 0.5em minus 0.4emrelax PMLR, 2021, pp. 8748-8763."},{"key":"e_1_3_2_1_40_1","volume-title":"Bhosale et al., ''Llama 2: Open foundation and fine-tuned chat models,'' arXiv preprint arXiv:2307.09288","author":"Touvron H.","year":"2023","unstructured":"H. Touvron, L. Martin, K. Stone, P. Albert, A. Almahairi, Y. Babaei, N. Bashlykov, S. Batra, P. Bhargava, S. Bhosale et al., ''Llama 2: Open foundation and fine-tuned chat models,'' arXiv preprint arXiv:2307.09288, 2023."},{"key":"e_1_3_2_1_41_1","volume-title":"Surgical-lvlm: Learning to adapt large vision-language model for grounded visual question answering in robotic surgery,'' arXiv preprint arXiv:2405.10948","author":"Wang G.","year":"2024","unstructured":"G. Wang, L. Bai, W. J. Nah, J. Wang, Z. Zhang, Z. Chen, J. Wu, M. Islam, H. Liu, and H. Ren, ''Surgical-lvlm: Learning to adapt large vision-language model for grounded visual question answering in robotic surgery,'' arXiv preprint arXiv:2405.10948, 2024."},{"key":"e_1_3_2_1_42_1","volume-title":"Multi-objective cross-task learning via goal-conditioned gpt-based decision transformers for surgical robot task automation,'' arXiv preprint arXiv:2405.18757","author":"Fu J.","year":"2024","unstructured":"J. Fu, Y. Long, K. Chen, W. Wei, and Q. Dou, ''Multi-objective cross-task learning via goal-conditioned gpt-based decision transformers for surgical robot task automation,'' arXiv preprint arXiv:2405.18757, 2024."},{"key":"e_1_3_2_1_43_1","volume-title":"Sanketi et al., ''Openvla: An open-source vision-language-action model,'' arXiv preprint arXiv:2406.09246","author":"Kim M. J.","year":"2024","unstructured":"M. J. Kim, K. Pertsch, S. Karamcheti, T. Xiao, A. Balakrishna, S. Nair, R. Rafailov, E. Foster, G. Lam, P. Sanketi et al., ''Openvla: An open-source vision-language-action model,'' arXiv preprint arXiv:2406.09246, 2024."},{"key":"e_1_3_2_1_44_1","unstructured":"A. O'Neill A. Rehman A. Maddukuri A. Gupta A. Padalkar A. Lee A. Pooley A. Gupta A. Mandlekar A. Jain et al. ''Open x-embodiment: Robotic learning datasets and rt-x models: Open x-embodiment collaboration 0 '' in 2024 IEEE International Conference on Robotics and Automation (ICRA). hskip 1em plus 0.5em minus 0.4emrelax IEEE 2024 pp. 6892-6903."},{"key":"e_1_3_2_1_45_1","volume-title":"Navila: Legged robot vision-language-action model for navigation,'' arXiv preprint arXiv:2412.04453","author":"Cheng A.-C.","year":"2024","unstructured":"A.-C. Cheng, Y. Ji, Z. Yang, Z. Gongye, X. Zou, J. Kautz, E. Biyik, H. Yin, S. Liu, and X. Wang, ''Navila: Legged robot vision-language-action model for navigation,'' arXiv preprint arXiv:2412.04453, 2024."},{"key":"e_1_3_2_1_46_1","first-page":"1","article-title":"Embodied large language models enable robots to complete complex tasks in unpredictable environments","author":"Mon-Williams R.","year":"2025","unstructured":"R. Mon-Williams, G. Li, R. Long, W. Du, and C. G. Lucas, ''Embodied large language models enable robots to complete complex tasks in unpredictable environments,'' Nature Machine Intelligence, pp. 1-10, 2025.","journal-title":"Nature Machine Intelligence"},{"key":"e_1_3_2_1_47_1","volume-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day,'' Advances in Neural Information Processing Systems","author":"Li C.","year":"2024","unstructured":"C. Li, C. Wong, S. Zhang, N. Usuyama, H. Liu, J. Yang, T. Naumann, H. Poon, and J. Gao, ''Llava-med: Training a large language-and-vision assistant for biomedicine in one day,'' Advances in Neural Information Processing Systems, vol. 36, 2024."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.birob.2023.100131"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.birob.2021.100001"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.birob.2024.100187"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.birob.2025.100220"},{"key":"e_1_3_2_1_52_1","volume-title":"Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models,'' arXiv preprint arXiv:2410.09750","author":"Jin J.","year":"2024","unstructured":"J. Jin and C. W. Jeong, ''Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models,'' arXiv preprint arXiv:2410.09750, 2024."},{"key":"e_1_3_2_1_53_1","volume-title":"Visual instruction tuning,'' Advances in neural information processing systems","author":"Liu H.","year":"2024","unstructured":"H. Liu, C. Li, Q. Wu, and Y. J. Lee, ''Visual instruction tuning,'' Advances in neural information processing systems, vol. 36, 2024."},{"key":"e_1_3_2_1_54_1","volume-title":"Memory-Augmented Multimodal LLMs for Surgical VQA via Self-Contained Inquiry,'' arXiv preprint arXiv:2411.10937","author":"Hou W.","year":"2024","unstructured":"W. Hou, Y. Cheng, K. Xu, Y. Hu, W. Li, and J. Liu, ''Memory-Augmented Multimodal LLMs for Surgical VQA via Self-Contained Inquiry,'' arXiv preprint arXiv:2411.10937, 2024."},{"key":"e_1_3_2_1_55_1","volume-title":"GP-VLS: A general-purpose vision language model for surgery,'' arXiv preprint arXiv:2407.19305","author":"Schmidgall S.","year":"2024","unstructured":"S. Schmidgall, J. Cho, C. Zakka, and W. Hiesinger, ''GP-VLS: A general-purpose vision language model for surgery,'' arXiv preprint arXiv:2407.19305, 2024."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.34133\/cbsystems.0042"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.34133\/cbsystems.0109"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:57:22Z","timestamp":1765310242000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758200"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":57,"alternative-id":["10.1145\/3746027.3758200","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758200","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}