{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:08:19Z","timestamp":1784146099410,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234844","type":"print"},{"value":"9789819234851","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3485-1_35","type":"book-chapter","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:00:15Z","timestamp":1784145615000},"page":"413-424","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Core3D: Dynamic Information Nucleus Selection and Token Pruning for Dense 3D Multimodal Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9069-4310","authenticated-orcid":false,"given":"Yue","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4571-340X","authenticated-orcid":false,"given":"Zengyi","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Wu, J.Y., Gan, W.S., Chen, Z.F., et al.: Multimodal large language models: a survey.In: 2023 IEEE International Conference on Big Data (BigData), pp. 2247\u20132256. IEEE (2023)","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"35_CR2","unstructured":"Chen, J.J., Liu, X.Y., Wen, Z.C., et al.: Variation-aware vision token dropping for faster large vision-language models. arXiv preprint arXiv:2509.01552 (2025)"},{"key":"35_CR3","unstructured":"Thengane, V., Zhu, X.T., Bouzerdoum, S., et al.: Foundational models for 3D point clouds: a survey and outlook. arXiv preprint arXiv:2501.18594 (2025)"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Zha, J.R., Fan, Y.X., Yang, X., et al.: How to enable LLM with 3D capacity? A survey of spatial reasoning in LLM. In: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, pp. 10817\u201310825 (2025)","DOI":"10.24963\/ijcai.2025\/1200"},{"key":"35_CR5","unstructured":"Huang, X.H., Wu, J.J., Xie, Q.Y., et al.: 3DRS: MLLMs need 3D-aware representation supervision for scene understanding. arXiv preprint arXiv:2506.01946 (2025)"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Wang, Y., Jia, B.X., Zhu, Z.Y., et al.: Masked point-entity contrast for open-vocabulary 3D scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14125\u201314136 (2025)","DOI":"10.1109\/CVPR52734.2025.01318"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y.W., Lan, Y.S., Zhou, S.C., et al.: SAR3D: autoregressive 3D object generation and understanding via multi-scale 3Dd VQVAE. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 28371\u201328382 (2025)","DOI":"10.1109\/CVPR52734.2025.02642"},{"key":"35_CR8","unstructured":"Ye, J.L., Wang, Z.Y., Zhao, R.W., et al.: Shapellm-omni: a native multimodal LLM for 3D generation and understanding. arXiv preprint arXiv:2506.01853 (2025)"},{"key":"35_CR9","doi-asserted-by":"crossref","unstructured":"Fang, S.K., Shen, I., Wang, Y.F., et al.: MeshLLM: empowering large language models to progressively understand and generate 3D mesh. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14061\u201314072 (2025)","DOI":"10.1109\/ICCV51701.2025.01305"},{"key":"35_CR10","unstructured":"Wasi, A.T., Faisal, W., Rahman, A., et al.: SpatiaLab: can vision-language models perform spatial reasoning in the wild?. arXiv preprint arXiv:2602.03916 (2026)"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Daxberger, E., Wenzel, N., Griffiths, D., et al.: Mm-spatial: exploring 3D spatial understanding in multimodal LLMs. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7395\u20137408 (2025)","DOI":"10.1109\/ICCV51701.2025.00694"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Mo, W.T., Chen, Q.C., Peng, Y.X., et al.: Advancing 3D scene understanding with MV-ScanQA multi-view reasoning evaluation and TripAlign pre-training dataset. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 12973\u201312980 (2025)","DOI":"10.1145\/3746027.3758244"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Zhou, S.L., Liu, Y., Zheng, F.: Learn 3D VQA better with active selection and reannotation. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 4610\u20134618 (2025)","DOI":"10.1145\/3746027.3755515"},{"key":"35_CR14","unstructured":"Li, R., Dong, Y.H., Hu, T.S., et al.: 3EED: ground everything everywhere in 3D. arXiv preprint arXiv:2511.01755 (2025)"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Wang, Z.X., Hu, J., Mu, R.H.: Safety of embodied navigation: a survey. In: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, pp. 10714\u201310722 (2025)","DOI":"10.24963\/ijcai.2025\/1189"},{"key":"35_CR16","unstructured":"Wang, Z.H., Lee, S.J., Lee, G.H.: Dynam3D: dynamic layered 3D tokens empower VLM for vision-and-language navigation. arXiv preprint arXiv:2505.11383 (2025)"},{"key":"35_CR17","unstructured":"Nottingham, K., Ammanabrolu, P., Suhr, A., et al.: Do embodied agents dream of pixelated sheep: embodied decision making using language guided world modelling. In: International Conference on Machine Learning, pp. 26311\u201326325. PMLR (2023)"},{"key":"35_CR18","unstructured":"Li, X Q, He X, Zhang L, et al.: A comprehensive survey on world models for embodied AI. arXiv preprint arXiv:2510.16732 (2025)"},{"key":"35_CR19","unstructured":"Zhou, S.Y., Du, Y.L., Yang, Y.C., et al. Learning 3D persistent embodied world models. arXiv preprint arXiv:2505.05495 (2025)"},{"key":"35_CR20","unstructured":"Vepa, A.M., Yu, Y.N., Gan, J.R., et al.: A multimodal LLM approach for visual question answering on multiparametric 3D brain MRI. arXiv preprint arXiv:2509.25889 (2025)"},{"key":"35_CR21","unstructured":"Bai, F., Du, Y.X., Huang, T.J., et al.: M3D: advancing 3D medical image analysis with multi-modal large language models. arXiv preprint arXiv:2404.00578 (2024)"},{"key":"35_CR22","unstructured":"Wang, P., Bai, S., Tan, S.N., et al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"35_CR23","unstructured":"Kazerooni, A.F., Khalili, N., Liu, X.Y., et al.: The brain tumor segmentation (BraTS) challenge 2023: focus on pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs). ArXiv (2024)"},{"key":"35_CR24","unstructured":"Baid, U., Ghodasara, S., Mohan, S., et al.: The rsna-asnr-miccai brats 2021 benchmark on brain tumor segmentation and radiogenomic classification. arXiv preprint arXiv:2107.02314 (2021)"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Zhu, C.M., Wang, T., Zhang, W.W., et al.: LLaVA-3D: a simple yet effective pathway to empowering LMMs with 3D-awareness. arXiv preprint arXiv:2409.18125 (2024)","DOI":"10.1109\/ICCV51701.2025.00409"},{"key":"35_CR26","doi-asserted-by":"crossref","unstructured":"Hong, Y.N., Zhen, H.Y., Chen, P.H., et al.: 3D-LLM: injecting the 3D world into large language models. In: Advances in Neural Information Processing Systems, vol. 36 (2023)","DOI":"10.52202\/075280-0900"},{"key":"35_CR27","doi-asserted-by":"crossref","unstructured":"Liu, H.T., Li, C.Y., Wu, Q.Y., et al.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.52202\/075280-1516"},{"key":"35_CR28","unstructured":"Bolya, D., Fu, C.Z., Dai, X.L., et al.: Token merging: your ViT but faster. In: International Conference on Learning Representations (2023)"},{"key":"35_CR29","unstructured":"Qi, C.R., Su, H., Mo, K.C., et al.: Pointnet: Deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"35_CR30","doi-asserted-by":"crossref","unstructured":"Xu, R.S., Wang, X.L., Wang, T., et al.: PointLLM: empowering large language models to understand point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"35_CR31","unstructured":"Wu, C.Y., Zhang, X.M., Zhang, Y., et al.: Towards generalist foundation models in radiology. arXiv preprint arXiv:2308.02463 (2023)"},{"key":"35_CR32","doi-asserted-by":"publisher","first-page":"59030","DOI":"10.52202\/079017-1883","volume":"37","author":"JW Yao","year":"2024","unstructured":"Yao, J.W., Li, C.M., Xiao, C.R.: Swift sampler: efficient learning of sampler by 10 parameters. Adv. Neural. Inf. Process. Syst. 37, 59030\u201359053 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR33","doi-asserted-by":"crossref","unstructured":"Yao, J.W., Qian, Q., Hu, J.H.: Multi-modal proxy learning towards personalized visual multiple clustering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14066\u201314075 (2024)","DOI":"10.1109\/CVPR52733.2024.01334"},{"key":"35_CR34","doi-asserted-by":"crossref","unstructured":"Zhou, T., Li, G.L., Li, Y.T., et al.: Dual-domain knowledge fusion for interpretable knowledge tracing. Knowl.-Based Syst. 115715 (2026)","DOI":"10.1016\/j.knosys.2026.115715"},{"key":"35_CR35","doi-asserted-by":"publisher","first-page":"82705","DOI":"10.52202\/079017-2629","volume":"37","author":"JW Yao","year":"2024","unstructured":"Yao, J.W., Qian, Q., Hu, J.H.: Customized multiple clustering via multi-modal subspace proxy learning. Adv. Neural. Inf. Process. Syst. 37, 82705\u201382725 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3485-1_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:00:19Z","timestamp":1784145619000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3485-1_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"ISBN":["9789819234844","9789819234851"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3485-1_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]},"assertion":[{"value":"16 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}